Token | pond |
Token ID | 16723 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
steep | +0.055 |
forget | +0.052 |
Josh | +0.051 |
also | +0.050 |
Josh | +0.048 |
Neg logit contributions | |
cient | -0.067 |
itt | -0.064 |
clay | -0.061 |
cuc | -0.059 |
lear | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
steep | +0.025 |
forget | +0.024 |
Josh | +0.024 |
also | +0.024 |
Josh | +0.023 |
Neg logit contributions | |
cient | -0.033 |
itt | -0.032 |
clay | -0.031 |
cuc | -0.030 |
lear | -0.027 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Josh | +0.019 |
steep | +0.019 |
forget | +0.018 |
annie | +0.017 |
ill | +0.017 |
Neg logit contributions | |
cient | -0.021 |
clay | -0.020 |
cuc | -0.019 |
itt | -0.019 |
lear | -0.018 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
cient | +0.064 |
clay | +0.061 |
itt | +0.061 |
cuc | +0.059 |
lear | +0.054 |
Neg logit contributions | |
steep | -0.055 |
Josh | -0.054 |
forget | -0.053 |
Josh | -0.051 |
also | -0.050 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
steep | +0.021 |
Josh | +0.021 |
forget | +0.021 |
Josh | +0.021 |
Dan | +0.021 |
Neg logit contributions | |
cient | -0.035 |
itt | -0.034 |
clay | -0.032 |
cuc | -0.032 |
lder | -0.031 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
clay | +0.076 |
cient | +0.071 |
itt | +0.070 |
lear | +0.070 |
cuc | +0.070 |
Neg logit contributions | |
steep | -0.040 |
Josh | -0.040 |
annie | -0.038 |
forget | -0.038 |
existed | -0.037 |
Token | ement |
Token ID | 972 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Josh | +0.327 |
Josh | +0.313 |
steep | +0.310 |
Dan | +0.305 |
also | +0.305 |
Neg logit contributions | |
cient | -0.446 |
itt | -0.412 |
clay | -0.408 |
cuc | -0.407 |
lear | -0.384 |
Token | as |
Token ID | 355 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
cient | +0.046 |
clay | +0.044 |
itt | +0.044 |
cuc | +0.042 |
lear | +0.038 |
Neg logit contributions | |
steep | -0.053 |
Josh | -0.052 |
forget | -0.052 |
also | -0.050 |
Josh | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
clay | +0.028 |
cient | +0.027 |
itt | +0.027 |
cuc | +0.025 |
lear | +0.024 |
Neg logit contributions | |
Josh | -0.027 |
steep | -0.027 |
forget | -0.026 |
ill | -0.024 |
Josh | -0.024 |
Token | thread |
Token ID | 4704 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
steep | +0.023 |
forget | +0.022 |
Josh | +0.022 |
also | +0.021 |
Josh | +0.021 |
Neg logit contributions | |
cient | -0.025 |
itt | -0.024 |
clay | -0.023 |
cuc | -0.023 |
lder | -0.021 |
Token | gl |
Token ID | 1278 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
cient | +0.020 |
clay | +0.020 |
itt | +0.019 |
cuc | +0.018 |
lear | +0.017 |
Neg logit contributions | |
steep | -0.020 |
Josh | -0.020 |
forget | -0.020 |
Josh | -0.019 |
also | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
steep | +0.079 |
forget | +0.077 |
also | +0.076 |
existed | +0.074 |
annie | +0.072 |
Neg logit contributions | |
itt | -0.074 |
cient | -0.073 |
lder | -0.065 |
d | -0.060 |
clay | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
forget | +0.018 |
steep | +0.018 |
existed | +0.016 |
hole | +0.015 |
adow | +0.015 |
Neg logit contributions | |
itt | -0.013 |
d | -0.011 |
cient | -0.011 |
clay | -0.011 |
B | -0.010 |
Token | Sam |
Token ID | 16305 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
steep | +0.012 |
forget | +0.012 |
existed | +0.012 |
hole | +0.011 |
also | +0.011 |
Neg logit contributions | |
itt | -0.012 |
P | -0.011 |
B | -0.011 |
cient | -0.011 |
d | -0.010 |
Token | gasped |
Token ID | 45236 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
steep | +0.064 |
forget | +0.060 |
Josh | +0.060 |
existed | +0.057 |
Sof | +0.056 |
Neg logit contributions | |
cient | -0.068 |
clay | -0.062 |
itt | -0.060 |
cuc | -0.059 |
