Token | convert |
Token ID | 10385 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Kenn | +0.004 |
backbone | +0.004 |
cale | +0.004 |
�� | +0.004 |
scale | +0.004 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
神 | -0.003 |
Premium | -0.003 |
Fountain | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -9.25e-03 |
Pos logit contributions | |
stice | +0.092 |
Hazard | +0.085 |
Premium | +0.082 |
神 | +0.081 |
Fountain | +0.080 |
Neg logit contributions | |
backbone | -0.107 |
Kenn | -0.106 |
scale | -0.105 |
cale | -0.104 |
�� | -0.103 |
Token | to |
Token ID | 284 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.010 |
Premium | +0.010 |
神 | +0.010 |
Fountain | +0.009 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | ays |
Token ID | 592 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
�� | +0.003 |
cale | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
iors | -0.003 |
Token | cale |
Token ID | 38765 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
################################ | +0.000 |
RFC | +0.000 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.014 |
神 | -0.014 |
Fountain | -0.014 |
Token | image |
Token ID | 2939 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
backbone | +0.356 |
Kenn | +0.351 |
scale | +0.350 |
cale | +0.343 |
################################ | +0.336 |
Neg logit contributions | |
stice | -0.557 |
Hazard | -0.522 |
Premium | -0.511 |
神 | -0.507 |
Fountain | -0.498 |
Token | = |
Token ID | 796 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.011 |
cale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.019 |
Hazard | -0.018 |
Premium | -0.018 |
神 | -0.017 |
Fountain | -0.017 |
Token | c |
Token ID | 269 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
backbone | +0.082 |
Kenn | +0.082 |
scale | +0.081 |
cale | +0.080 |
################################ | +0.079 |
Neg logit contributions | |
stice | -0.095 |
Hazard | -0.088 |
Premium | -0.086 |
神 | -0.085 |
Fountain | -0.084 |
Token | v |
Token ID | 85 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
backbone | +0.019 |
Kenn | +0.019 |
scale | +0.018 |
cale | +0.018 |
�� | +0.018 |
Neg logit contributions | |
stice | -0.016 |
Hazard | -0.014 |
Premium | -0.014 |
神 | -0.014 |
Fountain | -0.013 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.006 |
Kenn | -0.006 |
scale | -0.006 |
cale | -0.006 |
################################ | -0.006 |
Token | convert |
Token ID | 10385 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
cale | +0.004 |
scale | +0.004 |
�� | +0.004 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.006 |
神 | -0.006 |
Premium | -0.006 |
Fountain | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
stice | +0.084 |
Hazard | +0.077 |
Premium | +0.075 |
神 | +0.074 |
Fountain | +0.072 |
Neg logit contributions | |
backbone | -0.089 |
Kenn | -0.088 |
scale | -0.088 |
cale | -0.087 |
################################ | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e-03 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.002 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | gr |
Token ID | 1036 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | ays |
Token ID | 592 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.009 |
Token | cale |
Token ID | 38765 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | -0.000 |
Neg logit contributions | |
stice | -0.024 |
Hazard | -0.023 |
Premium | -0.023 |
神 | -0.023 |
Fountain | -0.023 |
Token | image |
Token ID | 2939 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
backbone | +0.402 |
Kenn | +0.399 |
scale | +0.395 |
cale | +0.391 |
################################ | +0.383 |
Neg logit contributions | |
stice | -0.508 |
Hazard | -0.474 |
Premium | -0.461 |
神 | -0.458 |
Fountain | -0.449 |
Token | = |
Token ID | 796 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
backbone | +0.019 |
Kenn | +0.018 |
scale | +0.018 |
cale | +0.018 |
################################ | +0.018 |
Neg logit contributions | |
stice | -0.021 |
Hazard | -0.019 |
Premium | -0.019 |
神 | -0.018 |
Fountain | -0.018 |
Token | c |
Token ID | 269 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
backbone | +0.081 |
Kenn | +0.080 |
scale | +0.080 |
cale | +0.079 |
################################ | +0.077 |
Neg logit contributions | |
stice | -0.096 |
Hazard | -0.089 |
Premium | -0.087 |
神 | -0.086 |
Fountain | -0.084 |
Token | v |
Token ID | 85 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
backbone | +0.021 |
Kenn | +0.021 |
scale | +0.021 |
cale | +0.020 |
################################ | +0.020 |
Neg logit contributions | |
stice | -0.018 |
Hazard | -0.016 |
Premium | -0.016 |
神 | -0.016 |
ottest | -0.015 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.002 |
Premium | -0.002 |
神 | -0.002 |
Fountain | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.006 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.006 |
Token | blurred |
Token ID | 38258 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.002 |
Premium | -0.002 |
神 | -0.002 |
Fountain | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
backbone | +0.116 |
Kenn | +0.115 |
scale | +0.114 |
cale | +0.113 |
################################ | +0.111 |
Neg logit contributions | |
stice | -0.164 |
Hazard | -0.154 |
Premium | -0.150 |
神 | -0.149 |
Fountain | -0.146 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.006 |
Premium | -0.006 |
神 | -0.005 |
Fountain | -0.005 |
Token | ays |
Token ID | 592 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
ottest | -0.001 |
Token | cale |
Token ID | 38765 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
################################ | +0.000 |
cale | +0.000 |
Neg logit contributions | |
stice | -0.018 |
Hazard | -0.018 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.017 |
Token | image |
Token ID | 2939 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
backbone | +0.362 |
Kenn | +0.358 |
scale | +0.355 |
cale | +0.351 |
################################ | +0.342 |
Neg logit contributions | |
stice | -0.532 |
Hazard | -0.499 |
Premium | -0.487 |
神 | -0.484 |
Fountain | -0.475 |
Token | on |
Token ID | 319 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.011 |
cale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | Line |
Token ID | 6910 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.017 |
scale | +0.017 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.010 |
神 | -0.010 |
ottest | -0.010 |
Token | 27 |
Token ID | 2681 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
stice | +0.120 |
Hazard | +0.112 |
Premium | +0.108 |
神 | +0.108 |
Fountain | +0.106 |
Neg logit contributions | |
backbone | -0.115 |
Kenn | -0.114 |
scale | -0.113 |
cale | -0.113 |
################################ | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.012 |
cale | -0.012 |
################################ | -0.012 |
Token | convert |
Token ID | 10385 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
神 | +0.007 |
Premium | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
Kenn | -0.011 |
backbone | -0.011 |
�� | -0.011 |
cale | -0.011 |
scale | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
stice | +0.096 |
Hazard | +0.090 |
Premium | +0.086 |
神 | +0.085 |
Fountain | +0.083 |
Neg logit contributions | |
backbone | -0.115 |
Kenn | -0.114 |
scale | -0.112 |
cale | -0.112 |
�� | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.010 |
神 | +0.010 |
Fountain | +0.010 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.017 |
scale | -0.016 |
cale | -0.016 |
�� | -0.016 |
Token | gr |
Token ID | 1036 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
stice | +0.023 |
Hazard | +0.021 |
Premium | +0.021 |
神 | +0.021 |
Fountain | +0.020 |
Neg logit contributions | |
backbone | -0.018 |
Kenn | -0.018 |
scale | -0.018 |
cale | -0.018 |
################################ | -0.017 |
Token | ays |
Token ID | 592 |
Feature activation | +3.47e-04 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
iors | +0.007 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
�� | -0.008 |
scale | -0.008 |
cale | -0.007 |
Token | cale |
Token ID | 38765 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
################################ | +0.000 |
RFC | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | image |
Token ID | 2939 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
backbone | +0.354 |
Kenn | +0.352 |
scale | +0.347 |
cale | +0.344 |
################################ | +0.336 |
Neg logit contributions | |
stice | -0.532 |
Hazard | -0.499 |
Premium | -0.485 |
神 | -0.484 |
Fountain | -0.475 |
Token | = |
Token ID | 796 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
�� | +0.003 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | c |
Token ID | 269 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
backbone | +0.067 |
Kenn | +0.067 |
scale | +0.066 |
cale | +0.065 |
################################ | +0.064 |
Neg logit contributions | |
stice | -0.076 |
Hazard | -0.071 |
神 | -0.069 |
Premium | -0.069 |
Fountain | -0.067 |
Token | v |
Token ID | 85 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
�� | -0.001 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
�� | -0.009 |
Token | begun |
Token ID | 9258 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
backbone | +0.043 |
Kenn | +0.042 |
scale | +0.042 |
cale | +0.042 |
################################ | +0.041 |
Neg logit contributions | |
stice | -0.044 |
Hazard | -0.041 |
Premium | -0.039 |
神 | -0.039 |
Fountain | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
backbone | +0.006 |
Kenn | +0.006 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | times |
Token ID | 1661 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
Kenn | +0.014 |
backbone | +0.014 |
cale | +0.014 |
scale | +0.014 |
�� | +0.014 |
Neg logit contributions | |
stice | -0.019 |
Hazard | -0.017 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.017 |
Token | cale |
Token ID | 38765 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.000 |
Kenn | -0.000 |
scale | -0.000 |
################################ | -0.000 |
RFC | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
backbone | +0.436 |
Kenn | +0.433 |
scale | +0.430 |
cale | +0.426 |
################################ | +0.417 |
Neg logit contributions | |
stice | -0.445 |
Hazard | -0.412 |
Premium | -0.400 |
神 | -0.397 |
Fountain | -0.388 |
Token | cannot |
Token ID | 2314 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
stice | +0.020 |
Hazard | +0.019 |
Premium | +0.018 |
神 | +0.018 |
Fountain | +0.018 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.017 |
�� | -0.016 |
cale | -0.016 |
################################ | -0.016 |
Token | predict |
Token ID | 4331 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
stice | +0.029 |
Hazard | +0.027 |
神 | +0.026 |
Premium | +0.026 |
Fountain | +0.026 |
Neg logit contributions | |
Kenn | -0.021 |
backbone | -0.021 |
�� | -0.020 |
cale | -0.020 |
################################ | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
backbone | +0.081 |
Kenn | +0.081 |
scale | +0.080 |
cale | +0.079 |
################################ | +0.078 |
Neg logit contributions | |
stice | -0.088 |
Hazard | -0.081 |
Premium | -0.079 |
神 | -0.078 |
Fountain | -0.077 |
Token | on |
Token ID | 319 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.006 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.006 |
Kenn | -0.006 |
scale | -0.006 |
cale | -0.006 |
################################ | -0.006 |
Token | blown |
Token ID | 16318 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
backbone | +0.046 |
Kenn | +0.046 |
scale | +0.045 |
cale | +0.045 |
################################ | +0.044 |
Neg logit contributions | |
stice | -0.043 |
Hazard | -0.040 |
Premium | -0.039 |
神 | -0.039 |
Fountain | -0.038 |
Token | me |
Token ID | 502 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | away |
Token ID | 1497 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.009 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
stice | +0.060 |
Hazard | +0.056 |
Premium | +0.054 |
神 | +0.054 |
Fountain | +0.052 |
Neg logit contributions | |
backbone | -0.059 |
Kenn | -0.059 |
scale | -0.058 |
cale | -0.058 |
################################ | -0.057 |
Token | Dead |
Token ID | 5542 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
backbone | +0.039 |
Kenn | +0.038 |
scale | +0.038 |
cale | +0.038 |
################################ | +0.037 |
Neg logit contributions | |
stice | -0.035 |
Hazard | -0.032 |
Premium | -0.031 |
神 | -0.031 |
Fountain | -0.030 |
Token | Kenn |
Token ID | 7158 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Kenn | +0.082 |
backbone | +0.082 |
scale | +0.081 |
cale | +0.080 |
################################ | +0.078 |
Neg logit contributions | |
stice | -0.086 |
Hazard | -0.080 |
Premium | -0.077 |
神 | -0.077 |
ottest | -0.075 |
Token | ed |
Token ID | 276 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
backbone | +0.287 |
Kenn | +0.281 |
scale | +0.281 |
cale | +0.278 |
################################ | +0.271 |
Neg logit contributions | |
stice | -0.510 |
Hazard | -0.480 |
Premium | -0.468 |
神 | -0.466 |
Fountain | -0.460 |
Token | ys |
Token ID | 893 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
backbone | +0.069 |
Kenn | +0.068 |
scale | +0.067 |
cale | +0.067 |
################################ | +0.065 |
Neg logit contributions | |
stice | -0.087 |
Hazard | -0.081 |
Premium | -0.078 |
神 | -0.078 |
Fountain | -0.077 |
Token | played |
Token ID | 2826 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
backbone | +0.094 |
Kenn | +0.094 |
scale | +0.093 |
cale | +0.092 |
################################ | +0.090 |
Neg logit contributions | |
stice | -0.076 |
Hazard | -0.070 |
Premium | -0.067 |
神 | -0.067 |
Fountain | -0.065 |
Token | with |
Token ID | 351 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.015 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.016 |
Kenn | -0.016 |
scale | -0.016 |
cale | -0.016 |
################################ | -0.016 |
Token | them |
Token ID | 606 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
backbone | +0.020 |
Kenn | +0.019 |
scale | +0.019 |
cale | +0.019 |
################################ | +0.019 |
Neg logit contributions | |
stice | -0.025 |
Hazard | -0.023 |
神 | -0.023 |
Premium | -0.023 |
Fountain | -0.022 |
Token | Scroll |
Token ID | 17428 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | down |
Token ID | 866 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
stice | +0.076 |
Hazard | +0.072 |
Premium | +0.070 |
神 | +0.069 |
Fountain | +0.068 |
Neg logit contributions | |
backbone | -0.055 |
Kenn | -0.055 |
scale | -0.054 |
cale | -0.054 |
################################ | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
backbone | +0.046 |
Kenn | +0.046 |
scale | +0.045 |
cale | +0.045 |
################################ | +0.044 |
Neg logit contributions | |
stice | -0.042 |
Hazard | -0.038 |
Premium | -0.037 |
神 | -0.037 |
Fountain | -0.036 |
Token | click |
Token ID | 3904 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
backbone | +0.097 |
Kenn | +0.097 |
scale | +0.096 |
cale | +0.095 |
################################ | +0.094 |
Neg logit contributions | |
stice | -0.094 |
Hazard | -0.086 |
Premium | -0.084 |
神 | -0.083 |
Fountain | -0.081 |
Token | Vide |
Token ID | 42551 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
backbone | +0.013 |
Kenn | +0.013 |
scale | +0.013 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.011 |
Token | opl |
Token ID | 20106 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
backbone | +0.411 |
Kenn | +0.407 |
scale | +0.405 |
cale | +0.402 |
################################ | +0.394 |
Neg logit contributions | |
stice | -0.368 |
Hazard | -0.339 |
Premium | -0.327 |
神 | -0.326 |
Fountain | -0.318 |
Token | ayer |
Token ID | 2794 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
backbone | +0.035 |
Kenn | +0.035 |
scale | +0.034 |
cale | +0.034 |
################################ | +0.034 |
Neg logit contributions | |
stice | -0.037 |
Hazard | -0.034 |
Premium | -0.033 |
神 | -0.032 |
Fountain | -0.032 |
Token | Input |
Token ID | 23412 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
backbone | +0.051 |
Kenn | +0.050 |
scale | +0.050 |
cale | +0.049 |
################################ | +0.049 |
Neg logit contributions | |
stice | -0.057 |
Hazard | -0.053 |
Premium | -0.051 |
神 | -0.051 |
Fountain | -0.050 |
Token | Stream |
Token ID | 12124 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
stice | +0.165 |
Hazard | +0.153 |
Premium | +0.149 |
神 | +0.149 |
Fountain | +0.145 |
Neg logit contributions | |
backbone | -0.141 |
Kenn | -0.140 |
scale | -0.139 |
cale | -0.137 |
################################ | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
stice | +0.264 |
Hazard | +0.246 |
Premium | +0.239 |
神 | +0.238 |
Fountain | +0.233 |
Neg logit contributions | |
backbone | -0.223 |
Kenn | -0.221 |
scale | -0.219 |
cale | -0.217 |
################################ | -0.213 |
Token | say |
Token ID | 910 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
stice | +0.097 |
Hazard | +0.091 |
Premium | +0.088 |
神 | +0.088 |
Fountain | +0.086 |
Neg logit contributions | |
backbone | -0.075 |
Kenn | -0.075 |
cale | -0.073 |
scale | -0.073 |
################################ | -0.072 |
Token | anything |
Token ID | 1997 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
backbone | +0.014 |
Kenn | +0.014 |
scale | +0.013 |
cale | +0.013 |
################################ | +0.013 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | negative |
Token ID | 4633 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
stice | +0.096 |
Hazard | +0.089 |
Premium | +0.086 |
神 | +0.086 |
Fountain | +0.084 |
Neg logit contributions | |
backbone | -0.089 |
Kenn | -0.089 |
scale | -0.088 |
cale | -0.087 |
################################ | -0.086 |
Token | about |
Token ID | 546 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
backbone | +0.035 |
Kenn | +0.034 |
scale | +0.034 |
cale | +0.034 |
################################ | +0.033 |
Neg logit contributions | |
stice | -0.044 |
Hazard | -0.041 |
Premium | -0.040 |
神 | -0.039 |
Fountain | -0.039 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
backbone | +0.064 |
Kenn | +0.063 |
scale | +0.063 |
cale | +0.062 |
################################ | +0.061 |
Neg logit contributions | |
stice | -0.072 |
Hazard | -0.067 |
Premium | -0.065 |
神 | -0.065 |
Fountain | -0.063 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
backbone | +0.081 |
Kenn | +0.080 |
scale | +0.078 |
cale | +0.077 |
################################ | +0.073 |
Neg logit contributions | |
stice | -0.323 |
Hazard | -0.308 |
Premium | -0.302 |
神 | -0.301 |
Fountain | -0.297 |
Token | in |
Token ID | 287 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
backbone | +0.406 |
Kenn | +0.404 |
scale | +0.401 |
cale | +0.397 |
################################ | +0.390 |
Neg logit contributions | |
stice | -0.361 |
Hazard | -0.332 |
Premium | -0.321 |
神 | -0.318 |
Fountain | -0.311 |
Token | public |
Token ID | 1171 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.014 |
cale | +0.014 |
################################ | +0.014 |
Neg logit contributions | |
stice | -0.017 |
Hazard | -0.016 |
Premium | -0.015 |
神 | -0.015 |
Fountain | -0.015 |
Token | — |
Token ID | 960 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
stice | +0.063 |
Hazard | +0.058 |
Premium | +0.057 |
神 | +0.056 |
Fountain | +0.055 |
Neg logit contributions | |
backbone | -0.057 |
Kenn | -0.057 |
scale | -0.056 |
cale | -0.056 |
################################ | -0.055 |
Token | p |
Token ID | 79 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
backbone | +0.066 |
Kenn | +0.066 |
scale | +0.065 |
cale | +0.065 |
################################ | +0.064 |
Neg logit contributions | |
stice | -0.057 |
Hazard | -0.053 |
Premium | -0.051 |
神 | -0.051 |
Fountain | -0.049 |
Token | iss |
Token ID | 747 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
backbone | +0.066 |