lder | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
cient | +0.001 |
clay | +0.001 |
itt | +0.001 |
cuc | +0.001 |
lear | +0.001 |
Neg logit contributions | |
steep | -0.002 |
Josh | -0.001 |
forget | -0.001 |
also | -0.001 |
Josh | -0.001 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
clay | +0.061 |
cuc | +0.056 |
cient | +0.055 |
itt | +0.054 |
lear | +0.053 |
Neg logit contributions | |
steep | -0.071 |
existed | -0.064 |
adow | -0.064 |
forget | -0.062 |
ill | -0.062 |
Token | ement |
Token ID | 972 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Josh | +0.372 |
steep | +0.368 |
Josh | +0.355 |
forget | +0.355 |
also | +0.351 |
Neg logit contributions | |
cient | -0.394 |
clay | -0.373 |
itt | -0.372 |
cuc | -0.356 |
lear | -0.330 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
cient | +0.060 |
clay | +0.057 |
itt | +0.057 |
cuc | +0.054 |
lear | +0.049 |
Neg logit contributions | |
steep | -0.080 |
Josh | -0.080 |
forget | -0.079 |
also | -0.075 |
Josh | -0.073 |
Token | He |
Token ID | 679 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
cient | +0.008 |
itt | +0.008 |
clay | +0.008 |
cuc | +0.008 |
lear | +0.007 |
Neg logit contributions | |
forget | -0.010 |
steep | -0.009 |
Josh | -0.009 |
also | -0.009 |
annie | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.008 |
ill | +0.008 |
Sof | +0.008 |
Neg logit contributions | |
cient | -0.009 |
clay | -0.008 |
cuc | -0.008 |
itt | -0.008 |
lear | -0.007 |
Token | never |
Token ID | 1239 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
steep | +0.060 |
Josh | +0.055 |
forget | +0.055 |
adow | +0.053 |
ibi | +0.052 |
Neg logit contributions | |
clay | -0.060 |
cuc | -0.057 |
cient | -0.056 |
itt | -0.056 |
printer | -0.055 |
Token | around |
Token ID | 1088 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
cient | +0.064 |
clay | +0.061 |
itt | +0.060 |
cuc | +0.057 |
lear | +0.054 |
Neg logit contributions | |
steep | -0.059 |
Josh | -0.059 |
forget | -0.056 |
Josh | -0.055 |
Sof | -0.054 |
Token | stopped |
Token ID | 5025 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
cient | +0.045 |
itt | +0.044 |
clay | +0.043 |
cuc | +0.042 |
lder | +0.038 |
Neg logit contributions | |
forget | -0.036 |
Josh | -0.036 |
steep | -0.035 |
Josh | -0.035 |
also | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
steep | +0.005 |
Josh | +0.004 |
forget | +0.004 |
Josh | +0.004 |
also | +0.004 |
Neg logit contributions | |
cient | -0.005 |
clay | -0.005 |
itt | -0.005 |
cuc | -0.004 |
lear | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Josh | +0.026 |
steep | +0.026 |
forget | +0.024 |
Josh | +0.024 |
ill | +0.023 |
Neg logit contributions | |
cient | -0.028 |
clay | -0.027 |
itt | -0.025 |
cuc | -0.025 |
lear | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Josh | +0.027 |
Dan | +0.026 |
Josh | +0.025 |
forget | +0.025 |
Sof | +0.025 |
Neg logit contributions | |
cient | -0.040 |
itt | -0.040 |
cuc | -0.037 |
clay | -0.036 |
lder | -0.035 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
clay | +0.075 |
cient | +0.074 |
itt | +0.072 |
cuc | +0.070 |
lear | +0.069 |
Neg logit contributions | |
steep | -0.040 |
Josh | -0.039 |
forget | -0.037 |
also | -0.035 |
Josh | -0.035 |
Token | ement |
Token ID | 972 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Josh | +0.324 |
Josh | +0.311 |
steep | +0.307 |
ill | +0.303 |
Dan | +0.302 |
Neg logit contributions | |
cient | -0.442 |
itt | -0.413 |
cuc | -0.408 |
clay | -0.407 |
lear | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
cient | +0.056 |
itt | +0.054 |
clay | +0.053 |
cuc | +0.051 |
lear | +0.046 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.059 |
forget | -0.059 |
Josh | -0.057 |
also | -0.057 |
Token | They |
Token ID | 1119 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
Josh | +0.009 |
steep | +0.009 |
Josh | +0.009 |
forget | +0.009 |
also | +0.008 |
Neg logit contributions | |
cient | -0.010 |
clay | -0.009 |
itt | -0.009 |
cuc | -0.009 |
lear | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
cient | +0.047 |
clay | +0.041 |
lear | +0.040 |
cuc | +0.040 |
itt | +0.039 |
Neg logit contributions | |
steep | -0.051 |
Josh | -0.050 |
Sof | -0.048 |
ill | -0.046 |
Josh | -0.046 |
Token | so |
Token ID | 523 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
steep | +0.032 |
existed | +0.031 |
forget | +0.031 |
Josh | +0.031 |
ill | +0.030 |
Neg logit contributions | |
clay | -0.036 |
cient | -0.035 |
soldiers | -0.032 |
cuc | -0.031 |
itt | -0.031 |
Token | looked |
Token ID | 3114 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
steep | +0.014 |
Josh | +0.014 |
forget | +0.013 |
ill | +0.013 |
Josh | +0.013 |
Neg logit contributions | |
cient | -0.015 |
clay | -0.015 |
itt | -0.015 |
cuc | -0.014 |
lear | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
cient | +0.051 |
itt | +0.049 |
clay | +0.048 |
cuc | +0.046 |
lear | +0.042 |
Neg logit contributions | |
steep | -0.049 |
forget | -0.047 |
Josh | -0.047 |
also | -0.046 |
Josh | -0.045 |
Token | each |
Token ID | 1123 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
cient | +0.006 |
itt | +0.006 |
clay | +0.006 |
cuc | +0.006 |
lear | +0.005 |
Neg logit contributions | |
steep | -0.005 |
Josh | -0.005 |
forget | -0.005 |
also | -0.005 |
Josh | -0.005 |
Token | other |
Token ID | 584 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
cient | +0.089 |
itt | +0.082 |
clay | +0.078 |
cuc | +0.077 |
lder | +0.071 |
Neg logit contributions | |
forget | -0.093 |
Josh | -0.092 |
also | -0.092 |
steep | -0.091 |
Josh | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
cient | +0.007 |
clay | +0.007 |
itt | +0.007 |
cuc | +0.006 |
lear | +0.006 |
Neg logit contributions | |
Josh | -0.008 |
steep | -0.008 |
forget | -0.008 |
Josh | -0.008 |
also | -0.008 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
clay | +0.073 |
cient | +0.072 |
itt | +0.070 |
cuc | +0.067 |
lear | +0.064 |
Neg logit contributions | |
steep | -0.056 |
Josh | -0.054 |
forget | -0.054 |
also | -0.051 |
Josh | -0.050 |
Token | ement |
Token ID | 972 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Josh | +0.328 |
steep | +0.318 |
Josh | +0.314 |
also | +0.311 |
ill | +0.309 |
Neg logit contributions | |
cient | -0.438 |
itt | -0.405 |
clay | -0.402 |
cuc | -0.402 |
lear | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
cient | +0.061 |
itt | +0.058 |
clay | +0.058 |
cuc | +0.055 |
lear | +0.050 |
Neg logit contributions | |
steep | -0.069 |
Josh | -0.068 |
forget | -0.067 |
also | -0.065 |
Josh | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
cient | +0.010 |
itt | +0.010 |
clay | +0.010 |
cuc | +0.009 |
lear | +0.008 |
Neg logit contributions | |
steep | -0.009 |
forget | -0.009 |
Josh | -0.009 |
also | -0.008 |
Josh | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
steep | +0.011 |
forget | +0.011 |
Josh | +0.010 |
Josh | +0.010 |
also | +0.009 |
Neg logit contributions | |
itt | -0.014 |
cient | -0.014 |
clay | -0.014 |
cuc | -0.013 |
lder | -0.012 |
Token | They |
Token ID | 2990 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.008 |
also | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
cient | -0.013 |
itt | -0.013 |
clay | -0.013 |
cuc | -0.012 |
lear | -0.012 |
Token | wind |
Token ID | 2344 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
steep | +0.023 |
forget | +0.022 |
also | +0.021 |
Josh | +0.021 |
Josh | +0.020 |
Neg logit contributions | |
cient | -0.022 |
itt | -0.022 |
clay | -0.020 |
cuc | -0.020 |
lder | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
cient | +0.049 |
clay | +0.048 |
itt | +0.047 |
cuc | +0.044 |
lear | +0.041 |