Kenn | +0.065 |
scale | +0.065 |
cale | +0.064 |
################################ | +0.063 |
Neg logit contributions | |
stice | -0.054 |
Hazard | -0.049 |
Premium | -0.048 |
神 | -0.047 |
Fountain | -0.046 |
Token | forcing |
Token ID | 10833 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
stice | +0.042 |
Hazard | +0.039 |
Premium | +0.038 |
神 | +0.037 |
Fountain | +0.036 |
Neg logit contributions | |
backbone | -0.048 |
Kenn | -0.048 |
scale | -0.047 |
cale | -0.047 |
################################ | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | fumble |
Token ID | 41405 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
backbone | +0.013 |
Kenn | +0.013 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.013 |
神 | -0.013 |
ottest | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
stice | +0.064 |
Hazard | +0.059 |
Premium | +0.057 |
神 | +0.057 |
Fountain | +0.056 |
Neg logit contributions | |
backbone | -0.061 |
Kenn | -0.061 |
scale | -0.061 |
cale | -0.060 |
################################ | -0.059 |
Token | Rob |
Token ID | 3851 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
backbone | +0.007 |
Kenn | +0.006 |
scale | +0.006 |
cale | +0.006 |
################################ | +0.006 |
Neg logit contributions | |
stice | -0.007 |
Hazard | -0.007 |
Premium | -0.006 |
神 | -0.006 |
Fountain | -0.006 |
Token | Gron |
Token ID | 40214 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
stice | +0.253 |
Hazard | +0.242 |
Premium | +0.240 |
神 | +0.239 |
ottest | +0.235 |
Neg logit contributions | |
Kenn | -0.017 |
backbone | -0.017 |
scale | -0.016 |
cale | -0.014 |
################################ | -0.010 |
Token | kowski |
Token ID | 26216 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
backbone | +0.447 |
Kenn | +0.443 |
scale | +0.437 |
cale | +0.433 |
################################ | +0.433 |
Neg logit contributions | |
stice | -0.317 |
Hazard | -0.290 |
Premium | -0.276 |
神 | -0.276 |
Fountain | -0.267 |
Token | during |
Token ID | 1141 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
stice | +0.120 |
Hazard | +0.112 |
Premium | +0.108 |
神 | +0.108 |
Fountain | +0.106 |
Neg logit contributions | |
backbone | -0.116 |
Kenn | -0.115 |
scale | -0.114 |
cale | -0.113 |
################################ | -0.111 |
Token | 7 |
Token ID | 767 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
stice | +0.035 |
Hazard | +0.032 |
Premium | +0.031 |
神 | +0.031 |
Fountain | +0.030 |
Neg logit contributions | |
backbone | -0.034 |
Kenn | -0.034 |
cale | -0.033 |
scale | -0.033 |
################################ | -0.033 |
Token | - |
Token ID | 12 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
stice | +0.129 |
Hazard | +0.120 |
Premium | +0.116 |
神 | +0.113 |
Fountain | +0.113 |
Neg logit contributions | |
backbone | -0.131 |
Kenn | -0.129 |
scale | -0.128 |
cale | -0.128 |
�� | -0.126 |
Token | on |
Token ID | 261 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.009 |
神 | +0.009 |
Premium | +0.009 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.017 |
scale | -0.017 |
cale | -0.017 |
################################ | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
backbone | +0.028 |
Kenn | +0.028 |
scale | +0.027 |
cale | +0.027 |
################################ | +0.027 |
Neg logit contributions | |
stice | -0.029 |
Hazard | -0.027 |
Premium | -0.026 |
神 | -0.026 |
Fountain | -0.026 |
Token | sound |
Token ID | 2128 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
backbone | +0.020 |
Kenn | +0.020 |
scale | +0.020 |
cale | +0.020 |
################################ | +0.019 |
Neg logit contributions | |
stice | -0.026 |
Hazard | -0.024 |
Premium | -0.023 |
神 | -0.023 |
Fountain | -0.023 |
Token | booth |
Token ID | 18600 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
backbone | +0.043 |
Kenn | +0.043 |
scale | +0.042 |
cale | +0.042 |
################################ | +0.041 |
Neg logit contributions | |
stice | -0.058 |
Hazard | -0.054 |
Premium | -0.053 |
神 | -0.053 |
Fountain | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.012 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.012 |
cale | -0.011 |
################################ | -0.011 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
backbone | +0.063 |
Kenn | +0.061 |
scale | +0.060 |
�� | +0.057 |
cale | +0.056 |
Neg logit contributions | |
stice | -0.318 |
Hazard | -0.303 |
Premium | -0.298 |
神 | -0.297 |
Fountain | -0.293 |
Token | puts |
Token ID | 7584 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
backbone | +0.376 |
Kenn | +0.374 |
scale | +0.371 |
cale | +0.366 |
################################ | +0.360 |
Neg logit contributions | |
stice | -0.378 |
Hazard | -0.349 |
Premium | -0.339 |
神 | -0.336 |
Fountain | -0.328 |
Token | on |
Token ID | 319 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
stice | +0.064 |
Hazard | +0.060 |
Premium | +0.058 |
神 | +0.058 |
Fountain | +0.057 |
Neg logit contributions | |
backbone | -0.052 |
Kenn | -0.052 |
scale | -0.052 |
cale | -0.051 |
################################ | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.016 |
Hazard | -0.015 |
Premium | -0.015 |
神 | -0.015 |
Fountain | -0.015 |
Token | pair |
Token ID | 5166 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
backbone | +0.024 |
Kenn | +0.024 |
scale | +0.024 |
cale | +0.023 |
################################ | +0.023 |
Neg logit contributions | |
stice | -0.029 |
Hazard | -0.027 |
Premium | -0.026 |
神 | -0.026 |
Fountain | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
stice | +0.037 |
Hazard | +0.035 |
Premium | +0.034 |
神 | +0.034 |
Fountain | +0.033 |
Neg logit contributions | |
backbone | -0.035 |
Kenn | -0.034 |
scale | -0.034 |
cale | -0.034 |
�� | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
backbone | +0.035 |
Kenn | +0.034 |
scale | +0.034 |
cale | +0.034 |
################################ | +0.033 |
Neg logit contributions | |
stice | -0.034 |
Hazard | -0.032 |
Premium | -0.030 |
神 | -0.030 |
Fountain | -0.030 |
Token | line |
Token ID | 1627 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
stice | +0.185 |
Hazard | +0.171 |
Premium | +0.166 |
神 | +0.165 |
Fountain | +0.162 |
Neg logit contributions | |
backbone | -0.174 |
Kenn | -0.173 |
scale | -0.171 |
cale | -0.170 |
################################ | -0.167 |
Token | � |
Token ID | 447 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.006 |
Premium | -0.006 |
神 | -0.006 |
Fountain | -0.005 |
Token | � |
Token ID | 251 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | Quant |
Token ID | 16972 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.005 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | rill |
Token ID | 20190 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
backbone | +0.275 |
Kenn | +0.272 |
scale | +0.269 |
cale | +0.266 |
################################ | +0.260 |
Neg logit contributions | |
stice | -0.475 |
Hazard | -0.447 |
Premium | -0.435 |
神 | -0.433 |
Fountain | -0.426 |
Token | said |
Token ID | 531 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
backbone | +0.130 |
Kenn | +0.129 |
scale | +0.128 |
cale | +0.127 |
################################ | +0.125 |
Neg logit contributions | |
stice | -0.117 |
Hazard | -0.108 |
Premium | -0.104 |
神 | -0.104 |
Fountain | -0.101 |
Token | with |
Token ID | 351 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Kenn | +0.033 |
backbone | +0.033 |
cale | +0.032 |
scale | +0.032 |
################################ | +0.032 |
Neg logit contributions | |
stice | -0.039 |
Hazard | -0.036 |
Premium | -0.035 |
神 | -0.035 |
Fountain | -0.034 |
Token | snap |
Token ID | 11495 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
backbone | +0.024 |
Kenn | +0.024 |
scale | +0.024 |
cale | +0.024 |
################################ | +0.023 |
Neg logit contributions | |
stice | -0.025 |
Hazard | -0.024 |
Premium | -0.023 |
神 | -0.023 |
Fountain | -0.022 |
Token | he |
Token ID | 339 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
backbone | +0.068 |
Kenn | +0.068 |
scale | +0.068 |
cale | +0.067 |
################################ | +0.065 |
Neg logit contributions | |
stice | -0.053 |
Hazard | -0.048 |
Premium | -0.046 |
神 | -0.046 |
Fountain | -0.045 |
Token | transferred |
Token ID | 11172 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.002 |
Premium | -0.002 |
神 | -0.002 |
Fountain | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
backbone | +0.051 |
Kenn | +0.051 |
scale | +0.050 |
cale | +0.050 |
################################ | +0.049 |
Neg logit contributions | |
stice | -0.042 |
Hazard | -0.038 |
Premium | -0.037 |
神 | -0.037 |
ottest | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.005 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | Quant |
Token ID | 16972 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.009 |
Fountain | -0.009 |
Token | ico |
Token ID | 3713 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
backbone | +0.458 |
Kenn | +0.455 |
scale | +0.454 |
cale | +0.451 |
################################ | +0.441 |
Neg logit contributions | |
stice | -0.293 |
Hazard | -0.260 |
Premium | -0.253 |
神 | -0.251 |
Fountain | -0.243 |
Token | Marine |
Token ID | 11000 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
stice | +0.085 |
Hazard | +0.080 |
Premium | +0.077 |
神 | +0.076 |
Fountain | +0.075 |
Neg logit contributions | |
backbone | -0.070 |
Kenn | -0.069 |
scale | -0.068 |
cale | -0.068 |
################################ | -0.067 |
Token | Corps |
Token ID | 12778 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
backbone | +0.239 |
Kenn | +0.237 |
scale | +0.235 |
cale | +0.232 |
################################ | +0.226 |
Neg logit contributions | |
stice | -0.381 |
Hazard | -0.358 |
Premium | -0.349 |
神 | -0.348 |
Fountain | -0.341 |
Token | Base |
Token ID | 7308 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
backbone | +0.112 |
Kenn | +0.112 |
scale | +0.111 |
cale | +0.110 |
################################ | +0.108 |
Neg logit contributions | |
stice | -0.109 |
Hazard | -0.101 |
Premium | -0.097 |
神 | -0.096 |
Fountain | -0.095 |
Token | in |
Token ID | 287 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
stice | +0.068 |
Hazard | +0.063 |
Premium | +0.061 |
神 | +0.061 |
Fountain | +0.059 |
Neg logit contributions | |
backbone | -0.067 |
Kenn | -0.067 |
scale | -0.066 |
cale | -0.066 |
################################ | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
stice | +0.061 |
Hazard | +0.057 |
Premium | +0.055 |
神 | +0.055 |
Fountain | +0.054 |
Neg logit contributions | |
backbone | -0.056 |
Kenn | -0.055 |
scale | -0.055 |
cale | -0.054 |
################################ | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | deal |
Token ID | 1730 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
backbone | +0.040 |
Kenn | +0.040 |
scale | +0.040 |
cale | +0.040 |
################################ | +0.039 |
Neg logit contributions | |
stice | -0.049 |
Hazard | -0.046 |
Premium | -0.044 |
神 | -0.044 |
Fountain | -0.043 |
Token | behind |
Token ID | 2157 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
backbone | +0.075 |
Kenn | +0.075 |
scale | +0.074 |
cale | +0.074 |
################################ | +0.072 |
Neg logit contributions | |
stice | -0.073 |
Hazard | -0.068 |
Premium | -0.066 |
神 | -0.065 |
Fountain | -0.064 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
stice | +0.074 |
Hazard | +0.069 |
Premium | +0.067 |
神 | +0.066 |
Fountain | +0.065 |
Neg logit contributions | |
backbone | -0.065 |
Kenn | -0.065 |
scale | -0.064 |
cale | -0.063 |
################################ | -0.062 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
backbone | +0.061 |
Kenn | +0.058 |
scale | +0.058 |
cale | +0.054 |
�� | +0.053 |
Neg logit contributions | |
stice | -0.319 |
Hazard | -0.304 |
Premium | -0.299 |
神 | -0.299 |
Fountain | -0.294 |
Token | Market |
Token ID | 5991 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
backbone | +0.362 |
Kenn | +0.361 |
scale | +0.358 |
cale | +0.354 |
################################ | +0.347 |
Neg logit contributions | |
stice | -0.385 |
Hazard | -0.357 |
Premium | -0.346 |
神 | -0.344 |
ottest | -0.337 |
Token | is |
Token ID | 318 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
backbone | +0.048 |
Kenn | +0.048 |
scale | +0.048 |
cale | +0.047 |
################################ | +0.046 |
Neg logit contributions | |
stice | -0.045 |
Hazard | -0.042 |
Premium | -0.041 |
神 | -0.040 |
Fountain | -0.039 |
Token | complicated |
Token ID | 8253 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
stice | +0.029 |
Hazard | +0.027 |
Premium | +0.026 |
神 | +0.026 |
Fountain | +0.025 |
Neg logit contributions | |
backbone | -0.027 |
Kenn | -0.027 |
scale | -0.027 |
cale | -0.027 |
################################ | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
backbone | +0.026 |
Kenn | +0.026 |
scale | +0.026 |
cale | +0.026 |
################################ | +0.025 |
Neg logit contributions | |
stice | -0.029 |
Hazard | -0.027 |
Premium | -0.026 |
神 | -0.026 |
Fountain | -0.026 |
Token | even |
Token ID | 772 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
backbone | +0.092 |
Kenn | +0.092 |
scale | +0.091 |
cale | +0.090 |
################################ | +0.088 |
Neg logit contributions | |
stice | -0.094 |
Hazard | -0.087 |
Premium | -0.084 |
神 | -0.084 |
Fountain | -0.082 |
Token | it |
Token ID | 340 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.015 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
backbone | +0.077 |
Kenn | +0.076 |
scale | +0.076 |
cale | +0.075 |
################################ | +0.074 |
Neg logit contributions | |
stice | -0.058 |
Hazard | -0.053 |
Premium | -0.051 |
神 | -0.051 |
Fountain | -0.049 |
Token | hit |
Token ID | 2277 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.015 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
cale | -0.011 |
scale | -0.011 |
################################ | -0.011 |
Token | Quant |
Token ID | 16972 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
stice | +0.050 |
Hazard | +0.047 |
Premium | +0.045 |
神 | +0.045 |
Fountain | +0.044 |
Neg logit contributions | |
backbone | -0.043 |
Kenn | -0.042 |
scale | -0.041 |
cale | -0.041 |
################################ | -0.041 |
Token | rill |
Token ID | 20190 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
backbone | +0.276 |
Kenn | +0.273 |
scale | +0.270 |
cale | +0.266 |
################################ | +0.261 |
Neg logit contributions | |
stice | -0.468 |
Hazard | -0.441 |
Premium | -0.428 |
神 | -0.427 |
Fountain | -0.419 |
Token | as |
Token ID | 355 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
backbone | +0.114 |
Kenn | +0.113 |
scale | +0.112 |
cale | +0.111 |
################################ | +0.109 |
Neg logit contributions | |
stice | -0.120 |
Hazard | -0.111 |
Premium | -0.108 |
神 | -0.107 |
Fountain | -0.105 |
Token | he |
Token ID | 339 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
stice | +0.069 |
Hazard | +0.065 |
Premium | +0.063 |
神 | +0.062 |
Fountain | +0.062 |
Neg logit contributions | |
backbone | -0.051 |
Kenn | -0.050 |
scale | -0.050 |
cale | -0.050 |
################################ | -0.049 |
Token | warmed |
Token ID | 38794 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
backbone | +0.063 |
Kenn | +0.063 |
scale | +0.062 |
cale | +0.062 |
################################ | +0.061 |
Neg logit contributions | |
stice | -0.054 |
Hazard | -0.050 |
Premium | -0.048 |
神 | -0.048 |
Fountain | -0.047 |
Token | up |
Token ID | 510 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
stice | +0.117 |
Hazard | +0.109 |
Premium | +0.106 |
神 | +0.105 |
Fountain | +0.103 |
Neg logit contributions | |
backbone | -0.099 |
Kenn | -0.098 |
scale | -0.097 |
cale | -0.097 |
################################ | -0.095 |
Token | sm |
Token ID | 5796 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
stice | +0.068 |
Hazard | +0.063 |
Premium | +0.061 |
神 | +0.060 |
Fountain | +0.059 |
Neg logit contributions | |
backbone | -0.072 |
Kenn | -0.071 |
scale | -0.070 |
cale | -0.070 |
################################ | -0.069 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
stice | +0.099 |
Hazard | +0.093 |
Premium | +0.090 |
神 | +0.090 |
Fountain | +0.088 |
Neg logit contributions | |
backbone | -0.079 |
Kenn | -0.078 |
scale | -0.077 |
cale | -0.076 |
################################ | -0.075 |
Token | Whatever |
Token ID | 21875 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
backbone | +0.121 |
Kenn | +0.120 |
scale | +0.119 |
cale | +0.118 |
################################ | +0.116 |
Neg logit contributions | |
stice | -0.126 |
Hazard | -0.117 |
Premium | -0.113 |
神 | -0.113 |
Fountain | -0.110 |
Token | reason |
Token ID | 1738 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
stice | +0.110 |
Hazard | +0.101 |
Premium | +0.099 |
神 | +0.098 |
ottest | +0.096 |
Neg logit contributions | |
backbone | -0.114 |
Kenn | -0.114 |
scale | -0.113 |
cale | -0.111 |
################################ | -0.109 |
Token | Cal |
Token ID | 2199 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
backbone | +0.043 |
Kenn | +0.043 |
scale | +0.043 |
cale | +0.042 |
################################ | +0.041 |
Neg logit contributions | |
stice | -0.044 |
Hazard | -0.040 |
Premium | -0.039 |
神 | -0.039 |
ottest | -0.038 |
Token | Quant |
Token ID | 16972 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
backbone | +0.074 |
Kenn | +0.074 |
scale | +0.073 |
cale | +0.072 |
################################ | +0.071 |
Neg logit contributions | |
stice | -0.080 |
Hazard | -0.075 |
Premium | -0.072 |
神 | -0.072 |
Fountain | -0.070 |
Token | rill |
Token ID | 20190 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
backbone | +0.359 |
Kenn | +0.358 |
scale | +0.355 |
cale | +0.351 |
################################ | +0.342 |
Neg logit contributions | |
stice | -0.383 |
Hazard | -0.355 |
Premium | -0.346 |
神 | -0.344 |
Fountain | -0.336 |
Token | had |
Token ID | 550 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
backbone | +0.120 |
Kenn | +0.119 |
scale | +0.118 |
cale | +0.117 |
################################ | +0.115 |
Neg logit contributions | |
stice | -0.113 |
Hazard | -0.104 |
Premium | -0.101 |
神 | -0.100 |
Fountain | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
stice | +0.040 |
Hazard | +0.037 |
Premium | +0.036 |
神 | +0.036 |
Fountain | +0.035 |
Neg logit contributions | |
backbone | -0.043 |
Kenn | -0.043 |
scale | -0.043 |
cale | -0.042 |
################################ | -0.041 |
Token | stress |
Token ID | 5503 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
cale | -0.010 |
scale | -0.010 |
################################ | -0.010 |
Token | even |
Token ID | 772 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
backbone | +0.096 |
Kenn | +0.095 |
scale | +0.094 |
cale | +0.094 |
################################ | +0.092 |
Neg logit contributions | |
stice | -0.109 |
Hazard | -0.102 |
Premium | -0.098 |
神 | -0.098 |
Fountain | -0.096 |
Token | The |
Token ID | 464 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
神 | +0.003 |
Premium | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | truth |
Token ID | 3872 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
backbone | +0.052 |
Kenn | +0.051 |
scale | +0.051 |
cale | +0.051 |
################################ | +0.050 |
Neg logit contributions | |
stice | -0.061 |
Hazard | -0.057 |
Premium | -0.055 |
神 | -0.055 |
Fountain | -0.054 |
Token | is |
Token ID | 318 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
stice | +0.192 |
Hazard | +0.178 |
Premium | +0.172 |
神 | +0.170 |
Fountain | +0.166 |
Neg logit contributions | |
backbone | -0.212 |
Kenn | -0.211 |
scale | -0.210 |
cale | -0.207 |
################################ | -0.203 |
Token | that |
Token ID | 326 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
stice | +0.026 |
Hazard | +0.024 |
Premium | +0.023 |
神 | +0.023 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.024 |
Kenn | -0.024 |
scale | -0.024 |