Neg logit contributions | |
Josh | -0.051 |
steep | -0.050 |
forget | -0.049 |
Josh | -0.048 |
also | -0.047 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
steep | +0.001 |
Josh | +0.001 |
forget | +0.001 |
also | +0.001 |
Josh | +0.001 |
Neg logit contributions | |
cient | -0.001 |
itt | -0.001 |
clay | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | watched |
Token ID | 7342 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
cient | +0.074 |
clay | +0.072 |
itt | +0.072 |
cuc | +0.066 |
lear | +0.065 |
Neg logit contributions | |
steep | -0.071 |
Josh | -0.069 |
forget | -0.068 |
Josh | -0.065 |
Sof | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Josh | +0.026 |
steep | +0.026 |
forget | +0.025 |
Josh | +0.025 |
also | +0.025 |
Neg logit contributions | |
cient | -0.040 |
itt | -0.039 |
cuc | -0.038 |
clay | -0.037 |
lder | -0.035 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
clay | +0.075 |
cient | +0.072 |
itt | +0.071 |
lear | +0.069 |
cuc | +0.068 |
Neg logit contributions | |
steep | -0.044 |
Josh | -0.044 |
forget | -0.042 |
annie | -0.040 |
existed | -0.040 |
Token | ement |
Token ID | 972 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Josh | +0.351 |
steep | +0.340 |
Josh | +0.336 |
also | +0.329 |
Dan | +0.326 |
Neg logit contributions | |
cient | -0.417 |
itt | -0.390 |
clay | -0.387 |
cuc | -0.385 |
lear | -0.351 |
Token | . |
Token ID | 13 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
cient | +0.054 |
clay | +0.052 |
itt | +0.052 |
cuc | +0.048 |
lear | +0.045 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.060 |
forget | -0.058 |
also | -0.056 |
Josh | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
steep | +0.003 |
Josh | +0.003 |
forget | +0.003 |
also | +0.003 |
Josh | +0.003 |
Neg logit contributions | |
cient | -0.004 |
itt | -0.004 |
clay | -0.004 |
cuc | -0.004 |
lear | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
forget | +0.025 |
steep | +0.025 |
Josh | +0.023 |
existed | +0.022 |
annie | +0.022 |
Neg logit contributions | |
itt | -0.025 |
clay | -0.024 |
cient | -0.023 |
cuc | -0.020 |
d | -0.020 |
Token | The |
Token ID | 464 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
steep | +0.018 |
forget | +0.017 |
Josh | +0.017 |
Josh | +0.016 |
also | +0.016 |
Neg logit contributions | |
cient | -0.028 |
itt | -0.027 |
clay | -0.027 |
cuc | -0.026 |
lear | -0.024 |
Token | looked |
Token ID | 3114 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
cient | +0.168 |
itt | +0.162 |
clay | +0.162 |
cuc | +0.154 |
lear | +0.143 |
Neg logit contributions | |
steep | -0.126 |
Josh | -0.125 |
forget | -0.123 |
also | -0.118 |
Josh | -0.118 |
Token | at |
Token ID | 379 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
cient | +0.043 |
clay | +0.042 |
itt | +0.040 |
cuc | +0.039 |
lear | +0.036 |
Neg logit contributions | |
Josh | -0.046 |
steep | -0.045 |
forget | -0.044 |
Josh | -0.043 |
also | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
clay | +0.003 |
cient | +0.003 |
itt | +0.003 |
cuc | +0.003 |
lear | +0.002 |
Neg logit contributions | |
steep | -0.003 |
Josh | -0.003 |
forget | -0.003 |
Josh | -0.002 |
also | -0.002 |
Token | bug |
Token ID | 5434 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
steep | +0.017 |
forget | +0.017 |
Josh | +0.016 |
also | +0.016 |
Josh | +0.016 |
Neg logit contributions | |
cient | -0.014 |
itt | -0.013 |
clay | -0.013 |
cuc | -0.012 |
lear | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
clay | +0.047 |
cient | +0.047 |
itt | +0.045 |
cuc | +0.043 |
lear | +0.040 |
Neg logit contributions | |
Josh | -0.044 |
steep | -0.042 |
forget | -0.041 |
Josh | -0.040 |
Dan | -0.039 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
clay | +0.064 |
itt | +0.059 |
cuc | +0.058 |
cient | +0.057 |
lear | +0.057 |
Neg logit contributions | |
steep | -0.055 |
Josh | -0.052 |
forget | -0.049 |
annie | -0.049 |
adow | -0.048 |
Token | ement |
Token ID | 972 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
steep | +0.396 |
Josh | +0.393 |
forget | +0.388 |
also | +0.374 |
Josh | +0.374 |
Neg logit contributions | |
cient | -0.366 |
itt | -0.349 |
clay | -0.349 |
cuc | -0.330 |
lear | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
clay | +0.051 |
cient | +0.050 |
itt | +0.049 |
cuc | +0.045 |
lear | +0.043 |
Neg logit contributions | |
Josh | -0.066 |
steep | -0.064 |
forget | -0.062 |
Josh | -0.059 |
also | -0.058 |
Token | She |
Token ID | 1375 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.008 |
Josh | +0.008 |
also | +0.008 |
Neg logit contributions | |
cient | -0.013 |
itt | -0.013 |
clay | -0.012 |
cuc | -0.012 |
lear | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.007 |
Josh | +0.007 |
Sof | +0.007 |
Neg logit contributions | |
cient | -0.008 |
itt | -0.008 |
clay | -0.008 |
cuc | -0.008 |
lear | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
clay | +0.030 |
cient | +0.026 |
te | +0.026 |
itt | +0.026 |
cuc | +0.026 |
Neg logit contributions | |
Josh | -0.030 |
steep | -0.029 |
ibi | -0.029 |
forget | -0.028 |
Dan | -0.028 |
Token | at |
Token ID | 379 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
cient | +0.047 |
clay | +0.046 |
itt | +0.043 |
cuc | +0.043 |
lear | +0.039 |
Neg logit contributions | |
Josh | -0.050 |
steep | -0.048 |
forget | -0.048 |
Josh | -0.047 |
also | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
cient | +0.003 |
clay | +0.003 |
itt | +0.003 |
cuc | +0.003 |
lear | +0.003 |
Neg logit contributions | |
steep | -0.003 |
Josh | -0.003 |
forget | -0.003 |
Josh | -0.003 |
also | -0.003 |
Token | bright |
Token ID | 6016 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
forget | +0.012 |
steep | +0.011 |
also | +0.011 |
Josh | +0.011 |
Josh | +0.010 |
Neg logit contributions | |
cient | -0.011 |
itt | -0.010 |
clay | -0.010 |
cuc | -0.009 |
lder | -0.009 |
Token | colours |
Token ID | 18915 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
cient | +0.027 |
itt | +0.026 |
clay | +0.025 |
cuc | +0.024 |
lear | +0.022 |
Neg logit contributions | |
steep | -0.026 |
Josh | -0.026 |
forget | -0.026 |
also | -0.025 |
Josh | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
clay | +0.006 |
itt | +0.006 |
cuc | +0.006 |
cient | +0.006 |
ware | +0.005 |
Neg logit contributions | |
Josh | -0.007 |
steep | -0.007 |
forget | -0.007 |
Josh | -0.006 |
Phill | -0.006 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
cient | +0.054 |
clay | +0.053 |
itt | +0.052 |
cuc | +0.050 |
lear | +0.046 |
Neg logit contributions | |
steep | -0.045 |
Josh | -0.045 |
forget | -0.044 |
Josh | -0.042 |
also | -0.042 |
Token | ement |
Token ID | 972 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Josh | +0.328 |
steep | +0.327 |
ill | +0.316 |
also | +0.314 |
Josh | +0.314 |
Neg logit contributions | |
cient | -0.435 |
itt | -0.399 |
clay | -0.392 |
cuc | -0.390 |
lear | -0.365 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
clay | +0.050 |
cient | +0.049 |
itt | +0.047 |
cuc | +0.044 |
lear | +0.041 |
Neg logit contributions | |
Josh | -0.068 |
steep | -0.067 |
forget | -0.065 |
also | -0.061 |
Josh | -0.061 |
Token | awe |
Token ID | 25030 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Josh | +0.015 |
steep | +0.014 |
forget | +0.014 |
ill | +0.014 |
annie | +0.013 |
Neg logit contributions | |
clay | -0.016 |
cient | -0.015 |
cuc | -0.015 |
itt | -0.014 |
lear | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
steep | +0.164 |
forget | +0.157 |
Josh | +0.156 |
also | +0.155 |
Josh | +0.153 |
Neg logit contributions | |
cient | -0.183 |
itt | -0.174 |
clay | -0.168 |
cuc | -0.163 |
lder | -0.153 |