cale | -0.023 |
################################ | -0.023 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
backbone | +0.062 |
Kenn | +0.059 |
scale | +0.058 |
cale | +0.054 |
�� | +0.054 |
Neg logit contributions | |
stice | -0.323 |
Hazard | -0.309 |
Premium | -0.303 |
神 | -0.302 |
Fountain | -0.298 |
Token | has |
Token ID | 468 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
backbone | +0.379 |
Kenn | +0.377 |
scale | +0.375 |
cale | +0.370 |
################################ | +0.364 |
Neg logit contributions | |
stice | -0.363 |
Hazard | -0.335 |
Premium | -0.324 |
神 | -0.321 |
Fountain | -0.314 |
Token | always |
Token ID | 1464 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.011 |
神 | -0.011 |
Fountain | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.008 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
stice | +0.047 |
Hazard | +0.044 |
神 | +0.042 |
Premium | +0.042 |
Fountain | +0.041 |
Neg logit contributions | |
Kenn | -0.038 |
backbone | -0.038 |
cale | -0.038 |
scale | -0.038 |
################################ | -0.037 |
Token | streak |
Token ID | 15113 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
backbone | +0.022 |
Kenn | +0.022 |
scale | +0.022 |
cale | +0.022 |
################################ | +0.021 |
Neg logit contributions | |
stice | -0.031 |
Hazard | -0.029 |
Premium | -0.028 |
神 | -0.028 |
Fountain | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
stice | +0.131 |
Hazard | +0.121 |
Premium | +0.118 |
神 | +0.117 |
ottest | +0.114 |
Neg logit contributions | |
backbone | -0.129 |
Kenn | -0.129 |
scale | -0.128 |
cale | -0.126 |
################################ | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
backbone | +0.007 |
Kenn | +0.007 |
scale | +0.007 |
cale | +0.006 |
################################ | +0.006 |
Neg logit contributions | |
stice | -0.007 |
Hazard | -0.006 |
Premium | -0.006 |
神 | -0.006 |
ottest | -0.006 |
Token | six |
Token ID | 2237 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
stice | +0.031 |
Hazard | +0.029 |
Premium | +0.028 |
神 | +0.028 |
Fountain | +0.027 |
Neg logit contributions | |
backbone | -0.029 |
Kenn | -0.029 |
scale | -0.029 |
cale | -0.028 |
################################ | -0.028 |
Token | hour |
Token ID | 9769 |
Feature activation | -8.13e-04 |
Pos logit contributions | |
backbone | +0.007 |
Kenn | +0.007 |
scale | +0.007 |
cale | +0.007 |
################################ | +0.007 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | Ascension |
Token ID | 41416 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
stice | +0.000 |
Hazard | +0.000 |
Premium | +0.000 |
神 | +0.000 |
Fountain | +0.000 |
Neg logit contributions | |
backbone | -0.000 |
Kenn | -0.000 |
scale | -0.000 |
cale | -0.000 |
################################ | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
backbone | +0.359 |
Kenn | +0.357 |
scale | +0.354 |
cale | +0.350 |
################################ | +0.344 |
Neg logit contributions | |
stice | -0.381 |
Hazard | -0.353 |
Premium | -0.343 |
神 | -0.341 |
Fountain | -0.333 |
Token | Sy |
Token ID | 1632 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
Fountain | -0.008 |
Token | fy |
Token ID | 24928 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
backbone | +0.094 |
Kenn | +0.093 |
scale | +0.092 |
cale | +0.091 |
################################ | +0.090 |
Neg logit contributions | |
stice | -0.089 |
Hazard | -0.082 |
Premium | -0.079 |
神 | -0.079 |
Fountain | -0.077 |
Token | has |
Token ID | 468 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.009 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
scale | -0.010 |
cale | -0.010 |
################################ | -0.010 |
Token | teamed |
Token ID | 31230 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.009 |
Token | its |
Token ID | 663 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
backbone | +0.137 |
Kenn | +0.137 |
scale | +0.135 |
cale | +0.134 |
################################ | +0.132 |
Neg logit contributions | |
stice | -0.147 |
Hazard | -0.136 |
Premium | -0.132 |
神 | -0.132 |
Fountain | -0.129 |
Token | look |
Token ID | 804 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.014 |
Hazard | -0.013 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
backbone | +0.065 |
Kenn | +0.062 |
scale | +0.062 |
�� | +0.058 |
cale | +0.057 |
Neg logit contributions | |
stice | -0.324 |
Hazard | -0.309 |
Premium | -0.303 |
神 | -0.302 |
Fountain | -0.298 |
Token | will |
Token ID | 481 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
backbone | +0.363 |
Kenn | +0.361 |
scale | +0.358 |
cale | +0.354 |
################################ | +0.347 |
Neg logit contributions | |
stice | -0.373 |
Hazard | -0.345 |
Premium | -0.334 |
神 | -0.332 |
Fountain | -0.324 |
Token | select |
Token ID | 2922 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
backbone | +0.042 |
Kenn | +0.041 |
cale | +0.041 |
scale | +0.040 |
################################ | +0.040 |
Neg logit contributions | |
stice | -0.054 |
Hazard | -0.050 |
Premium | -0.049 |
神 | -0.049 |
Fountain | -0.048 |
Token | who |
Token ID | 508 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.017 |
scale | +0.017 |
cale | +0.017 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.019 |
Hazard | -0.018 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.017 |
Token | will |
Token ID | 481 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
backbone | +0.040 |
Kenn | +0.040 |
cale | +0.039 |
scale | +0.039 |
################################ | +0.038 |
Neg logit contributions | |
stice | -0.055 |
Hazard | -0.052 |
Premium | -0.050 |
神 | -0.050 |
Fountain | -0.049 |
Token | humanitarian |
Token ID | 15706 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.013 |
神 | -0.013 |
Fountain | -0.013 |
Token | movement |
Token ID | 3356 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
backbone | +0.118 |
Kenn | +0.117 |
scale | +0.116 |
cale | +0.115 |
################################ | +0.113 |
Neg logit contributions | |
stice | -0.135 |
Hazard | -0.126 |
Premium | -0.122 |
神 | -0.121 |
Fountain | -0.119 |
Token | as |
Token ID | 355 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
backbone | +0.066 |
Kenn | +0.065 |
scale | +0.065 |
cale | +0.064 |
################################ | +0.063 |
Neg logit contributions | |
stice | -0.074 |
Hazard | -0.068 |
Premium | -0.067 |
神 | -0.066 |
Fountain | -0.065 |
Token | an |
Token ID | 281 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
stice | +0.051 |
Hazard | +0.047 |
Premium | +0.046 |
神 | +0.046 |
Fountain | +0.045 |
Neg logit contributions | |
backbone | -0.044 |
Kenn | -0.043 |
scale | -0.043 |
cale | -0.043 |
################################ | -0.042 |
Token | intrinsic |
Token ID | 28327 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | backbone |
Token ID | 32774 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
backbone | +0.129 |
Kenn | +0.129 |
scale | +0.128 |
cale | +0.126 |
################################ | +0.124 |
Neg logit contributions | |
stice | -0.120 |
Hazard | -0.111 |
Premium | -0.107 |
神 | -0.107 |
Fountain | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
backbone | +0.351 |
Kenn | +0.346 |
scale | +0.345 |
cale | +0.340 |
################################ | +0.334 |
Neg logit contributions | |
stice | -0.387 |
Hazard | -0.359 |
Premium | -0.349 |
神 | -0.347 |
Fountain | -0.339 |
Token | our |
Token ID | 674 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
backbone | +0.024 |
Kenn | +0.024 |
scale | +0.024 |
cale | +0.024 |
################################ | +0.023 |
Neg logit contributions | |
stice | -0.024 |
Hazard | -0.022 |
Premium | -0.021 |
神 | -0.021 |
Fountain | -0.021 |
Token | politics |
Token ID | 4819 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
stice | +0.058 |
Hazard | +0.054 |
神 | +0.053 |
Premium | +0.052 |
Fountain | +0.052 |
Neg logit contributions | |
Kenn | -0.044 |
backbone | -0.044 |
cale | -0.043 |
scale | -0.043 |
################################ | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
stice | +0.081 |
Hazard | +0.075 |
Premium | +0.073 |
神 | +0.073 |
Fountain | +0.071 |
Neg logit contributions | |
backbone | -0.069 |
Kenn | -0.068 |
scale | -0.068 |
cale | -0.067 |
################################ | -0.066 |
Token | Vermont |
Token ID | 16033 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Kenn | +0.017 |
backbone | +0.017 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.013 |
神 | -0.013 |
ottest | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.012 |
cale | -0.012 |
################################ | -0.012 |
Token | Parts |
Token ID | 22349 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.010 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.009 |
Token | Unknown |
Token ID | 16185 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Kenn | +0.032 |
backbone | +0.032 |
scale | +0.032 |
cale | +0.032 |
################################ | +0.031 |
Neg logit contributions | |
stice | -0.020 |
Hazard | -0.018 |
Premium | -0.018 |
神 | -0.017 |
Fountain | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
stice | +0.082 |
Hazard | +0.076 |
Premium | +0.074 |
神 | +0.073 |
Fountain | +0.072 |
Neg logit contributions | |
backbone | -0.072 |
Kenn | -0.071 |
scale | -0.070 |
cale | -0.070 |
################################ | -0.068 |
Token | Bour |
Token ID | 20576 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | dain |
Token ID | 27162 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
backbone | +0.062 |
Kenn | +0.060 |
scale | +0.059 |
�� | +0.056 |
cale | +0.055 |
Neg logit contributions | |
stice | -0.316 |
Hazard | -0.302 |
Premium | -0.297 |
神 | -0.295 |
Fountain | -0.291 |
Token | greets |
Token ID | 45204 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
backbone | +0.368 |
Kenn | +0.367 |
scale | +0.364 |
cale | +0.358 |
################################ | +0.353 |
Neg logit contributions | |
stice | -0.364 |
Hazard | -0.336 |
Premium | -0.326 |
神 | -0.322 |
Fountain | -0.315 |
Token | his |
Token ID | 465 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
stice | +0.163 |
Hazard | +0.152 |
Premium | +0.147 |
神 | +0.147 |
Fountain | +0.144 |
Neg logit contributions | |
backbone | -0.138 |
Kenn | -0.137 |
scale | -0.136 |
cale | -0.135 |
################################ | -0.132 |
Token | producers |
Token ID | 11408 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
backbone | +0.026 |
Kenn | +0.026 |
scale | +0.025 |
cale | +0.025 |
################################ | +0.025 |
Neg logit contributions | |
stice | -0.036 |
Hazard | -0.034 |
Premium | -0.033 |
神 | -0.033 |
Fountain | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | technicians |
Token ID | 33519 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
backbone | +0.044 |
Kenn | +0.044 |
scale | +0.043 |
cale | +0.043 |
################################ | +0.042 |
Neg logit contributions | |
stice | -0.050 |
Hazard | -0.046 |
Premium | -0.045 |
神 | -0.045 |
Fountain | -0.044 |
Token | insulin |
Token ID | 14588 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | ). |
Token ID | 737 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
backbone | +0.082 |
Kenn | +0.082 |
scale | +0.081 |
cale | +0.080 |
################################ | +0.079 |
Neg logit contributions | |
stice | -0.075 |
Hazard | -0.070 |
Premium | -0.067 |
神 | -0.067 |
Fountain | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
stice | +0.092 |
Hazard | +0.085 |
Premium | +0.082 |
神 | +0.082 |
Fountain | +0.080 |
Neg logit contributions | |
backbone | -0.095 |
Kenn | -0.095 |
scale | -0.094 |
cale | -0.093 |
################################ | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.009 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
scale | -0.010 |
cale | -0.010 |
�� | -0.010 |
Token | BUT |
Token ID | 47526 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | did |
Token ID | 750 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
stice | +0.394 |
Hazard | +0.366 |
Premium | +0.355 |
神 | +0.353 |
Fountain | +0.346 |
Neg logit contributions | |
backbone | -0.365 |
Kenn | -0.363 |
scale | -0.360 |
cale | -0.356 |
################################ | -0.350 |
Token | you |
Token ID | 345 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
backbone | +0.048 |
Kenn | +0.048 |
scale | +0.048 |
cale | +0.047 |
################################ | +0.046 |
Neg logit contributions | |
stice | -0.046 |
Hazard | -0.042 |
Premium | -0.041 |
神 | -0.041 |
Fountain | -0.040 |
Token | know |
Token ID | 760 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.015 |
Premium | +0.015 |
神 | +0.015 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.009 |
cale | -0.009 |
�� | -0.009 |
scale | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
backbone | +0.046 |
Kenn | +0.046 |
scale | +0.046 |
cale | +0.045 |
################################ | +0.044 |
Neg logit contributions | |
stice | -0.042 |
Hazard | -0.039 |
Premium | -0.038 |
神 | -0.038 |
Fountain | -0.037 |
Token | can |
Token ID | 460 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.010 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
################################ | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | � |
Token ID | 251 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -9.15e-03 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | BUT |
Token ID | 47526 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | LER |
Token ID | 39878 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
stice | +0.395 |
Hazard | +0.366 |
Premium | +0.355 |
神 | +0.354 |
Fountain | +0.346 |
Neg logit contributions | |
backbone | -0.363 |
Kenn | -0.361 |
scale | -0.358 |
cale | -0.354 |
################################ | -0.347 |
Token | ALWAYS |
Token ID | 49576 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
backbone | +0.037 |
Kenn | +0.037 |
scale | +0.037 |
cale | +0.036 |
################################ | +0.036 |
Neg logit contributions | |
stice | -0.038 |
Hazard | -0.035 |
Premium | -0.034 |
神 | -0.034 |
Fountain | -0.033 |
Token | thought |
Token ID | 1807 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
backbone | +0.025 |
Kenn | +0.025 |
scale | +0.025 |
cale | +0.025 |
################################ | +0.024 |
Neg logit contributions | |
stice | -0.026 |
Hazard | -0.024 |
Premium | -0.023 |
神 | -0.023 |
Fountain | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
stice | +0.055 |
Hazard | +0.052 |
Premium | +0.050 |
神 | +0.050 |
Fountain | +0.049 |
Neg logit contributions | |
backbone | -0.044 |
Kenn | -0.044 |
scale | -0.044 |
cale | -0.043 |
################################ | -0.043 |
Token | had |
Token ID | 550 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
backbone | +0.057 |
Kenn | +0.057 |
scale | +0.057 |
cale | +0.056 |
################################ | +0.055 |
Neg logit contributions | |
stice | -0.050 |
Hazard | -0.046 |
Premium | -0.045 |
神 | -0.044 |
Fountain | -0.043 |
Token | Cold |
Token ID | 10250 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
stice | +0.015 |
Hazard | +0.014 |
Premium | +0.013 |
神 | +0.013 |
Fountain | +0.013 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.012 |
cale | -0.011 |
################################ | -0.011 |
Token | War |
Token ID | 1810 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
stice | +0.055 |
Hazard | +0.052 |
Premium | +0.050 |
神 | +0.050 |
Fountain | +0.049 |
Neg logit contributions | |
backbone | -0.030 |
Kenn | -0.030 |
scale | -0.029 |
cale | -0.029 |
################################ | -0.028 |
Token | worries |
Token ID | 18572 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
backbone | +0.035 |
Kenn | +0.035 |
scale | +0.034 |
cale | +0.034 |
################################ | +0.033 |
Neg logit contributions | |
stice | -0.049 |
Hazard | -0.046 |
Premium | -0.044 |
神 | -0.044 |
Fountain | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.011 |
cale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.011 |
神 | -0.011 |
Fountain | -0.011 |
Token | A |
Token ID | 317 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | fountain |
Token ID | 29420 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
stice | +0.369 |
Hazard | +0.342 |
Premium | +0.333 |
神 | +0.330 |
ottest | +0.322 |
Neg logit contributions | |
backbone | -0.383 |
Kenn | -0.379 |
scale | -0.378 |
cale | -0.371 |
################################ | -0.364 |
Token | w |
Token ID | 266 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
ottest | +0.008 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
scale | -0.009 |
cale | -0.009 |
################################ | -0.009 |
Token | ading |
Token ID | 4980 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
stice | +0.111 |
Hazard | +0.103 |
Premium | +0.100 |
神 | +0.099 |
Fountain | +0.098 |
Neg logit contributions | |
backbone | -0.100 |
Kenn | -0.099 |
scale | -0.098 |
cale | -0.098 |
################################ | -0.096 |
Token | pool |
Token ID | 5933 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
stice | +0.027 |
Hazard | +0.025 |
Premium | +0.024 |
神 | +0.024 |
ottest | +0.023 |
Neg logit contributions | |
backbone | -0.026 |
Kenn | -0.026 |
scale | -0.026 |
cale | -0.026 |
################################ | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
stice | +0.109 |
Hazard | +0.101 |
Premium | +0.098 |
神 | +0.098 |
Fountain | +0.095 |
Neg logit contributions | |
backbone | -0.100 |
Kenn | -0.099 |
scale | -0.098 |
cale | -0.097 |
################################ | -0.095 |
Token | options |
Token ID | 3689 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Kenn | +0.120 |
backbone | +0.119 |
cale | +0.117 |
scale | +0.117 |
�� | +0.116 |
Neg logit contributions | |
stice | -0.140 |
Hazard | -0.131 |
Premium | -0.127 |
神 | -0.126 |
Fountain | -0.124 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
Kenn | +0.100 |
backbone | +0.100 |
scale | +0.098 |
cale | +0.098 |
################################ | +0.097 |
Neg logit contributions | |
stice | -0.109 |
Hazard | -0.102 |
Premium | -0.099 |
神 | -0.098 |
Fountain | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
stice | +0.013 |
Hazard | +0.012 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.012 |
cale | -0.012 |
################################ | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
cale | +0.002 |
scale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.002 |
Token | new |
Token ID | 649 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Kenn | +0.006 |
backbone | +0.006 |
cale | +0.006 |
�� | +0.006 |
scale | +0.005 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.007 |
Premium | -0.007 |
神 | -0.007 |
Fountain | -0.007 |
Token | Premium |
Token ID | 17315 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
stice | +0.154 |
Hazard | +0.144 |
Premium | +0.140 |
神 | +0.138 |
Fountain | +0.137 |
Neg logit contributions | |
Kenn | -0.126 |
backbone | -0.125 |
cale | -0.124 |
scale | -0.123 |
################################ | -0.122 |
Token | pricing |
Token ID | 13045 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
stice | +0.402 |
Hazard | +0.377 |
Premium | +0.368 |
神 | +0.358 |
Fountain | +0.357 |
Neg logit contributions | |
backbone | -0.338 |
Kenn | -0.337 |
cale | -0.332 |
scale | -0.330 |
�� | -0.329 |
Token | model |
Token ID | 2746 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
backbone | +0.082 |
Kenn | +0.081 |
scale | +0.080 |
cale | +0.080 |
################################ | +0.078 |
Neg logit contributions | |
stice | -0.096 |
Hazard | -0.089 |
Premium | -0.086 |
神 | -0.086 |
Fountain | -0.084 |
Token | was |
Token ID | 373 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.009 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.009 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
scale | -0.010 |
cale | -0.010 |
################################ | -0.010 |
Token | introduced |
Token ID | 5495 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
stice | +0.017 |
Hazard | +0.015 |
Premium | +0.015 |
神 | +0.015 |