Token | He |
Token ID | 679 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
cient | +0.001 |
itt | +0.001 |
clay | +0.001 |
cuc | +0.001 |
lear | +0.001 |
Neg logit contributions | |
steep | -0.001 |
forget | -0.001 |
Josh | -0.001 |
also | -0.001 |
Josh | -0.001 |
Token | Her |
Token ID | 2332 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
steep | +0.004 |
Josh | +0.004 |
forget | +0.004 |
also | +0.004 |
Josh | +0.004 |
Neg logit contributions | |
cient | -0.005 |
itt | -0.005 |
clay | -0.005 |
cuc | -0.005 |
lear | -0.005 |
Token | best |
Token ID | 1266 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
cient | +0.037 |
clay | +0.037 |
itt | +0.036 |
cuc | +0.034 |
lear | +0.032 |
Neg logit contributions | |
steep | -0.030 |
Josh | -0.030 |
forget | -0.029 |
ill | -0.028 |
Josh | -0.027 |
Token | friend |
Token ID | 1545 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
steep | +0.167 |
Josh | +0.162 |
forget | +0.155 |
Sof | +0.152 |
Josh | +0.152 |
Neg logit contributions | |
clay | -0.118 |
cient | -0.112 |
itt | -0.112 |
cuc | -0.105 |
lear | -0.105 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
cient | +0.049 |
clay | +0.047 |
itt | +0.045 |
cuc | +0.044 |
lear | +0.042 |
Neg logit contributions | |
steep | -0.050 |
Josh | -0.049 |
forget | -0.048 |
also | -0.044 |
Josh | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Josh | +0.025 |
Mary | +0.024 |
Sof | +0.023 |
Dan | +0.023 |
also | +0.023 |
Neg logit contributions | |
cient | -0.037 |
itt | -0.037 |
cuc | -0.034 |
clay | -0.033 |
lder | -0.033 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
clay | +0.063 |
cient | +0.060 |
itt | +0.058 |
cuc | +0.057 |
lear | +0.057 |
Neg logit contributions | |
steep | -0.054 |
Josh | -0.054 |
forget | -0.052 |
annie | -0.050 |
existed | -0.049 |
Token | ement |
Token ID | 972 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Josh | +0.331 |
Josh | +0.319 |
steep | +0.316 |
also | +0.310 |
ill | +0.309 |
Neg logit contributions | |
cient | -0.434 |
itt | -0.404 |
clay | -0.400 |
cuc | -0.400 |
lear | -0.369 |
Token | as |
Token ID | 355 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
cient | +0.063 |
itt | +0.060 |
clay | +0.060 |
cuc | +0.057 |
lear | +0.052 |
Neg logit contributions | |
steep | -0.065 |
Josh | -0.064 |
forget | -0.064 |
also | -0.062 |
Josh | -0.062 |
Token | Amelia |
Token ID | 49769 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
cient | +0.026 |
clay | +0.026 |
itt | +0.025 |
cuc | +0.024 |
lear | +0.023 |
Neg logit contributions | |
steep | -0.022 |
Josh | -0.021 |
forget | -0.021 |
also | -0.019 |
ill | -0.019 |
Token | gigg |
Token ID | 30442 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
forget | +0.039 |
Josh | +0.039 |
steep | +0.039 |
also | +0.038 |
Josh | +0.037 |
Neg logit contributions | |
cient | -0.051 |
clay | -0.050 |
itt | -0.049 |
cuc | -0.046 |
lear | -0.042 |
Token | led |
Token ID | 992 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
also | +0.044 |
steep | +0.043 |
existed | +0.043 |
ax | +0.042 |
ill | +0.042 |
Neg logit contributions | |
itt | -0.029 |
cient | -0.027 |
clay | -0.026 |
printer | -0.026 |
cuc | -0.025 |
Token | The |
Token ID | 383 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
steep | +0.007 |
forget | +0.007 |
Josh | +0.007 |
also | +0.006 |
Josh | +0.006 |
Neg logit contributions | |
cient | -0.008 |
itt | -0.008 |
clay | -0.008 |
cuc | -0.007 |
lear | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
cient | +0.111 |
itt | +0.107 |
cuc | +0.101 |
clay | +0.100 |
lder | +0.094 |
Neg logit contributions | |
forget | -0.092 |
steep | -0.088 |
also | -0.088 |
Josh | -0.087 |
Josh | -0.083 |
Token | boy |
Token ID | 2933 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
cient | +0.081 |
itt | +0.078 |
clay | +0.074 |