Fountain | +0.015 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.016 |
scale | -0.016 |
cale | -0.016 |
################################ | -0.016 |
Token | tank |
Token ID | 6873 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
stice | +0.010 |
Hazard | +0.010 |
Premium | +0.009 |
神 | +0.009 |
Fountain | +0.009 |
Neg logit contributions | |
backbone | -0.010 |
Kenn | -0.010 |
scale | -0.010 |
cale | -0.010 |
################################ | -0.010 |
Token | ers |
Token ID | 364 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
stice | +0.138 |
Hazard | +0.131 |
Premium | +0.128 |
神 | +0.127 |
Fountain | +0.126 |
Neg logit contributions | |
backbone | -0.049 |
Kenn | -0.048 |
scale | -0.048 |
cale | -0.047 |
################################ | -0.045 |
Token | until |
Token ID | 1566 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
backbone | +0.090 |
Kenn | +0.089 |
scale | +0.088 |
cale | +0.087 |
################################ | +0.086 |
Neg logit contributions | |
stice | -0.097 |
Hazard | -0.090 |
Premium | -0.087 |
神 | -0.087 |
Fountain | -0.085 |
Token | re |
Token ID | 302 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
backbone | +0.068 |
Kenn | +0.068 |
scale | +0.067 |
cale | +0.066 |
################################ | +0.065 |
Neg logit contributions | |
stice | -0.067 |
Hazard | -0.062 |
Premium | -0.060 |
神 | -0.060 |
Fountain | -0.059 |
Token | - |
Token ID | 12 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
stice | +0.024 |
Hazard | +0.022 |
Premium | +0.022 |
神 | +0.022 |
Fountain | +0.021 |
Neg logit contributions | |
backbone | -0.025 |
Kenn | -0.024 |
scale | -0.024 |
cale | -0.024 |
################################ | -0.024 |
Token | gas |
Token ID | 22649 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | ified |
Token ID | 1431 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
stice | +0.386 |
Hazard | +0.359 |
Premium | +0.348 |
神 | +0.345 |
Fountain | +0.339 |
Neg logit contributions | |
backbone | -0.349 |
Kenn | -0.347 |
scale | -0.343 |
cale | -0.341 |
################################ | -0.335 |
Token | at |
Token ID | 379 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
backbone | +0.092 |
Kenn | +0.091 |
scale | +0.090 |
cale | +0.089 |
################################ | +0.088 |
Neg logit contributions | |
stice | -0.100 |
Hazard | -0.093 |
Premium | -0.090 |
神 | -0.090 |
Fountain | -0.088 |
Token | newly |
Token ID | 8308 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
stice | +0.068 |
Hazard | +0.063 |
Premium | +0.061 |
神 | +0.061 |
Fountain | +0.060 |
Neg logit contributions | |
backbone | -0.058 |
Kenn | -0.057 |
scale | -0.057 |
cale | -0.056 |
################################ | -0.055 |
Token | constructed |
Token ID | 12006 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
stice | +0.104 |
Hazard | +0.097 |
Premium | +0.094 |
神 | +0.094 |
Fountain | +0.091 |
Neg logit contributions | |
backbone | -0.091 |
Kenn | -0.090 |
scale | -0.089 |
cale | -0.088 |
################################ | -0.086 |
Token | ports |
Token ID | 14090 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
backbone | +0.022 |
Kenn | +0.022 |
cale | +0.021 |
scale | +0.021 |
################################ | +0.021 |
Neg logit contributions | |
stice | -0.026 |
Hazard | -0.024 |
Premium | -0.023 |
神 | -0.023 |
Fountain | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
stice | +0.142 |
Hazard | +0.131 |
Premium | +0.127 |
神 | +0.125 |
ottest | +0.123 |
Neg logit contributions | |
Kenn | -0.176 |
backbone | -0.176 |
scale | -0.175 |
cale | -0.173 |
kin | -0.169 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
stice | +0.108 |
Hazard | +0.099 |
Premium | +0.095 |
神 | +0.094 |
Fountain | +0.092 |
Neg logit contributions | |
backbone | -0.135 |
Kenn | -0.134 |
scale | -0.134 |
cale | -0.132 |
kin | -0.129 |
Token | create |
Token ID | 2251 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
stice | +0.025 |
Hazard | +0.023 |
Premium | +0.022 |
神 | +0.022 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.021 |
Kenn | -0.021 |
scale | -0.020 |
cale | -0.020 |
################################ | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
stice | +0.056 |
Hazard | +0.052 |
Premium | +0.050 |
神 | +0.050 |
ottest | +0.049 |
Neg logit contributions | |
backbone | -0.047 |
Kenn | -0.047 |
scale | -0.047 |
cale | -0.046 |
################################ | -0.045 |
Token | mural |
Token ID | 36192 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.013 |
神 | -0.013 |
ottest | -0.013 |
Token | capturing |
Token ID | 21430 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
stice | +0.353 |
Hazard | +0.327 |
Premium | +0.316 |
神 | +0.314 |
Fountain | +0.307 |
Neg logit contributions | |
backbone | -0.366 |
Kenn | -0.363 |
scale | -0.360 |
cale | -0.357 |
################################ | -0.351 |
Token | the |
Token ID | 262 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
stice | +0.023 |
Hazard | +0.021 |
Premium | +0.020 |
神 | +0.020 |
Fountain | +0.020 |
Neg logit contributions | |
backbone | -0.023 |
Kenn | -0.022 |
scale | -0.022 |
cale | -0.022 |
################################ | -0.022 |
Token | spirit |
Token ID | 4437 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
cale | -0.007 |
scale | -0.006 |
################################ | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
backbone | +0.139 |
Kenn | +0.138 |
scale | +0.137 |
cale | +0.135 |
################################ | +0.132 |
Neg logit contributions | |
stice | -0.165 |
Hazard | -0.153 |
Premium | -0.150 |
神 | -0.149 |
Fountain | -0.145 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.005 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
stice | +0.111 |
Hazard | +0.103 |
Premium | +0.099 |
神 | +0.099 |
Fountain | +0.097 |
Neg logit contributions | |
backbone | -0.101 |
Kenn | -0.100 |
scale | -0.099 |
cale | -0.099 |
################################ | -0.097 |
Token | old |
Token ID | 727 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
stice | +0.013 |
Hazard | +0.013 |
Premium | +0.012 |
神 | +0.012 |
ottest | +0.012 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
�� | -0.009 |
Token | Herm |
Token ID | 18113 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | osa |
Token ID | 8546 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
stice | +0.021 |
Hazard | +0.020 |
Premium | +0.019 |
神 | +0.019 |
Fountain | +0.019 |
Neg logit contributions | |
backbone | -0.018 |
Kenn | -0.018 |
scale | -0.018 |
cale | -0.018 |
################################ | -0.017 |
Token | Beach |
Token ID | 8511 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
backbone | +0.108 |
Kenn | +0.107 |
cale | +0.106 |
scale | +0.106 |
################################ | +0.103 |
Neg logit contributions | |
stice | -0.148 |
Hazard | -0.139 |
Premium | -0.134 |
神 | -0.134 |
Fountain | -0.133 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
backbone | +0.063 |
Kenn | +0.062 |
scale | +0.062 |
cale | +0.061 |
################################ | +0.060 |
Neg logit contributions | |
stice | -0.072 |
Hazard | -0.067 |
Premium | -0.065 |
神 | -0.064 |
Fountain | -0.064 |
Token | K |
Token ID | 509 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
stice | +0.378 |
Hazard | +0.351 |
Premium | +0.339 |
神 | +0.338 |
Fountain | +0.333 |
Neg logit contributions | |
backbone | -0.339 |
Kenn | -0.335 |
scale | -0.333 |
cale | -0.331 |
################################ | -0.325 |
Token | la |
Token ID | 5031 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.010 |
Premium | +0.010 |
神 | +0.010 |
Fountain | +0.010 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.010 |
################################ | -0.010 |
Token | as |
Token ID | 292 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
backbone | +0.042 |
Kenn | +0.042 |
scale | +0.042 |
cale | +0.042 |
################################ | +0.041 |
Neg logit contributions | |
stice | -0.040 |
Hazard | -0.037 |
Premium | -0.036 |
神 | -0.036 |
Fountain | -0.035 |
Token | case |
Token ID | 1339 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
stice | +0.056 |
Hazard | +0.052 |
Premium | +0.050 |
神 | +0.050 |
Fountain | +0.049 |
Neg logit contributions | |
backbone | -0.051 |
Kenn | -0.050 |
scale | -0.050 |
cale | -0.049 |
################################ | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.014 |
################################ | -0.013 |
Token | If |
Token ID | 1532 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
stice | +0.018 |
Hazard | +0.016 |
Premium | +0.016 |
神 | +0.016 |
Fountain | +0.016 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.017 |
scale | -0.017 |
cale | -0.017 |
################################ | -0.017 |
Token | Annie |
Token ID | 25860 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.010 |
Premium | +0.010 |
神 | +0.009 |
ottest | +0.009 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.010 |
################################ | -0.010 |
Token | Hall |
Token ID | 4789 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
Kenn | +0.004 |
backbone | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
ottest | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
backbone | +0.127 |
Kenn | +0.127 |
scale | +0.126 |
cale | +0.124 |
################################ | +0.122 |
Neg logit contributions | |
stice | -0.113 |
Hazard | -0.104 |
Premium | -0.101 |
神 | -0.100 |
Fountain | -0.098 |
Token | Inter |
Token ID | 4225 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.014 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.015 |
Kenn | -0.015 |
scale | -0.015 |
cale | -0.015 |
################################ | -0.015 |
Token | iors |
Token ID | 12706 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.008 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.128 |
Kenn | -0.128 |
scale | -0.127 |
cale | -0.126 |
################################ | -0.125 |
Token | didn |
Token ID | 1422 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
stice | +0.354 |
Hazard | +0.327 |
Premium | +0.316 |
神 | +0.316 |
Fountain | +0.308 |
Neg logit contributions | |
backbone | -0.362 |
Kenn | -0.359 |
scale | -0.355 |
cale | -0.353 |
################################ | -0.347 |
Token | � |
Token ID | 447 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
stice | +0.047 |
Hazard | +0.043 |
Premium | +0.042 |
神 | +0.041 |
Fountain | +0.040 |
Neg logit contributions | |
backbone | -0.059 |
Kenn | -0.059 |
scale | -0.058 |
cale | -0.058 |
�� | -0.057 |
Token | � |
Token ID | 247 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
stice | +0.018 |
Hazard | +0.017 |
Premium | +0.016 |
神 | +0.016 |
Fountain | +0.016 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
################################ | -0.009 |
Token | t |
Token ID | 83 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.007 |
Premium | -0.007 |
神 | -0.006 |
Fountain | -0.006 |
Token | already |
Token ID | 1541 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
stice | +0.110 |
Hazard | +0.103 |
神 | +0.100 |
Premium | +0.100 |
Fountain | +0.098 |
Neg logit contributions | |
backbone | -0.085 |
Kenn | -0.085 |
cale | -0.083 |
scale | -0.082 |
################################ | -0.082 |
Token | Park |
Token ID | 3250 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
backbone | +0.030 |
Kenn | +0.030 |
scale | +0.029 |
cale | +0.029 |
################################ | +0.028 |
Neg logit contributions | |
stice | -0.037 |
Hazard | -0.035 |
Premium | -0.034 |
神 | -0.034 |
ottest | -0.033 |
Token | ( |
Token ID | 357 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
stice | +0.069 |
Hazard | +0.064 |
Premium | +0.062 |
神 | +0.061 |
Fountain | +0.060 |
Neg logit contributions | |
backbone | -0.066 |
Kenn | -0.066 |
scale | -0.065 |
cale | -0.064 |
################################ | -0.063 |
Token | pictured |
Token ID | 28852 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
backbone | +0.053 |
Kenn | +0.053 |
scale | +0.052 |
cale | +0.052 |
################################ | +0.051 |
Neg logit contributions | |
stice | -0.056 |
Hazard | -0.052 |
Premium | -0.050 |
神 | -0.050 |
Fountain | -0.049 |
Token | ); |
Token ID | 1776 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
backbone | +0.084 |
Kenn | +0.084 |
scale | +0.083 |
cale | +0.082 |
################################ | +0.081 |
Neg logit contributions | |
stice | -0.090 |
Hazard | -0.083 |
Premium | -0.081 |
神 | -0.080 |
Fountain | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
stice | +0.110 |
Hazard | +0.103 |
Premium | +0.099 |
神 | +0.099 |
Fountain | +0.097 |
Neg logit contributions | |
backbone | -0.100 |
Kenn | -0.099 |
scale | -0.098 |
cale | -0.097 |
################################ | -0.096 |
Token | mural |
Token ID | 36192 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.002 |
神 | -0.002 |
Fountain | -0.002 |
Token | collaboration |
Token ID | 12438 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
stice | +0.350 |
Hazard | +0.323 |
Premium | +0.314 |
神 | +0.311 |
Fountain | +0.304 |
Neg logit contributions | |
backbone | -0.361 |
Kenn | -0.359 |
scale | -0.356 |
cale | -0.352 |
################################ | -0.346 |
Token | between |
Token ID | 1022 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
stice | +0.091 |
Hazard | +0.084 |
Premium | +0.082 |
神 | +0.081 |
ottest | +0.079 |
Neg logit contributions | |
backbone | -0.094 |
Kenn | -0.094 |
scale | -0.093 |
cale | -0.092 |
################################ | -0.090 |
Token | Urban |
Token ID | 14665 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
stice | +0.038 |
Hazard | +0.036 |
Premium | +0.034 |
神 | +0.034 |
Fountain | +0.034 |
Neg logit contributions | |
backbone | -0.037 |
Kenn | -0.037 |
scale | -0.036 |
cale | -0.036 |
################################ | -0.035 |
Token | Ar |
Token ID | 3163 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
stice | +0.040 |
Hazard | +0.037 |
Premium | +0.036 |
神 | +0.036 |
ottest | +0.035 |
Neg logit contributions | |
backbone | -0.041 |
Kenn | -0.041 |
scale | -0.041 |
cale | -0.040 |
################################ | -0.039 |
Token | ts |
Token ID | 912 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
stice | +0.055 |
Hazard | +0.050 |
Premium | +0.049 |
神 | +0.048 |
Fountain | +0.047 |
Neg logit contributions | |
backbone | -0.070 |
Kenn | -0.070 |
scale | -0.069 |
cale | -0.069 |
################################ | -0.068 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
backbone | +0.239 |
Kenn | +0.238 |
scale | +0.235 |
cale | +0.233 |
################################ | +0.229 |
Neg logit contributions | |
stice | -0.254 |
Hazard | -0.236 |
Premium | -0.229 |
神 | -0.228 |
Fountain | -0.223 |
Token | An |
Token ID | 2025 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | ore |
Token ID | 382 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.005 |
Kenn | -0.005 |
scale | -0.005 |
cale | -0.005 |
################################ | -0.005 |
Token | x |
Token ID | 87 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
backbone | +0.090 |
Kenn | +0.090 |
scale | +0.089 |
cale | +0.088 |
################################ | +0.085 |
Neg logit contributions | |
stice | -0.124 |
Hazard | -0.116 |
Premium | -0.114 |
神 | -0.113 |
Fountain | -0.110 |
Token | ic |
Token ID | 291 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Kenn | +0.121 |
backbone | +0.121 |
scale | +0.120 |
cale | +0.119 |
################################ | +0.116 |
Neg logit contributions | |
stice | -0.065 |
Hazard | -0.057 |
Premium | -0.056 |
神 | -0.055 |
ottest | -0.053 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
stice | +0.152 |
Hazard | +0.140 |
Premium | +0.136 |
神 | +0.135 |
Fountain | +0.132 |
Neg logit contributions | |
backbone | -0.155 |
Kenn | -0.153 |
scale | -0.152 |
cale | -0.151 |
################################ | -0.148 |
Token | Carpenter |
Token ID | 32659 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
stice | +0.368 |
Hazard | +0.343 |
Premium | +0.331 |
神 | +0.329 |
Fountain | +0.324 |
Neg logit contributions | |
backbone | -0.342 |
Kenn | -0.337 |
scale | -0.335 |
cale | -0.333 |
################################ | -0.327 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
backbone | +0.075 |
Kenn | +0.074 |
scale | +0.073 |
cale | +0.073 |
################################ | +0.071 |
Neg logit contributions | |
stice | -0.083 |
Hazard | -0.077 |
Premium | -0.075 |
神 | -0.075 |
Fountain | -0.073 |
Token | 01 |
Token ID | 486 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
backbone | +0.031 |
Kenn | +0.030 |
scale | +0.029 |
�� | +0.029 |
cale | +0.029 |
Neg logit contributions | |
stice | -0.079 |
Hazard | -0.075 |
Premium | -0.074 |
神 | -0.072 |
Fountain | -0.072 |
Token | 15 |
Token ID | 1314 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
backbone | +0.122 |
Kenn | +0.119 |
scale | +0.119 |
cale | +0.117 |
################################ | +0.113 |
Neg logit contributions | |
stice | -0.189 |
Hazard | -0.178 |
Premium | -0.174 |
神 | -0.172 |
ottest | -0.170 |
Token | O |
Token ID | 440 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
backbone | +0.063 |
Kenn | +0.062 |
scale | +0.062 |
cale | +0.061 |
################################ | +0.060 |
Neg logit contributions | |
stice | -0.053 |
Hazard | -0.049 |
Premium | -0.047 |
神 | -0.046 |
Fountain | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
ottest | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | While |
Token ID | 3633 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.002 |
Premium | -0.002 |
神 | -0.002 |
Fountain | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | Oregon |
Token ID | 8819 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | Cannabis |
Token ID | 28838 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
backbone | +0.056 |
Kenn | +0.055 |
scale | +0.055 |
cale | +0.054 |
################################ | +0.053 |
Neg logit contributions | |
stice | -0.052 |
Hazard | -0.048 |
Premium | -0.047 |
神 | -0.046 |
Fountain | -0.045 |
Token | Tax |
Token ID | 9241 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
stice | +0.367 |
Hazard | +0.342 |
Premium | +0.329 |
神 | +0.327 |
Fountain | +0.324 |
Neg logit contributions | |
backbone | -0.339 |
Kenn | -0.335 |
scale | -0.332 |
cale | -0.331 |
################################ | -0.326 |
Token | Act |
Token ID | 2191 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
backbone | +0.072 |
Kenn | +0.072 |
scale | +0.071 |
cale | +0.070 |
################################ | +0.069 |
Neg logit contributions | |
stice | -0.079 |
Hazard | -0.073 |
Premium | -0.071 |
神 | -0.071 |
ottest | -0.069 |
Token | was |
Token ID | 373 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
backbone | +0.049 |
Kenn | +0.048 |
scale | +0.048 |
cale | +0.047 |
################################ | +0.046 |
Neg logit contributions | |
stice | -0.051 |
Hazard | -0.048 |
Premium | -0.046 |
神 | -0.046 |
Fountain | -0.045 |
Token | able |
Token ID | 1498 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
backbone | +0.087 |
Kenn | +0.087 |
scale | +0.086 |
cale | +0.085 |
################################ | +0.084 |
Neg logit contributions | |
stice | -0.068 |
Hazard | -0.062 |
Premium | -0.060 |
神 | -0.059 |
Fountain | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
backbone | +0.048 |
Kenn | +0.048 |
scale | +0.047 |
cale | +0.046 |
################################ | +0.046 |
Neg logit contributions | |
stice | -0.056 |
Hazard | -0.053 |
Premium | -0.051 |
神 | -0.051 |
Fountain | -0.050 |
Token | my |
Token ID | 616 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.009 |
Token | head |
Token ID | 1182 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
stice | +0.082 |
Hazard | +0.076 |
Premium | +0.073 |
神 | +0.073 |
Fountain | +0.071 |
Neg logit contributions | |
backbone | -0.092 |
Kenn | -0.092 |
scale | -0.091 |
cale | -0.091 |
################################ | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
stice | +0.096 |
Hazard | +0.089 |
Premium | +0.086 |
神 | +0.085 |
Fountain | +0.083 |
Neg logit contributions | |
backbone | -0.099 |
Kenn | -0.099 |
scale | -0.098 |
cale | -0.097 |
################################ | -0.095 |
Token | probably |
Token ID | 2192 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
backbone | +0.030 |
Kenn | +0.030 |
scale | +0.029 |
cale | +0.029 |
################################ | +0.029 |
Neg logit contributions | |
stice | -0.031 |
Hazard | -0.029 |
Premium | -0.028 |
神 | -0.028 |
Fountain | -0.027 |
Token | � |
Token ID | 447 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
stice | +0.353 |
Hazard | +0.327 |
Premium | +0.317 |
神 | +0.314 |
Fountain | +0.307 |
Neg logit contributions | |
backbone | -0.349 |
Kenn | -0.348 |
scale | -0.345 |
cale | -0.341 |
################################ | -0.335 |
Token | � |
Token ID | 247 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.005 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | s |
Token ID | 82 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
backbone | +0.019 |
Kenn | +0.019 |
scale | +0.019 |
cale | +0.018 |
################################ | +0.018 |
Neg logit contributions | |
stice | -0.021 |
Hazard | -0.020 |
Premium | -0.019 |
神 | -0.019 |
Fountain | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.017 |
Hazard | -0.015 |
Premium | -0.015 |
神 | -0.015 |
Fountain | -0.014 |
Token | tells |
Token ID | 4952 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.002 |
Premium | -0.002 |
神 | -0.002 |
ottest | -0.002 |
Token | pleted |
Token ID | 16838 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | eight |
Token ID | 3624 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
backbone | +0.158 |
Kenn | +0.157 |
scale | +0.157 |
cale | +0.155 |
################################ | +0.153 |
Neg logit contributions | |
stice | -0.067 |
Hazard | -0.059 |
Premium | -0.056 |
神 | -0.055 |
ottest | -0.053 |
Token | - |
Token ID | 12 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
backbone | +0.027 |
scale | +0.027 |
Kenn | +0.027 |
cale | +0.026 |
################################ | +0.025 |
Neg logit contributions | |
stice | -0.030 |
Hazard | -0.028 |
Premium | -0.027 |
神 | -0.027 |
ottest | -0.026 |
Token | store |
Token ID | 8095 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
ottest | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
scale | -0.001 |
Kenn | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | y |
Token ID | 88 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
backbone | +0.101 |
scale | +0.100 |
Kenn | +0.100 |
cale | +0.099 |
################################ | +0.098 |
Neg logit contributions | |
stice | -0.056 |
Hazard | -0.050 |
神 | -0.048 |
Premium | -0.047 |
Fountain | -0.045 |
Token | mural |
Token ID | 36192 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
stice | +0.112 |
Hazard | +0.103 |
Premium | +0.100 |
神 | +0.099 |
Fountain | +0.096 |
Neg logit contributions | |
backbone | -0.129 |
Kenn | -0.128 |
scale | -0.127 |
cale | -0.126 |
################################ | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
stice | +0.346 |
Hazard | +0.321 |
Premium | +0.310 |
神 | +0.308 |
Fountain | +0.302 |
Neg logit contributions | |
backbone | -0.354 |
Kenn | -0.352 |
scale | -0.349 |
cale | -0.346 |
################################ | -0.340 |
Token | Dep |
Token ID | 2129 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
ottest | -0.009 |
Token | ict |
Token ID | 713 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
backbone | +0.092 |
Kenn | +0.091 |
scale | +0.091 |
cale | +0.090 |
################################ | +0.089 |
Neg logit contributions | |
stice | -0.060 |
Hazard | -0.055 |
Premium | -0.052 |
神 | -0.052 |
Fountain | -0.050 |
Token | ing |
Token ID | 278 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
stice | +0.046 |
Hazard | +0.042 |
Premium | +0.041 |
神 | +0.040 |
ottest | +0.039 |
Neg logit contributions | |
backbone | -0.068 |
Kenn | -0.067 |
scale | -0.067 |
cale | -0.066 |
################################ | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
stice | +0.090 |
Hazard | +0.084 |
Premium | +0.081 |
神 | +0.081 |
Fountain | +0.079 |
Neg logit contributions | |
backbone | -0.082 |
Kenn | -0.081 |
scale | -0.081 |
cale | -0.080 |
################################ | -0.079 |
Token | man |
Token ID | 805 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
stice | +0.020 |
Hazard | +0.018 |
Premium | +0.018 |
神 | +0.017 |
Fountain | +0.017 |
Neg logit contributions | |
backbone | -0.021 |
Kenn | -0.021 |
scale | -0.021 |
cale | -0.021 |
################################ | -0.020 |
Token | esque |
Token ID | 28939 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
stice | +0.026 |
Hazard | +0.024 |
Premium | +0.023 |
神 | +0.023 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.026 |
Kenn | -0.025 |
scale | -0.025 |
cale | -0.025 |
################################ | -0.024 |
Token | chamber |
Token ID | 11847 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
stice | +0.102 |
Hazard | +0.095 |
Premium | +0.092 |
神 | +0.092 |
Fountain | +0.090 |
Neg logit contributions | |
backbone | -0.089 |
Kenn | -0.089 |
scale | -0.088 |
cale | -0.087 |
################################ | -0.085 |
Token | piece |
Token ID | 3704 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
stice | +0.085 |
Hazard | +0.079 |
Premium | +0.077 |
神 | +0.076 |
Fountain | +0.075 |
Neg logit contributions | |
backbone | -0.077 |
Kenn | -0.077 |
scale | -0.076 |
cale | -0.076 |
################################ | -0.074 |
Token | Inter |
Token ID | 4225 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
stice | +0.067 |
Hazard | +0.062 |
Premium | +0.060 |
神 | +0.059 |
Fountain | +0.058 |
Neg logit contributions | |
backbone | -0.066 |
Kenn | -0.066 |
scale | -0.065 |
cale | -0.064 |
################################ | -0.063 |
Token | iors |
Token ID | 12706 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.007 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.118 |
Kenn | -0.118 |
scale | -0.118 |
cale | -0.117 |
################################ | -0.116 |
Token | as |
Token ID | 355 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
stice | +0.349 |
Hazard | +0.322 |
Premium | +0.312 |
神 | +0.310 |
Fountain | +0.303 |
Neg logit contributions | |
backbone | -0.350 |
Kenn | -0.348 |
scale | -0.346 |
cale | -0.342 |
################################ | -0.336 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
stice | +0.067 |
Hazard | +0.062 |
Premium | +0.060 |
神 | +0.060 |
Fountain | +0.058 |
Neg logit contributions | |
backbone | -0.062 |
Kenn | -0.061 |
scale | -0.061 |
cale | -0.060 |
################################ | -0.059 |
Token | film |
Token ID | 2646 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.018 |
Hazard | -0.017 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
backbone | +0.152 |
Kenn | +0.151 |
scale | +0.149 |
cale | +0.148 |
################################ | +0.145 |
Neg logit contributions | |
stice | -0.159 |
Hazard | -0.147 |
Premium | -0.143 |
神 | -0.142 |
Fountain | -0.139 |
Token | � |
Token ID | 447 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
stice | +0.015 |
Hazard | +0.014 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.013 |
Neg logit contributions | |
backbone | -0.016 |
Kenn | -0.016 |
scale | -0.015 |
cale | -0.015 |
################################ | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
backbone | +0.033 |
Kenn | +0.033 |
scale | +0.032 |
cale | +0.032 |
################################ | +0.032 |
Neg logit contributions | |
stice | -0.036 |
Hazard | -0.034 |
Premium | -0.033 |
神 | -0.033 |
Fountain | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
stice | +0.013 |
Hazard | +0.012 |
Premium | +0.012 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.011 |
################################ | -0.011 |
Token | death |
Token ID | 1918 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
stice | +0.062 |
Hazard | +0.058 |
Premium | +0.056 |
神 | +0.056 |
Fountain | +0.055 |
Neg logit contributions | |
backbone | -0.052 |
Kenn | -0.052 |
scale | -0.051 |
cale | -0.051 |
################################ | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
stice | +0.069 |
Hazard | +0.064 |
Premium | +0.063 |
神 | +0.062 |
Fountain | +0.061 |
Neg logit contributions | |
backbone | -0.062 |
Kenn | -0.062 |
scale | -0.061 |
cale | -0.061 |
################################ | -0.059 |
Token | CEO |
Token ID | 6123 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.011 |
Fountain | -0.011 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
backbone | +0.030 |
Kenn | +0.029 |
scale | +0.029 |
cale | +0.029 |
################################ | +0.028 |
Neg logit contributions | |
stice | -0.029 |
Hazard | -0.027 |
Premium | -0.026 |
神 | -0.026 |
Fountain | -0.025 |
Token | Brick |
Token ID | 28347 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
stice | +0.373 |
Hazard | +0.349 |
Premium | +0.336 |
神 | +0.335 |
Fountain | +0.330 |
Neg logit contributions | |
backbone | -0.325 |
Kenn | -0.320 |
scale | -0.319 |
cale | -0.316 |
################################ | -0.311 |
Token | le |
Token ID | 293 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
backbone | +0.050 |
Kenn | +0.050 |
scale | +0.049 |
cale | +0.049 |
################################ | +0.048 |
Neg logit contributions | |
stice | -0.053 |
Hazard | -0.049 |
Premium | -0.047 |
神 | -0.047 |
Fountain | -0.046 |
Token | my |
Token ID | 1820 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
stice | +0.052 |
Hazard | +0.048 |
Premium | +0.047 |
神 | +0.047 |
Fountain | +0.046 |
Neg logit contributions | |
backbone | -0.049 |
Kenn | -0.049 |
scale | -0.048 |
cale | -0.048 |
################################ | -0.047 |
Token | er |
Token ID | 263 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
stice | +0.062 |
Hazard | +0.058 |
Premium | +0.056 |
神 | +0.056 |
Fountain | +0.055 |
Neg logit contributions | |
backbone | -0.046 |
Kenn | -0.046 |
scale | -0.045 |
cale | -0.045 |
################################ | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
backbone | +0.041 |
Kenn | +0.041 |
scale | +0.041 |
cale | +0.040 |
################################ | +0.039 |
Neg logit contributions | |
stice | -0.044 |
Hazard | -0.041 |
Premium | -0.040 |
神 | -0.040 |
Fountain | -0.039 |
Token | identity |
Token ID | 5369 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
backbone | +0.105 |
Kenn | +0.104 |
scale | +0.103 |
cale | +0.102 |
################################ | +0.100 |
Neg logit contributions | |
stice | -0.124 |
Hazard | -0.115 |
Premium | -0.113 |
神 | -0.112 |
Fountain | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.016 |
Hazard | -0.014 |
Premium | -0.014 |
神 | -0.014 |
Fountain | -0.014 |
Token | killer |
Token ID | 11868 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
backbone | +0.164 |
Kenn | +0.162 |
scale | +0.161 |
cale | +0.160 |
################################ | +0.157 |
Neg logit contributions | |
stice | -0.174 |
Hazard | -0.162 |
Premium | -0.156 |
神 | -0.155 |
Fountain | -0.153 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.015 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.011 |
Fountain | -0.011 |
Token | Kl |
Token ID | 14770 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
stice | +0.349 |
Hazard | +0.324 |
Premium | +0.312 |
神 | +0.311 |
Fountain | +0.305 |
Neg logit contributions | |
backbone | -0.348 |
Kenn | -0.344 |
scale | -0.343 |
cale | -0.340 |
################################ | -0.334 |
Token | ass |
Token ID | 562 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
backbone | +0.090 |
Kenn | +0.089 |
scale | +0.088 |
cale | +0.087 |
################################ | +0.086 |
Neg logit contributions | |
stice | -0.084 |
Hazard | -0.078 |
Premium | -0.075 |
神 | -0.075 |
ottest | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-05 |
Pos logit contributions | |
backbone | +0.103 |
Kenn | +0.102 |
scale | +0.101 |
cale | +0.100 |
################################ | +0.099 |
Neg logit contributions | |
stice | -0.119 |
Hazard | -0.111 |
Premium | -0.108 |
神 | -0.107 |
Fountain | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
backbone | +0.000 |
Kenn | +0.000 |
scale | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.000 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
Fountain | -0.000 |
Token | ex |
Token ID | 409 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
################################ | +0.004 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.011 |
Premium | +0.010 |
神 | +0.010 |
Fountain | +0.010 |
Neg logit contributions | |
backbone | -0.006 |
Kenn | -0.006 |
scale | -0.006 |
cale | -0.006 |
################################ | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.018 |
Hazard | -0.017 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.016 |
Token | problems |
Token ID | 2761 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.013 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
stice | +0.043 |
Hazard | +0.039 |
Premium | +0.038 |
神 | +0.038 |
Fountain | +0.037 |
Neg logit contributions | |
backbone | -0.038 |
Kenn | -0.038 |
scale | -0.038 |
cale | -0.037 |
################################ | -0.037 |
Token | Inter |
Token ID | 4225 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
ottest | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | iors |
Token ID | 12706 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.007 |
Premium | +0.005 |
神 | +0.004 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.115 |
Kenn | -0.114 |
scale | -0.114 |
cale | -0.113 |
################################ | -0.112 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
stice | +0.333 |
Hazard | +0.308 |
Premium | +0.298 |
神 | +0.296 |
Fountain | +0.289 |
Neg logit contributions | |
backbone | -0.361 |
Kenn | -0.358 |
scale | -0.355 |
cale | -0.352 |
################################ | -0.346 |
Token | good |
Token ID | 922 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.017 |
Hazard | -0.016 |
Premium | -0.015 |
神 | -0.015 |
Fountain | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
backbone | +0.022 |
Kenn | +0.022 |
cale | +0.022 |
scale | +0.022 |
################################ | +0.021 |
Neg logit contributions | |
stice | -0.028 |
Hazard | -0.026 |
Premium | -0.026 |
神 | -0.025 |
Fountain | -0.025 |
Token | its |
Token ID | 663 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.011 |
cale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.011 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | potential |
Token ID | 2785 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
神 | -0.008 |
Premium | -0.008 |
Fountain | -0.008 |
Token | s |
Token ID | 82 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.026 |
Hazard | -0.024 |
Premium | -0.024 |
神 | -0.024 |
Fountain | -0.023 |
Token | Yar |
Token ID | 45184 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
backbone | +0.016 |
Kenn | +0.016 |
scale | +0.016 |
cale | +0.016 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.014 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.012 |
ottest | -0.012 |
Token | oslav |
Token ID | 26388 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
stice | +0.006 |
Hazard | +0.006 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.005 |
Neg logit contributions | |
backbone | -0.005 |
Kenn | -0.005 |
scale | -0.005 |
cale | -0.005 |
################################ | -0.005 |
Token | Tro |
Token ID | 8498 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
stice | +0.017 |
Hazard | +0.015 |
Premium | +0.015 |
神 | +0.015 |
ottest | +0.015 |
Neg logit contributions | |
Kenn | -0.018 |
backbone | -0.018 |
scale | -0.017 |
cale | -0.017 |
################################ | -0.017 |
Token | f |
Token ID | 69 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
backbone | +0.163 |
Kenn | +0.162 |
scale | +0.161 |
cale | +0.160 |
################################ | +0.156 |
Neg logit contributions | |
stice | -0.160 |
Hazard | -0.149 |
Premium | -0.144 |
神 | -0.143 |
Fountain | -0.140 |
Token | imov |
Token ID | 44273 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | reports |
Token ID | 3136 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
stice | +0.343 |
Hazard | +0.317 |
Premium | +0.307 |
神 | +0.306 |
Fountain | +0.299 |
Neg logit contributions | |
backbone | -0.347 |
Kenn | -0.345 |
scale | -0.342 |
cale | -0.339 |
################################ | -0.333 |
Token | this |
Token ID | 428 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
backbone | +0.025 |
Kenn | +0.025 |
scale | +0.024 |
cale | +0.024 |
################################ | +0.024 |
Neg logit contributions | |
stice | -0.030 |
Hazard | -0.028 |
Premium | -0.027 |
神 | -0.027 |
Fountain | -0.026 |
Token | morning |
Token ID | 3329 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
backbone | +0.026 |
Kenn | +0.026 |
scale | +0.026 |
cale | +0.026 |
################################ | +0.025 |
Neg logit contributions | |
stice | -0.021 |
Hazard | -0.019 |
Premium | -0.018 |
神 | -0.018 |
Fountain | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
stice | +0.157 |
Hazard | +0.146 |
Premium | +0.142 |
神 | +0.141 |
Fountain | +0.138 |
Neg logit contributions | |
backbone | -0.136 |
Kenn | -0.135 |
scale | -0.134 |
cale | -0.132 |
################################ | -0.129 |
Token | Jordan |
Token ID | 8078 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.007 |
Hazard | -0.006 |
Premium | -0.006 |
神 | -0.006 |
Fountain | -0.006 |
Token | � |
Token ID | 447 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
stice | +0.099 |
Hazard | +0.092 |
Premium | +0.089 |
神 | +0.089 |
Fountain | +0.087 |
Neg logit contributions | |
backbone | -0.092 |
Kenn | -0.092 |
scale | -0.091 |
cale | -0.090 |
################################ | -0.088 |
Token | � |
Token ID | 247 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.003 |
Token | carefully |
Token ID | 7773 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.014 |
Neg logit contributions | |
stice | -0.023 |
Hazard | -0.021 |
Premium | -0.021 |
神 | -0.021 |
Fountain | -0.020 |
Token | controlled |
Token ID | 6856 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
backbone | +0.031 |
Kenn | +0.031 |
scale | +0.031 |
cale | +0.030 |
################################ | +0.030 |
Neg logit contributions | |
stice | -0.028 |
Hazard | -0.025 |
Premium | -0.025 |
神 | -0.024 |
Fountain | -0.024 |
Token | inter |
Token ID | 987 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.006 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | iors |
Token ID | 12706 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
backbone | +0.058 |
Kenn | +0.058 |
scale | +0.058 |
cale | +0.057 |
################################ | +0.057 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.004 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
stice | +0.358 |
Hazard | +0.333 |
Premium | +0.322 |
神 | +0.322 |
Fountain | +0.315 |
Neg logit contributions | |
backbone | -0.328 |
Kenn | -0.326 |
scale | -0.322 |
cale | -0.320 |
################################ | -0.315 |
Token | or |
Token ID | 393 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.005 |
Kenn | -0.005 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | interior |
Token ID | 11087 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | ity |
Token ID | 414 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
stice | +0.235 |
Hazard | +0.218 |
Premium | +0.211 |
神 | +0.210 |
Fountain | +0.205 |
Neg logit contributions | |
backbone | -0.222 |
Kenn | -0.221 |
scale | -0.219 |
cale | -0.217 |
################################ | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
backbone | +0.082 |
Kenn | +0.082 |
scale | +0.082 |
cale | +0.080 |
################################ | +0.079 |
Neg logit contributions | |
stice | -0.084 |
Hazard | -0.077 |
Premium | -0.075 |
神 | -0.074 |
Fountain | -0.073 |
Token | � |
Token ID | 251 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.009 |
Premium | -0.008 |
神 | -0.008 |
Fountain | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
�� | +0.005 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.004 |