cuc | +0.072 |
lder | +0.067 |
Neg logit contributions | |
forget | -0.067 |
steep | -0.066 |
Josh | -0.066 |
Josh | -0.064 |
also | -0.064 |
Token | watched |
Token ID | 7342 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
steep | +0.038 |
Josh | +0.037 |
forget | +0.036 |
Josh | +0.035 |
Sof | +0.034 |
Neg logit contributions | |
cient | -0.041 |
clay | -0.040 |
itt | -0.040 |
cuc | -0.038 |
lear | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Josh | +0.024 |
also | +0.024 |
Dan | +0.024 |
steep | +0.023 |
forget | +0.023 |
Neg logit contributions | |
cient | -0.041 |
itt | -0.041 |
lder | -0.037 |
cuc | -0.037 |
clay | -0.036 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
clay | +0.083 |
cient | +0.082 |
itt | +0.080 |
cuc | +0.079 |
lear | +0.076 |
Neg logit contributions | |
steep | -0.034 |
Josh | -0.033 |
forget | -0.032 |
also | -0.029 |
annie | -0.029 |
Token | ement |
Token ID | 972 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Josh | +0.349 |
steep | +0.338 |
Josh | +0.334 |
also | +0.329 |
Dan | +0.325 |
Neg logit contributions | |
cient | -0.416 |
itt | -0.390 |
clay | -0.386 |
cuc | -0.379 |
lear | -0.351 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
cient | +0.058 |
itt | +0.055 |
clay | +0.055 |
cuc | +0.052 |
lear | +0.048 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.060 |
forget | -0.059 |
also | -0.057 |
Josh | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
forget | +0.005 |
steep | +0.005 |
Josh | +0.005 |
also | +0.004 |
annie | +0.004 |
Neg logit contributions | |
cient | -0.006 |
itt | -0.006 |
clay | -0.006 |
cuc | -0.005 |
lear | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
forget | +0.021 |
steep | +0.021 |
existed | +0.019 |
Josh | +0.019 |
Sof | +0.018 |
Neg logit contributions | |
itt | -0.020 |
clay | -0.019 |
cient | -0.018 |
d | -0.017 |
cuc | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
steep | +0.015 |
forget | +0.015 |
Josh | +0.014 |
Josh | +0.013 |
Sof | +0.013 |
Neg logit contributions | |
itt | -0.024 |
cient | -0.024 |
clay | -0.023 |
cuc | -0.022 |
lear | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
forget | +0.001 |
steep | +0.001 |
Josh | +0.001 |
adow | +0.001 |
annie | +0.001 |
Neg logit contributions | |
clay | -0.001 |
cient | -0.001 |
cuc | -0.001 |
itt | -0.001 |
soldiers | -0.001 |
Token | zipper |
Token ID | 48992 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
Josh | +0.012 |
Josh | +0.012 |
steep | +0.011 |
ill | +0.011 |
Dan | +0.011 |
Neg logit contributions | |
cient | -0.016 |
clay | -0.016 |
itt | -0.015 |
printer | -0.015 |
cuc | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Josh | +0.169 |
steep | +0.166 |
forget | +0.166 |
Josh | +0.155 |
also | +0.152 |
Neg logit contributions | |
cient | -0.186 |
itt | -0.180 |
clay | -0.179 |
cuc | -0.168 |
printer | -0.157 |
Token | gasped |
Token ID | 45236 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
steep | +0.023 |
Josh | +0.022 |
forget | +0.021 |
Sof | +0.020 |
ill | +0.020 |
Neg logit contributions | |
cient | -0.020 |
clay | -0.019 |
itt | -0.019 |
cuc | -0.019 |
ted | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
steep | +0.007 |
Josh | +0.007 |
forget | +0.007 |
Josh | +0.007 |
also | +0.007 |
Neg logit contributions | |
cient | -0.008 |
itt | -0.008 |
clay | -0.007 |
cuc | -0.007 |
lear | -0.007 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
clay | +0.051 |
cient | +0.048 |
cuc | +0.047 |
itt | +0.047 |
soldiers | +0.042 |
Neg logit contributions | |
steep | -0.048 |
Josh | -0.046 |
forget | -0.045 |
existed | -0.045 |
ill | -0.043 |
Token | ement |
Token ID | 972 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Josh | +0.305 |
steep | +0.295 |
Josh | +0.292 |
ill | +0.290 |
also | +0.288 |
Neg logit contributions | |
cient | -0.455 |