Premium | -0.004 |
神 | -0.004 |
Fountain | -0.004 |
Token | Staff |
Token ID | 31449 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
backbone | +0.007 |
Kenn | +0.007 |
scale | +0.007 |
cale | +0.007 |
################################ | +0.006 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.006 |
Premium | -0.006 |
神 | -0.006 |
Fountain | -0.006 |
Token | writer |
Token ID | 6260 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
backbone | +0.034 |
Kenn | +0.034 |
scale | +0.033 |
cale | +0.033 |
################################ | +0.033 |
Neg logit contributions | |
stice | -0.025 |
Hazard | -0.022 |
Premium | -0.022 |
神 | -0.021 |
Fountain | -0.021 |
Token | Karen |
Token ID | 18678 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
stice | +0.038 |
Hazard | +0.035 |
Premium | +0.034 |
神 | +0.034 |
ottest | +0.033 |
Neg logit contributions | |
Kenn | -0.045 |
backbone | -0.045 |
scale | -0.044 |
cale | -0.044 |
################################ | -0.043 |
Token | De |
Token ID | 1024 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
stice | +0.357 |
Hazard | +0.335 |
Premium | +0.321 |
神 | +0.320 |
Fountain | +0.317 |
Neg logit contributions | |
backbone | -0.326 |
Kenn | -0.320 |
scale | -0.320 |
cale | -0.317 |
################################ | -0.312 |
Token | Young |
Token ID | 20917 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
backbone | +0.065 |
Kenn | +0.064 |
scale | +0.064 |
cale | +0.063 |
################################ | +0.062 |
Neg logit contributions | |
stice | -0.068 |
Hazard | -0.063 |
Premium | -0.061 |
神 | -0.060 |
Fountain | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
stice | +0.027 |
Hazard | +0.024 |
Premium | +0.023 |
神 | +0.023 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.050 |
Kenn | -0.049 |
scale | -0.049 |
cale | -0.049 |
################################ | -0.048 |
Token | Washington |
Token ID | 2669 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
backbone | +0.013 |
Kenn | +0.013 |
scale | +0.013 |
cale | +0.013 |
################################ | +0.013 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.012 |
Premium | -0.011 |
神 | -0.011 |
Fountain | -0.011 |
Token | contributed |
Token ID | 8639 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
stice | +0.027 |
Hazard | +0.024 |
Premium | +0.024 |
神 | +0.023 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.050 |
Kenn | -0.049 |
scale | -0.049 |
cale | -0.048 |
################################ | -0.048 |
Token | named |
Token ID | 3706 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | Norman |
Token ID | 19636 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
backbone | +0.080 |
Kenn | +0.080 |
scale | +0.079 |
cale | +0.078 |
################################ | +0.077 |
Neg logit contributions | |
stice | -0.081 |
Hazard | -0.075 |
Premium | -0.073 |
神 | -0.073 |
Fountain | -0.071 |
Token | Bates |
Token ID | 35591 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
backbone | +0.050 |
Kenn | +0.050 |
scale | +0.049 |
cale | +0.049 |
################################ | +0.048 |
Neg logit contributions | |
stice | -0.061 |
Hazard | -0.057 |
Premium | -0.056 |
神 | -0.055 |
Fountain | -0.054 |
Token | ( |
Token ID | 357 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
backbone | +0.206 |
Kenn | +0.205 |
scale | +0.203 |
cale | +0.201 |
################################ | +0.196 |
Neg logit contributions | |
stice | -0.272 |
Hazard | -0.254 |
Premium | -0.247 |
神 | -0.246 |
Fountain | -0.241 |
Token | Anthony |
Token ID | 32697 |
Feature activation | +4.40e-03 |
Pos logit contributions | |
backbone | +0.062 |
Kenn | +0.061 |
scale | +0.061 |
cale | +0.060 |
################################ | +0.059 |
Neg logit contributions | |
stice | -0.061 |
Hazard | -0.057 |
Premium | -0.055 |
神 | -0.055 |
Fountain | -0.053 |
Token | Perkins |
Token ID | 29618 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
backbone | +0.000 |
scale | +0.000 |
Kenn | +0.000 |
cale | +0.000 |
################################ | +0.000 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
神 | -0.001 |
Premium | -0.001 |
Fountain | -0.001 |
Token | .) |
Token ID | 2014 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
backbone | +0.304 |
Kenn | +0.303 |
scale | +0.300 |
cale | +0.297 |
################################ | +0.290 |
Neg logit contributions | |
stice | -0.303 |
Hazard | -0.279 |
Premium | -0.271 |
神 | -0.269 |
ottest | -0.263 |
Token | Norman |
Token ID | 19636 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
stice | +0.044 |
Hazard | +0.041 |
Premium | +0.039 |
神 | +0.039 |
Fountain | +0.038 |
Neg logit contributions | |
backbone | -0.042 |
Kenn | -0.041 |
scale | -0.041 |
cale | -0.041 |
################################ | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
backbone | +0.059 |
Kenn | +0.059 |
scale | +0.058 |
cale | +0.058 |
################################ | +0.057 |
Neg logit contributions | |
stice | -0.059 |
Hazard | -0.055 |
Premium | -0.053 |
神 | -0.053 |
Fountain | -0.052 |
Token | shall |
Token ID | 2236 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
backbone | +0.006 |
Kenn | +0.006 |
scale | +0.006 |
cale | +0.006 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.006 |
Hazard | -0.006 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | w |
Token ID | 266 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
backbone | +0.060 |
Kenn | +0.060 |
scale | +0.059 |
cale | +0.059 |
################################ | +0.058 |
Neg logit contributions | |
stice | -0.063 |
Hazard | -0.058 |
Premium | -0.056 |
神 | -0.056 |
Fountain | -0.055 |
Token | all |
Token ID | 477 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
stice | +0.021 |
Hazard | +0.019 |
神 | +0.019 |
Premium | +0.019 |
Fountain | +0.019 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.011 |
################################ | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
backbone | +0.073 |
Kenn | +0.072 |
scale | +0.072 |
cale | +0.071 |
################################ | +0.070 |
Neg logit contributions | |
stice | -0.079 |
Hazard | -0.073 |
Premium | -0.071 |
神 | -0.070 |
Fountain | -0.069 |
Token | en |
Token ID | 268 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
�� | +0.002 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | comp |
Token ID | 5589 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
stice | +0.000 |
Hazard | +0.000 |
Premium | +0.000 |
神 | +0.000 |
Fountain | +0.000 |
Neg logit contributions | |
backbone | -0.000 |
Kenn | -0.000 |
scale | -0.000 |
cale | -0.000 |
################################ | -0.000 |
Token | assing |
Token ID | 19696 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
stice | +0.029 |
Hazard | +0.027 |
Premium | +0.026 |
神 | +0.026 |
ottest | +0.025 |
Neg logit contributions | |
backbone | -0.033 |
Kenn | -0.033 |
scale | -0.032 |
cale | -0.032 |
################################ | -0.032 |
Token | stereotype |
Token ID | 31240 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
backbone | +0.262 |
Kenn | +0.261 |
scale | +0.257 |
cale | +0.256 |
�� | +0.252 |
Neg logit contributions | |
stice | -0.286 |
Hazard | -0.267 |
Premium | -0.258 |
神 | -0.257 |
Fountain | -0.252 |
Token | trou |
Token ID | 4057 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
backbone | +0.013 |
Kenn | +0.013 |
scale | +0.013 |
cale | +0.013 |
################################ | +0.013 |
Neg logit contributions | |
stice | -0.014 |
Hazard | -0.013 |
Premium | -0.013 |
神 | -0.013 |
Fountain | -0.012 |
Token | ser |
Token ID | 2655 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
backbone | +0.036 |
Kenn | +0.036 |
scale | +0.036 |
cale | +0.035 |
################################ | +0.035 |
Neg logit contributions | |
stice | -0.023 |
Hazard | -0.021 |
Premium | -0.020 |
神 | -0.020 |
Fountain | -0.019 |
Token | - |
Token ID | 12 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
stice | +0.118 |
Hazard | +0.110 |
Premium | +0.106 |
神 | +0.106 |
Fountain | +0.104 |
Neg logit contributions | |
backbone | -0.110 |
Kenn | -0.109 |
scale | -0.108 |
cale | -0.107 |
################################ | -0.105 |
Token | w |
Token ID | 86 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.000 |
Premium | +0.000 |
神 | +0.000 |
Fountain | +0.000 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
backbone | +0.098 |
Kenn | +0.098 |
scale | +0.097 |
cale | +0.096 |
################################ | +0.094 |
Neg logit contributions | |
stice | -0.094 |
Hazard | -0.087 |
Premium | -0.084 |
神 | -0.084 |
Fountain | -0.082 |
Token | fulfillment |
Token ID | 32402 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
stice | +0.019 |
Hazard | +0.018 |
Premium | +0.017 |
神 | +0.017 |
Fountain | +0.017 |
Neg logit contributions | |
backbone | -0.017 |
Kenn | -0.017 |
scale | -0.017 |
cale | -0.017 |
################################ | -0.016 |
Token | completion |
Token ID | 11939 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
stice | +0.008 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
stice | +0.053 |
Hazard | +0.050 |
Premium | +0.048 |
神 | +0.048 |
Fountain | +0.047 |
Neg logit contributions | |
backbone | -0.048 |
Kenn | -0.048 |
scale | -0.047 |
cale | -0.047 |
################################ | -0.046 |
Token | Duke |
Token ID | 11083 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | Energy |
Token ID | 6682 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
backbone | +0.244 |
Kenn | +0.242 |
scale | +0.240 |
cale | +0.237 |
################################ | +0.232 |
Neg logit contributions | |
stice | -0.290 |
Hazard | -0.269 |
Premium | -0.263 |
神 | -0.261 |
Fountain | -0.256 |
Token | � |
Token ID | 447 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
backbone | +0.020 |
Kenn | +0.020 |
scale | +0.020 |
cale | +0.019 |
################################ | +0.019 |
Neg logit contributions | |
stice | -0.020 |
Hazard | -0.019 |
Premium | -0.018 |
神 | -0.018 |
Fountain | -0.018 |
Token | � |
Token ID | 247 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.004 |
Premium | +0.003 |
神 | +0.003 |
Gloria | +0.003 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
backbone | +0.010 |
Kenn | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.014 |
神 | -0.014 |
Fountain | -0.014 |
Token | obligations |
Token ID | 13675 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.011 |
Hazard | -0.010 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | chopped |
Token ID | 20720 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
backbone | +0.006 |
Kenn | +0.006 |
scale | +0.006 |
cale | +0.006 |
################################ | +0.006 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.007 |
Premium | -0.007 |
神 | -0.007 |
Fountain | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
backbone | +0.027 |
Kenn | +0.027 |
scale | +0.027 |
cale | +0.027 |
################################ | +0.026 |
Neg logit contributions | |
stice | -0.031 |
Hazard | -0.029 |
Premium | -0.028 |
神 | -0.028 |
Fountain | -0.027 |
Token | society |
Token ID | 3592 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
stice | +0.016 |
Hazard | +0.015 |
Premium | +0.014 |
神 | +0.014 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.013 |
Kenn | -0.013 |
scale | -0.013 |
cale | -0.013 |
################################ | -0.013 |
Token | as |
Token ID | 355 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
backbone | +0.022 |
Kenn | +0.022 |
scale | +0.022 |
cale | +0.021 |
################################ | +0.021 |
Neg logit contributions | |
stice | -0.016 |
Hazard | -0.015 |
Premium | -0.014 |
神 | -0.014 |
Fountain | -0.014 |
Token | unsu |
Token ID | 48092 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
stice | +0.081 |
Hazard | +0.075 |
Premium | +0.073 |
神 | +0.072 |
Fountain | +0.071 |
Neg logit contributions | |
backbone | -0.076 |
Kenn | -0.075 |
scale | -0.074 |
cale | -0.074 |
################################ | -0.072 |
Token | ited |
Token ID | 863 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
stice | +0.214 |
Hazard | +0.202 |
Premium | +0.197 |
神 | +0.196 |
Fountain | +0.193 |
Neg logit contributions | |
backbone | -0.113 |
Kenn | -0.110 |
scale | -0.109 |
cale | -0.107 |
################################ | -0.105 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
backbone | +0.278 |
Kenn | +0.275 |
scale | +0.274 |
cale | +0.271 |
################################ | +0.266 |
Neg logit contributions | |
stice | -0.235 |
Hazard | -0.216 |
Premium | -0.208 |
神 | -0.206 |
Fountain | -0.202 |
Token | state |
Token ID | 1181 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
stice | +0.029 |
Hazard | +0.027 |
Premium | +0.026 |
神 | +0.026 |
Fountain | +0.025 |
Neg logit contributions | |
backbone | -0.027 |
Kenn | -0.027 |
scale | -0.026 |
cale | -0.026 |
################################ | -0.026 |
Token | hood |
Token ID | 2894 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
stice | +0.020 |
Hazard | +0.018 |
Premium | +0.017 |
神 | +0.017 |
Fountain | +0.016 |
Neg logit contributions | |
backbone | -0.042 |
Kenn | -0.042 |
scale | -0.041 |
cale | -0.041 |
################################ | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
stice | +0.162 |
Hazard | +0.150 |
Premium | +0.146 |
神 | +0.145 |
Fountain | +0.142 |
Neg logit contributions | |
backbone | -0.154 |
Kenn | -0.153 |
scale | -0.152 |
cale | -0.151 |
################################ | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
################################ | -0.009 |
Token | sample |
Token ID | 6291 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
stice | +0.079 |
Hazard | +0.074 |
Premium | +0.071 |
神 | +0.071 |
Fountain | +0.070 |
Neg logit contributions | |
backbone | -0.069 |
Kenn | -0.068 |
scale | -0.068 |
cale | -0.067 |
################################ | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
backbone | +0.039 |
Kenn | +0.038 |
scale | +0.038 |
cale | +0.038 |
################################ | +0.037 |
Neg logit contributions | |
stice | -0.039 |
Hazard | -0.036 |
Premium | -0.035 |
神 | -0.035 |
Fountain | -0.034 |
Token | Got |
Token ID | 11853 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
backbone | +0.014 |
Kenn | +0.014 |
scale | +0.014 |
cale | +0.014 |
################################ | +0.013 |
Neg logit contributions | |
stice | -0.014 |
Hazard | -0.013 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | lands |
Token ID | 4447 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
backbone | +0.053 |
Kenn | +0.052 |
scale | +0.052 |
cale | +0.051 |
################################ | +0.051 |
Neg logit contributions | |
stice | -0.031 |
Hazard | -0.028 |
Premium | -0.027 |
神 | -0.027 |
Fountain | -0.026 |
Token | d |
Token ID | 67 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
stice | +0.102 |
Hazard | +0.096 |
Premium | +0.093 |
神 | +0.092 |
Fountain | +0.091 |
Neg logit contributions | |
backbone | -0.070 |
Kenn | -0.069 |
scale | -0.069 |
cale | -0.068 |
################################ | -0.067 |
Token | rick |
Token ID | 5557 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
backbone | +0.035 |
Kenn | +0.035 |
scale | +0.034 |
cale | +0.033 |
################################ | +0.032 |
Neg logit contributions | |
stice | -0.125 |
Hazard | -0.119 |
Premium | -0.116 |
神 | -0.115 |
ottest | -0.114 |
Token | a |
Token ID | 64 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
backbone | +0.265 |
Kenn | +0.263 |
scale | +0.260 |
cale | +0.256 |
################################ | +0.252 |
Neg logit contributions | |
stice | -0.327 |
Hazard | -0.306 |
Premium | -0.296 |
神 | -0.294 |
Fountain | -0.290 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-03 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.012 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
�� | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | And |
Token ID | 1870 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | ers |
Token ID | 364 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
stice | +0.033 |
Hazard | +0.031 |
Premium | +0.030 |
神 | +0.030 |
Fountain | +0.030 |
Neg logit contributions | |
backbone | -0.024 |
Kenn | -0.023 |
scale | -0.023 |
cale | -0.023 |
################################ | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
backbone | +0.060 |
Kenn | +0.060 |
scale | +0.059 |
cale | +0.059 |
################################ | +0.058 |
Neg logit contributions | |
stice | -0.068 |
Hazard | -0.063 |
Premium | -0.062 |
神 | -0.061 |
Fountain | -0.060 |
Token | The |
Token ID | 383 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.017 |
scale | +0.017 |
cale | +0.017 |
################################ | +0.017 |
Neg logit contributions | |
stice | -0.019 |
Hazard | -0.017 |
Premium | -0.017 |
神 | -0.017 |
Fountain | -0.016 |
Token | wheels |
Token ID | 13666 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
backbone | +0.051 |
Kenn | +0.050 |
scale | +0.050 |
cale | +0.049 |
################################ | +0.048 |
Neg logit contributions | |
stice | -0.070 |
Hazard | -0.065 |
Premium | -0.064 |
神 | -0.064 |
Fountain | -0.062 |
Token | are |
Token ID | 389 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | H |
Token ID | 367 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
stice | +0.011 |
Hazard | +0.010 |
Premium | +0.010 |
神 | +0.010 |
Fountain | +0.010 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.010 |
################################ | -0.010 |
Token | + |
Token ID | 10 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
stice | +0.059 |
Hazard | +0.055 |
Premium | +0.053 |
神 | +0.053 |
ottest | +0.052 |
Neg logit contributions | |
backbone | -0.052 |
Kenn | -0.052 |
scale | -0.051 |
cale | -0.051 |
################################ | -0.050 |
Token | son |
Token ID | 1559 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
backbone | +0.059 |
Kenn | +0.059 |
scale | +0.058 |
cale | +0.058 |
################################ | +0.057 |
Neg logit contributions | |
stice | -0.061 |
Hazard | -0.056 |
Premium | -0.055 |
神 | -0.054 |
Fountain | -0.053 |
Token | arch |
Token ID | 3934 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
backbone | +0.125 |
Kenn | +0.124 |
scale | +0.123 |
cale | +0.122 |
################################ | +0.120 |
Neg logit contributions | |
stice | -0.128 |
Hazard | -0.119 |
Premium | -0.115 |
神 | -0.115 |
Fountain | -0.112 |
Token | type |
Token ID | 4906 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
backbone | +0.059 |
Kenn | +0.059 |
scale | +0.058 |
cale | +0.057 |
################################ | +0.057 |
Neg logit contributions | |
stice | -0.060 |
Hazard | -0.055 |
Premium | -0.054 |
神 | -0.053 |
Fountain | -0.052 |
Token | an |
Token ID | 281 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
backbone | +0.025 |
Kenn | +0.025 |
scale | +0.025 |
cale | +0.025 |
################################ | +0.024 |
Neg logit contributions | |
stice | -0.027 |
Hazard | -0.026 |
Premium | -0.025 |
神 | -0.025 |
Fountain | -0.024 |
Token | od |
Token ID | 375 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.005 |
Kenn | -0.005 |
scale | -0.005 |
cale | -0.005 |
################################ | -0.005 |
Token | place |
Token ID | 1295 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
stice | +0.063 |
Hazard | +0.059 |
Premium | +0.057 |
神 | +0.056 |
Fountain | +0.056 |
Neg logit contributions | |
backbone | -0.062 |
Kenn | -0.061 |
scale | -0.061 |
cale | -0.061 |
################################ | -0.060 |
Token | you |
Token ID | 345 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
stice | +0.054 |
Hazard | +0.050 |
Premium | +0.048 |
神 | +0.048 |
Fountain | +0.047 |
Neg logit contributions | |
backbone | -0.061 |
Kenn | -0.061 |
scale | -0.060 |
cale | -0.060 |
################################ | -0.059 |
Token | can |
Token ID | 460 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
cale | +0.001 |
scale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
backbone | +0.033 |
Kenn | +0.033 |
cale | +0.032 |
scale | +0.032 |
################################ | +0.032 |
Neg logit contributions | |
stice | -0.042 |
Hazard | -0.039 |
Premium | -0.038 |
神 | -0.038 |
Fountain | -0.037 |
Token | ,'" |
Token ID | 16078 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
backbone | +0.073 |
Kenn | +0.072 |
scale | +0.071 |
cale | +0.071 |
################################ | +0.070 |
Neg logit contributions | |
stice | -0.074 |
Hazard | -0.069 |
Premium | -0.067 |
神 | -0.066 |
Fountain | -0.065 |
Token | he |
Token ID | 339 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
backbone | +0.128 |
Kenn | +0.127 |
scale | +0.126 |
cale | +0.124 |
################################ | +0.122 |
Neg logit contributions | |
stice | -0.116 |
Hazard | -0.106 |
Premium | -0.103 |
神 | -0.103 |
Fountain | -0.100 |
Token | said |
Token ID | 531 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
backbone | +0.071 |
Kenn | +0.070 |
scale | +0.070 |
cale | +0.069 |
################################ | +0.068 |
Neg logit contributions | |
stice | -0.051 |
Hazard | -0.047 |
Premium | -0.045 |
神 | -0.045 |
Fountain | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
scale | +0.011 |
cale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.013 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Kenn | +0.010 |
backbone | +0.010 |
scale | +0.010 |
cale | +0.010 |
################################ | +0.010 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.007 |
Fountain | -0.007 |
Token | I |
Token ID | 40 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
stice | +0.059 |
Hazard | +0.055 |
Premium | +0.053 |
神 | +0.053 |
Fountain | +0.051 |
Neg logit contributions | |
backbone | -0.060 |
Kenn | -0.059 |
scale | -0.059 |
cale | -0.058 |
################################ | -0.057 |
Token | love |
Token ID | 1842 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
backbone | +0.031 |
Kenn | +0.031 |
cale | +0.031 |
scale | +0.031 |
�� | +0.030 |
Neg logit contributions | |
stice | -0.027 |
Hazard | -0.025 |
Premium | -0.024 |
神 | -0.024 |
Fountain | -0.023 |
Token | ailing |
Token ID | 11608 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
stice | +0.132 |
Hazard | +0.124 |
Premium | +0.120 |
神 | +0.120 |
ottest | +0.119 |
Neg logit contributions | |
backbone | -0.089 |
Kenn | -0.088 |
scale | -0.087 |
cale | -0.086 |
################################ | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
backbone | +0.023 |
Kenn | +0.023 |
scale | +0.023 |
cale | +0.023 |
################################ | +0.022 |
Neg logit contributions | |
stice | -0.023 |
Hazard | -0.021 |
Premium | -0.021 |
神 | -0.021 |
Fountain | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
scale | -0.011 |
cale | -0.011 |
################################ | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
stice | +0.019 |
Hazard | +0.018 |
Premium | +0.017 |
神 | +0.017 |
Fountain | +0.017 |
Neg logit contributions | |
backbone | -0.021 |
Kenn | -0.021 |
scale | -0.021 |
cale | -0.021 |
�� | -0.020 |
Token | N |
Token ID | 45 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
stice | +0.015 |
Hazard | +0.014 |
Premium | +0.014 |
神 | +0.013 |
Fountain | +0.013 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.013 |
################################ | -0.013 |
Token | is |
Token ID | 271 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
stice | +0.031 |
Hazard | +0.029 |
Premium | +0.028 |
神 | +0.028 |
ottest | +0.027 |
Neg logit contributions | |
backbone | -0.027 |
Kenn | -0.027 |
scale | -0.027 |
cale | -0.027 |
################################ | -0.026 |
Token | ar |
Token ID | 283 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
backbone | +0.062 |
Kenn | +0.062 |
scale | +0.061 |
cale | +0.061 |
################################ | +0.060 |
Neg logit contributions | |
stice | -0.064 |
Hazard | -0.059 |
Premium | -0.058 |
神 | -0.057 |
Fountain | -0.056 |
Token | Malik |
Token ID | 31745 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
stice | +0.013 |
Hazard | +0.012 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.013 |
Kenn | -0.013 |
scale | -0.013 |
cale | -0.013 |
################################ | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
stice | +0.090 |
Hazard | +0.083 |
Premium | +0.081 |
神 | +0.080 |
Fountain | +0.079 |
Neg logit contributions | |
backbone | -0.086 |
Kenn | -0.085 |
scale | -0.085 |
cale | -0.084 |
################################ | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.013 |
神 | +0.013 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.014 |
################################ | -0.014 |
Token | Pakistani |
Token ID | 17807 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
backbone | +0.008 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.008 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
stice | +0.133 |
Hazard | +0.122 |
Premium | +0.118 |
神 | +0.117 |
Fountain | +0.114 |
Neg logit contributions | |
backbone | -0.164 |
Kenn | -0.163 |
scale | -0.161 |
cale | -0.160 |
################################ | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e-03 |
Pos logit contributions | |
stice | +0.024 |
Hazard | +0.022 |
Premium | +0.022 |
神 | +0.022 |
Fountain | +0.021 |
Neg logit contributions | |
backbone | -0.020 |
Kenn | -0.020 |
scale | -0.020 |
cale | -0.020 |
################################ | -0.019 |
Token | 299 |
Token ID | 22579 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
stice | +0.000 |
Hazard | +0.000 |
Premium | +0.000 |
神 | +0.000 |
Fountain | +0.000 |
Neg logit contributions | |
backbone | -0.000 |
Kenn | -0.000 |
scale | -0.000 |
cale | -0.000 |
################################ | -0.000 |
Token | based |
Token ID | 1912 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
stice | +0.055 |
Hazard | +0.051 |
Premium | +0.050 |
神 | +0.049 |
Fountain | +0.048 |
Neg logit contributions | |
backbone | -0.048 |
Kenn | -0.047 |
scale | -0.047 |
cale | -0.047 |
################################ | -0.046 |
Token | on |
Token ID | 319 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
backbone | +0.028 |
Kenn | +0.028 |
scale | +0.028 |
cale | +0.028 |
################################ | +0.027 |
Neg logit contributions | |
stice | -0.030 |
Hazard | -0.028 |
Premium | -0.027 |
神 | -0.027 |
Fountain | -0.026 |
Token | departures |
Token ID | 50050 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
backbone | +0.013 |
Kenn | +0.013 |
scale | +0.013 |
cale | +0.013 |
################################ | +0.013 |
Neg logit contributions | |
stice | -0.015 |
Hazard | -0.014 |
Premium | -0.013 |
神 | -0.013 |
Fountain | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
backbone | +0.050 |
Kenn | +0.050 |
scale | +0.049 |
cale | +0.049 |
################################ | +0.049 |
Neg logit contributions | |
stice | -0.050 |
Hazard | -0.046 |
Premium | -0.045 |
神 | -0.044 |
Fountain | -0.043 |
Token | December |
Token ID | 3426 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
Fountain | -0.008 |
Token | 20 |
Token ID | 1160 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
stice | +0.046 |
Hazard | +0.043 |
Premium | +0.042 |
神 | +0.042 |
Fountain | +0.041 |
Neg logit contributions | |
backbone | -0.042 |
Kenn | -0.042 |
scale | -0.041 |
cale | -0.041 |
################################ | -0.040 |
Token | or |
Token ID | 393 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
stice | +0.015 |
Hazard | +0.014 |
Premium | +0.013 |
神 | +0.013 |
Fountain | +0.013 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.013 |
################################ | -0.013 |
Token | 27 |
Token ID | 2681 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.005 |
Kenn | -0.005 |
scale | -0.005 |
cale | -0.005 |
################################ | -0.005 |
Token | go |
Token ID | 467 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
stice | +0.025 |
Hazard | +0.024 |
Premium | +0.023 |
神 | +0.023 |
Fountain | +0.022 |
Neg logit contributions | |
backbone | -0.024 |
Kenn | -0.024 |
scale | -0.024 |
cale | -0.024 |
################################ | -0.023 |
Token | beyond |
Token ID | 3675 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
backbone | +0.061 |
Kenn | +0.061 |
scale | +0.061 |
cale | +0.060 |
################################ | +0.059 |
Neg logit contributions | |
stice | -0.069 |
Hazard | -0.065 |
Premium | -0.063 |
神 | -0.062 |
Fountain | -0.061 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
backbone | +0.096 |
Kenn | +0.095 |
scale | +0.094 |
cale | +0.094 |
################################ | +0.092 |
Neg logit contributions | |
stice | -0.093 |
Hazard | -0.086 |
Premium | -0.083 |
神 | -0.083 |
Fountain | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
stice | +0.062 |
Hazard | +0.058 |
Premium | +0.056 |
神 | +0.055 |
Fountain | +0.054 |
Neg logit contributions | |
backbone | -0.059 |
Kenn | -0.059 |
scale | -0.058 |
cale | -0.058 |
################################ | -0.057 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
backbone | +0.005 |
Kenn | +0.005 |
scale | +0.005 |
cale | +0.005 |
################################ | +0.005 |
Neg logit contributions | |
stice | -0.005 |
Hazard | -0.005 |
Premium | -0.005 |
神 | -0.005 |
Fountain | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
backbone | +0.114 |
Kenn | +0.113 |
scale | +0.112 |
cale | +0.111 |
################################ | +0.109 |
Neg logit contributions | |
stice | -0.119 |
Hazard | -0.110 |
Premium | -0.107 |
神 | -0.106 |
Fountain | -0.104 |
Token | special |
Token ID | 2041 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
backbone | +0.046 |
Kenn | +0.046 |
scale | +0.045 |
cale | +0.045 |
################################ | +0.044 |
Neg logit contributions | |
stice | -0.052 |
Hazard | -0.048 |
Premium | -0.047 |
神 | -0.047 |
Fountain | -0.046 |
Token | counsel |
Token ID | 7739 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
stice | +0.105 |
Hazard | +0.098 |
Premium | +0.095 |
神 | +0.094 |
Fountain | +0.093 |
Neg logit contributions | |
backbone | -0.086 |
Kenn | -0.085 |
scale | -0.085 |
cale | -0.085 |
################################ | -0.083 |
Token | leading |
Token ID | 3756 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
stice | +0.123 |
Hazard | +0.114 |
Premium | +0.110 |
神 | +0.110 |
Fountain | +0.107 |
Neg logit contributions | |
backbone | -0.123 |
Kenn | -0.123 |
scale | -0.122 |
cale | -0.120 |
################################ | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | probe |
Token ID | 12774 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
backbone | +0.001 |
Kenn | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.017 |
scale | +0.017 |
cale | +0.017 |
################################ | +0.016 |
Neg logit contributions | |
stice | -0.023 |
Hazard | -0.021 |
Premium | -0.021 |
神 | -0.021 |
Fountain | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
stice | +0.044 |
Hazard | +0.041 |
Premium | +0.039 |
神 | +0.039 |
Fountain | +0.038 |
Neg logit contributions | |
backbone | -0.040 |
Kenn | -0.040 |
scale | -0.039 |
cale | -0.039 |
################################ | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
backbone | +0.008 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.010 |
Hazard | -0.009 |
Premium | -0.009 |
神 | -0.009 |
Fountain | -0.009 |
Token | weaknesses |
Token ID | 20256 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
backbone | +0.129 |
Kenn | +0.128 |
scale | +0.127 |
cale | +0.125 |
################################ | +0.123 |
Neg logit contributions | |
stice | -0.127 |
Hazard | -0.118 |
Premium | -0.114 |
神 | -0.113 |
Fountain | -0.111 |
Token | we |
Token ID | 356 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.012 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.013 |
################################ | -0.013 |
Token | have |
Token ID | 423 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
backbone | +0.009 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.008 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.007 |
Premium | -0.007 |
神 | -0.007 |
Fountain | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
backbone | +0.028 |
Kenn | +0.028 |
scale | +0.027 |
cale | +0.027 |
################################ | +0.027 |
Neg logit contributions | |
stice | -0.027 |
Hazard | -0.025 |
Premium | -0.024 |
神 | -0.024 |
Fountain | -0.024 |
Token | car |
Token ID | 1097 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.004 |
Premium | +0.004 |
神 | +0.004 |
Fountain | +0.004 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
stice | +0.058 |
Hazard | +0.053 |
Premium | +0.052 |
神 | +0.052 |
Fountain | +0.050 |
Neg logit contributions | |
backbone | -0.053 |
Kenn | -0.052 |
scale | -0.052 |
cale | -0.051 |
################################ | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
backbone | +0.030 |
Kenn | +0.030 |
scale | +0.029 |
cale | +0.029 |
################################ | +0.028 |
Neg logit contributions | |
stice | -0.034 |
Hazard | -0.031 |
Premium | -0.030 |
神 | -0.030 |
Fountain | -0.029 |
Token | Lib |
Token ID | 7980 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.014 |
Neg logit contributions | |
stice | -0.014 |
Hazard | -0.013 |
Premium | -0.012 |
神 | -0.012 |
ottest | -0.012 |
Token | o |
Token ID | 78 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
stice | +0.120 |
Hazard | +0.110 |
Premium | +0.106 |
神 | +0.105 |
Fountain | +0.102 |
Neg logit contributions | |
backbone | -0.148 |
Kenn | -0.147 |
scale | -0.146 |
cale | -0.145 |
################################ | -0.142 |
Token | last |
Token ID | 938 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
stice | +0.053 |
Hazard | +0.049 |
Premium | +0.048 |
神 | +0.048 |
ottest | +0.046 |
Neg logit contributions | |
backbone | -0.049 |
Kenn | -0.049 |
scale | -0.048 |
cale | -0.048 |
################################ | -0.047 |
Token | year |
Token ID | 614 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
backbone | +0.102 |
Kenn | +0.101 |
scale | +0.100 |
cale | +0.099 |
################################ | +0.098 |
Neg logit contributions | |
stice | -0.062 |
Hazard | -0.056 |
Premium | -0.053 |
神 | -0.053 |
Fountain | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
stice | +0.077 |
Hazard | +0.072 |
Premium | +0.070 |
神 | +0.069 |
Fountain | +0.068 |
Neg logit contributions | |
backbone | -0.063 |
Kenn | -0.063 |
scale | -0.062 |
cale | -0.061 |
################################ | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
Kenn | +0.009 |
backbone | +0.009 |
scale | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
ottest | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
stice | +0.001 |
Hazard | +0.001 |
Premium | +0.001 |
神 | +0.001 |
Fountain | +0.001 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
�� | -0.001 |
Token | At |
Token ID | 2953 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
神 | -0.003 |
Premium | -0.003 |
Fountain | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
stice | +0.028 |
Hazard | +0.026 |
Premium | +0.025 |
神 | +0.025 |
ottest | +0.024 |
Neg logit contributions | |
backbone | -0.027 |
Kenn | -0.027 |
scale | -0.027 |
cale | -0.027 |
################################ | -0.026 |
Token | time |
Token ID | 640 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
backbone | +0.023 |
Kenn | +0.023 |
scale | +0.023 |
cale | +0.022 |
################################ | +0.022 |
Neg logit contributions | |
stice | -0.028 |
Hazard | -0.027 |
Premium | -0.026 |
神 | -0.026 |
Fountain | -0.025 |
Token | what |
Token ID | 644 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
stice | +0.041 |
Hazard | +0.038 |
Premium | +0.037 |
神 | +0.036 |
Fountain | +0.036 |
Neg logit contributions | |
backbone | -0.044 |
Kenn | -0.044 |
scale | -0.044 |
cale | -0.043 |
################################ | -0.043 |
Token | by |
Token ID | 416 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
stice | +0.019 |
Hazard | +0.018 |
Premium | +0.017 |
神 | +0.017 |
ottest | +0.017 |
Neg logit contributions | |
backbone | -0.022 |
Kenn | -0.022 |
scale | -0.022 |
cale | -0.022 |
################################ | -0.021 |
Token | all |
Token ID | 477 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
stice | +0.047 |
Hazard | +0.044 |
Premium | +0.042 |
神 | +0.042 |
Fountain | +0.041 |
Neg logit contributions | |
backbone | -0.039 |
Kenn | -0.039 |
scale | -0.039 |
cale | -0.038 |
################################ | -0.038 |
Token | rights |
Token ID | 2489 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
backbone | +0.062 |
Kenn | +0.062 |
scale | +0.061 |
cale | +0.061 |
################################ | +0.060 |
Neg logit contributions | |
stice | -0.066 |
Hazard | -0.062 |
Premium | -0.060 |
神 | -0.059 |
Fountain | -0.058 |
Token | should |
Token ID | 815 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
backbone | +0.039 |
Kenn | +0.038 |
scale | +0.038 |
cale | +0.038 |
################################ | +0.037 |
Neg logit contributions | |
stice | -0.038 |
Hazard | -0.035 |
Premium | -0.034 |
神 | -0.034 |
Fountain | -0.033 |
Token | be |
Token ID | 307 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
backbone | +0.045 |
Kenn | +0.045 |
scale | +0.044 |
cale | +0.044 |
################################ | +0.043 |
Neg logit contributions | |
stice | -0.059 |
Hazard | -0.055 |
Premium | -0.054 |
神 | -0.054 |
Fountain | -0.052 |
Token | utterly |
Token ID | 15950 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
backbone | +0.059 |
Kenn | +0.058 |
scale | +0.058 |
cale | +0.057 |
################################ | +0.056 |
Neg logit contributions | |
stice | -0.067 |
Hazard | -0.062 |
Premium | -0.060 |
神 | -0.060 |
Fountain | -0.059 |
Token | bears |
Token ID | 13062 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
backbone | +0.072 |
Kenn | +0.072 |
scale | +0.071 |
cale | +0.070 |
################################ | +0.069 |
Neg logit contributions | |
stice | -0.076 |
Hazard | -0.071 |
Premium | -0.069 |
神 | -0.068 |
Fountain | -0.067 |
Token | any |
Token ID | 597 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
stice | +0.039 |
Hazard | +0.036 |
Premium | +0.035 |
神 | +0.035 |
Fountain | +0.034 |
Neg logit contributions | |
backbone | -0.032 |
Kenn | -0.032 |
scale | -0.032 |
cale | -0.031 |
################################ | -0.031 |
Token | relation |
Token ID | 8695 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
stice | +0.098 |
Hazard | +0.092 |
神 | +0.088 |
Premium | +0.088 |
Fountain | +0.087 |
Neg logit contributions | |
Kenn | -0.074 |
backbone | -0.074 |
cale | -0.073 |
scale | -0.072 |
################################ | -0.071 |
Token | they |
Token ID | 484 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
scale | +0.002 |
cale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.002 |
Hazard | -0.001 |
Premium | -0.001 |
神 | -0.001 |
Fountain | -0.001 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
stice | +0.004 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
cale | -0.003 |
scale | -0.003 |
�� | -0.003 |
Token | lose |
Token ID | 4425 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
backbone | +0.018 |
Kenn | +0.018 |
cale | +0.018 |
�� | +0.018 |
################################ | +0.018 |
Neg logit contributions | |
stice | -0.023 |
Hazard | -0.021 |
Premium | -0.021 |
神 | -0.021 |
Fountain | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
backbone | +0.076 |
Kenn | +0.076 |
scale | +0.075 |
cale | +0.075 |
################################ | +0.074 |
Neg logit contributions | |
stice | -0.081 |
Hazard | -0.075 |
Premium | -0.072 |
神 | -0.072 |
Fountain | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
backbone | +0.027 |
Kenn | +0.026 |
scale | +0.026 |
cale | +0.026 |
################################ | +0.026 |
Neg logit contributions | |
stice | -0.026 |
Hazard | -0.024 |
Premium | -0.024 |
神 | -0.023 |
Fountain | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
backbone | +0.011 |
Kenn | +0.011 |
cale | +0.011 |
scale | +0.011 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.010 |
神 | -0.010 |
Fountain | -0.010 |
Token | chance |
Token ID | 2863 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
cale | +0.003 |
scale | +0.003 |
RFC | +0.003 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.004 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
stice | +0.076 |
Hazard | +0.070 |
Premium | +0.067 |
神 | +0.067 |
Fountain | +0.065 |
Neg logit contributions | |
backbone | -0.094 |
Kenn | -0.093 |
scale | -0.093 |
cale | -0.092 |
################################ | -0.090 |
Token | sign |
Token ID | 1051 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
stice | +0.014 |
Hazard | +0.013 |
Premium | +0.013 |
神 | +0.013 |
Fountain | +0.013 |
Neg logit contributions | |
backbone | -0.012 |
Kenn | -0.012 |
cale | -0.012 |
scale | -0.012 |
�� | -0.012 |
Token | early |
Token ID | 1903 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
stice | +0.062 |
Hazard | +0.059 |
Premium | +0.056 |
神 | +0.056 |
Fountain | +0.055 |
Neg logit contributions | |
backbone | -0.059 |
Kenn | -0.058 |
scale | -0.058 |
cale | -0.058 |
RFC | -0.057 |
Token | free |
Token ID | 1479 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
backbone | +0.036 |
Kenn | +0.036 |
scale | +0.036 |
cale | +0.035 |
################################ | +0.035 |
Neg logit contributions | |
stice | -0.045 |
Hazard | -0.042 |
Premium | -0.041 |
神 | -0.040 |
Fountain | -0.040 |
Token | ceremony |
Token ID | 10542 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
stice | +0.006 |
Hazard | +0.006 |
神 | +0.006 |
Premium | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
cale | -0.004 |
scale | -0.004 |
################################ | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
backbone | +0.064 |
Kenn | +0.064 |
scale | +0.063 |
cale | +0.063 |
################################ | +0.061 |
Neg logit contributions | |
stice | -0.075 |
Hazard | -0.069 |
Premium | -0.067 |
神 | -0.067 |
Fountain | -0.066 |
Token | I |
Token ID | 314 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Kenn | +0.001 |
backbone | +0.001 |
scale | +0.001 |
cale | +0.001 |
################################ | +0.001 |
Neg logit contributions | |
stice | -0.001 |
Hazard | -0.000 |
Premium | -0.000 |
神 | -0.000 |
ottest | -0.000 |
Token | wasn |
Token ID | 2492 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
stice | +0.020 |
Hazard | +0.018 |
Premium | +0.018 |
神 | +0.017 |
Fountain | +0.017 |
Neg logit contributions | |
backbone | -0.021 |
Kenn | -0.021 |
scale | -0.021 |
cale | -0.021 |
################################ | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
stice | +0.039 |
Hazard | +0.036 |
Premium | +0.035 |
神 | +0.035 |
Fountain | +0.034 |
Neg logit contributions | |
backbone | -0.028 |
Kenn | -0.027 |
scale | -0.027 |
cale | -0.027 |
�� | -0.026 |
Token | allowed |
Token ID | 3142 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
backbone | +0.007 |
Kenn | +0.007 |
scale | +0.007 |
cale | +0.007 |
################################ | +0.007 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.007 |
Premium | -0.007 |
神 | -0.007 |
Fountain | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
stice | +0.017 |
Hazard | +0.015 |
Premium | +0.015 |
神 | +0.015 |
Fountain | +0.014 |
Neg logit contributions | |
backbone | -0.022 |
Kenn | -0.021 |
scale | -0.021 |
cale | -0.021 |
################################ | -0.021 |
Token | tell |
Token ID | 1560 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
stice | +0.021 |
Hazard | +0.020 |
神 | +0.019 |
Premium | +0.019 |
Fountain | +0.019 |
Neg logit contributions | |
backbone | -0.016 |
Kenn | -0.016 |
cale | -0.015 |
scale | -0.015 |
�� | -0.015 |
Token | my |
Token ID | 616 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
stice | +0.090 |
Hazard | +0.083 |
Premium | +0.080 |
神 | +0.080 |
Fountain | +0.078 |
Neg logit contributions | |
backbone | -0.096 |
Kenn | -0.096 |
scale | -0.095 |
cale | -0.094 |
################################ | -0.092 |
Token | younger |
Token ID | 7099 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
stice | +0.106 |
Hazard | +0.099 |
Premium | +0.096 |
神 | +0.096 |
Fountain | +0.094 |
Neg logit contributions | |
backbone | -0.079 |
Kenn | -0.078 |
scale | -0.077 |
cale | -0.076 |
################################ | -0.075 |
Token | sister |
Token ID | 6621 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
stice | +0.130 |
Hazard | +0.122 |
Premium | +0.118 |
神 | +0.118 |
Fountain | +0.116 |
Neg logit contributions | |
backbone | -0.092 |
Kenn | -0.091 |
scale | -0.090 |
cale | -0.089 |
################################ | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
stice | +0.072 |
Hazard | +0.067 |
Premium | +0.065 |
神 | +0.064 |
Fountain | +0.063 |
Neg logit contributions | |
backbone | -0.065 |
Kenn | -0.064 |
scale | -0.064 |
cale | -0.063 |
################################ | -0.062 |
Token | running |
Token ID | 2491 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.008 |
Neg logit contributions | |
backbone | -0.008 |
Kenn | -0.008 |
scale | -0.008 |
cale | -0.008 |
################################ | -0.008 |
Token | medical |
Token ID | 3315 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
backbone | +0.027 |
Kenn | +0.027 |
scale | +0.027 |
cale | +0.026 |
################################ | +0.026 |
Neg logit contributions | |
stice | -0.032 |
Hazard | -0.029 |
Premium | -0.028 |
神 | -0.028 |
Fountain | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
stice | +0.088 |
Hazard | +0.080 |
Premium | +0.077 |
神 | +0.076 |
Fountain | +0.075 |
Neg logit contributions | |
backbone | -0.122 |
Kenn | -0.121 |
scale | -0.120 |
cale | -0.120 |
################################ | -0.118 |
Token | m |
Token ID | 76 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
stice | +0.009 |
Hazard | +0.008 |
Premium | +0.008 |
神 | +0.008 |
Fountain | +0.007 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.009 |
################################ | -0.009 |
Token | arijuana |
Token ID | 42834 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
stice | +0.038 |
Hazard | +0.033 |
Premium | +0.031 |
神 | +0.031 |
Fountain | +0.030 |
Neg logit contributions | |
backbone | -0.090 |
Kenn | -0.089 |
scale | -0.089 |
cale | -0.088 |
################################ | -0.087 |
Token | dispensaries |
Token ID | 40698 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
stice | +0.199 |
Hazard | +0.184 |
Premium | +0.177 |
神 | +0.176 |
Fountain | +0.173 |
Neg logit contributions | |
backbone | -0.219 |
Kenn | -0.217 |
scale | -0.215 |
cale | -0.214 |
################################ | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
stice | +0.141 |
Hazard | +0.131 |
Premium | +0.127 |
神 | +0.126 |
Fountain | +0.124 |
Neg logit contributions | |
backbone | -0.134 |
Kenn | -0.133 |
scale | -0.131 |
cale | -0.130 |
################################ | -0.129 |
Token | Dark |
Token ID | 3801 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
ottest | +0.006 |
Neg logit contributions | |
backbone | -0.007 |
Kenn | -0.007 |
scale | -0.007 |
cale | -0.007 |
################################ | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
backbone | +0.067 |
Kenn | +0.067 |
scale | +0.067 |
cale | +0.066 |
################################ | +0.065 |
Neg logit contributions | |
stice | -0.074 |
Hazard | -0.069 |
Premium | -0.067 |
神 | -0.067 |
Fountain | -0.065 |
Token | haired |
Token ID | 29972 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.014 |
Kenn | -0.014 |
scale | -0.014 |
cale | -0.014 |
################################ | -0.013 |
Token | Moor |
Token ID | 31451 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
stice | +0.032 |
Hazard | +0.030 |
Premium | +0.029 |
神 | +0.029 |
Fountain | +0.028 |
Neg logit contributions | |
backbone | -0.032 |
Kenn | -0.031 |
scale | -0.031 |
cale | -0.031 |
################################ | -0.030 |
Token | claw |
Token ID | 43143 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
backbone | +0.030 |
Kenn | +0.030 |
scale | +0.030 |
cale | +0.030 |
################################ | +0.029 |
Neg logit contributions | |
stice | -0.031 |
Hazard | -0.029 |
Premium | -0.028 |
神 | -0.028 |
Fountain | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
stice | +0.155 |
Hazard | +0.145 |
Premium | +0.140 |
神 | +0.140 |
Fountain | +0.137 |
Neg logit contributions | |
backbone | -0.135 |
Kenn | -0.134 |
scale | -0.132 |
cale | -0.131 |
################################ | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | Col |
Token ID | 1623 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.002 |
Kenn | -0.002 |
scale | -0.002 |
cale | -0.002 |
################################ | -0.002 |
Token | bie |
Token ID | 12590 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
stice | +0.064 |
Hazard | +0.059 |
Premium | +0.058 |
神 | +0.057 |
Fountain | +0.055 |
Neg logit contributions | |
backbone | -0.068 |
Kenn | -0.068 |
scale | -0.067 |
cale | -0.067 |
################################ | -0.066 |
Token | Sterling |
Token ID | 23647 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
stice | +0.234 |
Hazard | +0.218 |
Premium | +0.210 |
神 | +0.209 |
Fountain | +0.206 |
Neg logit contributions | |
backbone | -0.215 |
Kenn | -0.212 |
scale | -0.211 |
cale | -0.209 |
################################ | -0.205 |
Token | — |
Token ID | 960 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
stice | +0.094 |
Hazard | +0.088 |
Premium | +0.085 |
神 | +0.085 |
Fountain | +0.083 |
Neg logit contributions | |
backbone | -0.080 |
Kenn | -0.080 |
scale | -0.079 |
cale | -0.078 |
################################ | -0.077 |
Token | all |
Token ID | 439 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
backbone | +0.049 |
Kenn | +0.048 |
scale | +0.048 |
cale | +0.048 |
################################ | +0.047 |
Neg logit contributions | |
stice | -0.045 |
Hazard | -0.041 |
Premium | -0.040 |
神 | -0.040 |
Fountain | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
stice | +0.012 |
Hazard | +0.011 |
Premium | +0.011 |
神 | +0.011 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.011 |
Kenn | -0.011 |
scale | -0.011 |
cale | -0.010 |
################################ | -0.010 |
Token | whom |
Token ID | 4150 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
backbone | +0.015 |
Kenn | +0.015 |
scale | +0.015 |
cale | +0.015 |
################################ | +0.015 |
Neg logit contributions | |
stice | -0.013 |
Hazard | -0.012 |
Premium | -0.012 |
神 | -0.012 |
Fountain | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
backbone | +0.008 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.007 |
################################ | +0.007 |
Neg logit contributions | |
stice | -0.009 |
Hazard | -0.008 |
Premium | -0.008 |
神 | -0.008 |
Fountain | -0.007 |
Token | face |
Token ID | 1986 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
backbone | +0.039 |
Kenn | +0.039 |
cale | +0.038 |
scale | +0.038 |
################################ | +0.037 |
Neg logit contributions | |
stice | -0.042 |
Hazard | -0.039 |
Premium | -0.038 |
神 | -0.038 |
Fountain | -0.037 |
Token | jail |
Token ID | 7356 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
stice | +0.098 |
Hazard | +0.092 |
Premium | +0.088 |
神 | +0.088 |
Fountain | +0.086 |
Neg logit contributions | |
backbone | -0.083 |
Kenn | -0.082 |
scale | -0.081 |
cale | -0.081 |
################################ | -0.080 |
Token | sentences |
Token ID | 13439 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
stice | +0.112 |
Hazard | +0.104 |
Premium | +0.101 |
神 | +0.100 |
Fountain | +0.098 |
Neg logit contributions | |
backbone | -0.099 |
Kenn | -0.098 |
scale | -0.097 |
cale | -0.096 |
################################ | -0.094 |
Token | if |
Token ID | 611 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
stice | +0.085 |
Hazard | +0.079 |
Premium | +0.076 |
神 | +0.076 |
Fountain | +0.074 |
Neg logit contributions | |
backbone | -0.075 |
Kenn | -0.075 |
scale | -0.074 |
cale | -0.073 |
################################ | -0.072 |
Token | found |
Token ID | 1043 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.006 |
Premium | +0.006 |
神 | +0.006 |
Fountain | +0.006 |
Neg logit contributions | |
backbone | -0.013 |
Kenn | -0.013 |
scale | -0.012 |
cale | -0.012 |
################################ | -0.012 |
Token | guilty |
Token ID | 6717 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
stice | +0.151 |
Hazard | +0.135 |
神 | +0.131 |
Premium | +0.129 |
ottest | +0.125 |
Neg logit contributions | |
backbone | -0.242 |
Kenn | -0.241 |
scale | -0.240 |
cale | -0.235 |
kin | -0.233 |
Token | of |
Token ID | 286 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
stice | +0.154 |
Hazard | +0.144 |
Premium | +0.139 |
神 | +0.139 |
Fountain | +0.136 |
Neg logit contributions | |
backbone | -0.133 |
Kenn | -0.132 |
scale | -0.130 |
cale | -0.129 |
################################ | -0.127 |
Token | any |
Token ID | 597 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
backbone | +0.010 |
scale | +0.010 |
Kenn | +0.009 |
cale | +0.009 |
################################ | +0.009 |
Neg logit contributions | |
stice | -0.007 |
Hazard | -0.006 |
神 | -0.006 |
Premium | -0.006 |
ottest | -0.006 |
Token | wrongdoing |
Token ID | 25013 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
stice | +0.082 |
Hazard | +0.075 |
Premium | +0.073 |
神 | +0.073 |
ottest | +0.071 |
Neg logit contributions | |
backbone | -0.097 |
Kenn | -0.096 |
scale | -0.096 |
cale | -0.094 |
################################ | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
stice | +0.125 |
Hazard | +0.116 |
Premium | +0.113 |
神 | +0.112 |
Fountain | +0.110 |
Neg logit contributions | |
backbone | -0.106 |
Kenn | -0.105 |
scale | -0.104 |
cale | -0.103 |
################################ | -0.101 |
Token | damage |
Token ID | 2465 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
backbone | +0.002 |
Kenn | +0.002 |
cale | +0.002 |
scale | +0.002 |
################################ | +0.002 |
Neg logit contributions | |
stice | -0.004 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | we |
Token ID | 356 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
backbone | +0.047 |
Kenn | +0.046 |
scale | +0.046 |
cale | +0.046 |
################################ | +0.045 |
Neg logit contributions | |
stice | -0.050 |
Hazard | -0.047 |
Premium | -0.045 |
神 | -0.045 |
Fountain | -0.044 |
Token | are |
Token ID | 389 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
backbone | +0.006 |
Kenn | +0.006 |
cale | +0.006 |
scale | +0.006 |
�� | +0.006 |
Neg logit contributions | |
stice | -0.007 |
Hazard | -0.007 |
神 | -0.007 |
Premium | -0.007 |
Fountain | -0.007 |
Token | unconsciously |
Token ID | 48570 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
stice | +0.028 |
Hazard | +0.026 |
Premium | +0.025 |
神 | +0.025 |
Fountain | +0.025 |
Neg logit contributions | |
backbone | -0.026 |
Kenn | -0.026 |
scale | -0.025 |
cale | -0.025 |
################################ | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
stice | +0.184 |
Hazard | +0.170 |
Premium | +0.163 |
神 | +0.163 |
Fountain | +0.159 |
Neg logit contributions | |
backbone | -0.204 |
Kenn | -0.203 |
scale | -0.201 |
cale | -0.200 |
################################ | -0.196 |
Token | consciously |
Token ID | 30410 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
stice | +0.003 |
Hazard | +0.003 |
Premium | +0.003 |
神 | +0.003 |
Fountain | +0.003 |
Neg logit contributions | |
backbone | -0.004 |
Kenn | -0.004 |
scale | -0.004 |
cale | -0.004 |
################################ | -0.004 |
Token | causing |
Token ID | 6666 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
stice | +0.190 |
Hazard | +0.175 |
Premium | +0.169 |
神 | +0.168 |
Fountain | +0.164 |
Neg logit contributions | |
backbone | -0.212 |
Kenn | -0.211 |
scale | -0.209 |
cale | -0.207 |
################################ | -0.204 |
Token | to |
Token ID | 284 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
stice | +0.073 |
Hazard | +0.068 |
Premium | +0.065 |
神 | +0.065 |
Fountain | +0.064 |
Neg logit contributions | |
backbone | -0.080 |
Kenn | -0.080 |
scale | -0.079 |
cale | -0.078 |
################################ | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
stice | +0.013 |
Hazard | +0.012 |
Premium | +0.012 |
神 | +0.012 |
Fountain | +0.011 |
Neg logit contributions | |
backbone | -0.013 |
Kenn | -0.013 |
scale | -0.013 |
cale | -0.013 |
################################ | -0.013 |
Token | ocean |
Token ID | 9151 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
stice | +0.005 |
Hazard | +0.005 |
Premium | +0.005 |
神 | +0.005 |
Fountain | +0.005 |
Neg logit contributions | |
backbone | -0.003 |
Kenn | -0.003 |
scale | -0.003 |
cale | -0.003 |
################################ | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
backbone | +0.132 |
scale | +0.130 |
Kenn | +0.129 |
cale | +0.127 |
################################ | +0.125 |
Neg logit contributions | |
stice | -0.151 |
Hazard | -0.140 |
Premium | -0.137 |
神 | -0.136 |
ottest | -0.133 |
Token | seats |
Token ID | 8632 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
stice | +0.073 |
Hazard | +0.067 |
Premium | +0.065 |
神 | +0.064 |
Fountain | +0.063 |
Neg logit contributions | |
backbone | -0.091 |
Kenn | -0.091 |
scale | -0.090 |
cale | -0.089 |
################################ | -0.088 |
Token | to |
Token ID | 284 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
stice | +0.221 |
Hazard | +0.203 |
Premium | +0.196 |
神 | +0.195 |
Fountain | +0.190 |
Neg logit contributions | |
backbone | -0.268 |
Kenn | -0.266 |
scale | -0.264 |
cale | -0.262 |
################################ | -0.258 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
stice | +0.007 |
Hazard | +0.007 |
Premium | +0.007 |
神 | +0.007 |
ottest | +0.006 |
Neg logit contributions | |
backbone | -0.009 |
Kenn | -0.009 |
scale | -0.009 |
cale | -0.008 |
################################ | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
stice | +0.002 |
Hazard | +0.002 |
Premium | +0.002 |
神 | +0.002 |
Fountain | +0.002 |
Neg logit contributions | |
backbone | -0.001 |
Kenn | -0.001 |
scale | -0.001 |
cale | -0.001 |
################################ | -0.001 |
Token | 000 |
Token ID | 830 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
backbone | +0.003 |
Kenn | +0.003 |
scale | +0.003 |
cale | +0.003 |
################################ | +0.003 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | seats |
Token ID | 8632 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
backbone | +0.017 |
Kenn | +0.017 |
scale | +0.017 |
cale | +0.017 |
################################ | +0.017 |
Neg logit contributions | |
stice | -0.018 |
Hazard | -0.017 |
Premium | -0.016 |
神 | -0.016 |
Fountain | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
stice | +0.253 |
Hazard | +0.236 |
Premium | +0.229 |
神 | +0.227 |
Fountain | +0.223 |
Neg logit contributions | |
backbone | -0.229 |
Kenn | -0.227 |
scale | -0.225 |
cale | -0.223 |
################################ | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
backbone | +0.012 |
Kenn | +0.012 |
scale | +0.012 |
cale | +0.012 |
################################ | +0.011 |
Neg logit contributions | |
stice | -0.012 |
Hazard | -0.011 |
Premium | -0.011 |
神 | -0.011 |
ottest | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
backbone | +0.004 |
Kenn | +0.004 |
scale | +0.004 |
cale | +0.004 |
�� | +0.004 |
Neg logit contributions | |
stice | -0.003 |
Hazard | -0.003 |
Premium | -0.003 |
神 | -0.003 |
Fountain | -0.003 |
Token | H |
Token ID | 39 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
backbone | +0.008 |
Kenn | +0.008 |
scale | +0.008 |
cale | +0.008 |
################################ | +0.007 |
Neg logit contributions | |
stice | -0.008 |
Hazard | -0.008 |
Premium | -0.007 |
神 | -0.007 |
Fountain | -0.007 |
Token | ower |
Token ID | 789 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
stice | +0.048 |
Hazard | +0.044 |
Premium | +0.042 |
神 | +0.042 |
Fountain | +0.041 |
Neg logit contributions | |
backbone | -0.061 |
Kenn | -0.060 |
scale | -0.060 |
cale | -0.059 |
################################ | -0.058 |