itt | -0.422 |
clay | -0.417 |
cuc | -0.414 |
lear | -0.389 |
Token | at |
Token ID | 379 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
cient | +0.060 |
itt | +0.057 |
clay | +0.057 |
cuc | +0.054 |
lear | +0.049 |
Neg logit contributions | |
steep | -0.062 |
Josh | -0.061 |
forget | -0.060 |
Josh | -0.059 |
also | -0.058 |
Token | all |
Token ID | 477 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
cient | +0.004 |
clay | +0.004 |
itt | +0.004 |
cuc | +0.004 |
printer | +0.004 |
Neg logit contributions | |
steep | -0.003 |
Josh | -0.003 |
forget | -0.003 |
also | -0.003 |
Josh | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
clay | +0.022 |
cient | +0.019 |
itt | +0.018 |
cuc | +0.017 |
soldiers | +0.017 |
Neg logit contributions | |
forget | -0.028 |
Josh | -0.027 |
steep | -0.027 |
Phill | -0.026 |
Sof | -0.025 |
Token | treasures |
Token ID | 29561 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Josh | +0.016 |
ill | +0.016 |
steep | +0.016 |
Josh | +0.015 |
Sof | +0.015 |
Neg logit contributions | |
clay | -0.014 |
cient | -0.013 |
itt | -0.012 |
cuc | -0.012 |
printer | -0.012 |
Token | both |
Token ID | 1111 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
cient | +0.061 |
clay | +0.059 |
itt | +0.057 |
cuc | +0.056 |
lear | +0.052 |
Neg logit contributions | |
steep | -0.053 |
Josh | -0.053 |
Josh | -0.049 |
Sof | -0.048 |
forget | -0.048 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
cient | +0.038 |
clay | +0.037 |
itt | +0.037 |
cuc | +0.036 |
lear | +0.033 |
Neg logit contributions | |
steep | -0.032 |
Josh | -0.031 |
forget | -0.029 |
Josh | -0.029 |
Sof | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.008 |
also | +0.008 |
Josh | +0.008 |
Neg logit contributions | |
cient | -0.012 |
itt | -0.012 |
clay | -0.011 |
cuc | -0.011 |
lear | -0.010 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
steep | +0.019 |
Josh | +0.019 |
forget | +0.017 |
ill | +0.017 |
annie | +0.017 |
Neg logit contributions | |
cient | -0.019 |
clay | -0.018 |
itt | -0.018 |
cuc | -0.017 |
lear | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
cient | +0.062 |
clay | +0.060 |
itt | +0.058 |
cuc | +0.056 |
lear | +0.052 |
Neg logit contributions | |
Josh | -0.069 |
steep | -0.069 |
forget | -0.067 |
Josh | -0.065 |
also | -0.065 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
clay | +0.070 |
cient | +0.070 |
itt | +0.068 |
cuc | +0.066 |
lear | +0.062 |
Neg logit contributions | |
steep | -0.053 |
Josh | -0.052 |
forget | -0.050 |
Josh | -0.048 |
also | -0.048 |
Token | ement |
Token ID | 972 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Josh | +0.314 |
Josh | +0.304 |
ill | +0.298 |
steep | +0.297 |
Dan | +0.297 |
Neg logit contributions | |
cient | -0.450 |
itt | -0.416 |
cuc | -0.412 |
clay | -0.411 |
lear | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
cient | +0.063 |
itt | +0.060 |
clay | +0.059 |
cuc | +0.057 |
printer | +0.051 |
Neg logit contributions | |
steep | -0.059 |
forget | -0.058 |
Josh | -0.058 |
Josh | -0.057 |
also | -0.056 |
Token | Bob |
Token ID | 5811 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
steep | +0.007 |
forget | +0.007 |
Josh | +0.007 |
also | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
cient | -0.008 |
itt | -0.008 |
clay | -0.008 |
cuc | -0.007 |
lear | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
steep | +0.044 |
Josh | +0.043 |
forget | +0.041 |
Josh | +0.040 |
Sof | +0.039 |
Neg logit contributions | |
cient | -0.052 |
clay | -0.051 |
itt | -0.050 |
cuc | -0.048 |
lear | -0.045 |
Token | printed |
Token ID | 10398 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
steep | +0.075 |
Josh | +0.071 |
forget | +0.069 |
existed | +0.066 |
Josh | +0.066 |
Neg logit contributions | |
clay | -0.065 |
cuc | -0.062 |
cient | -0.061 |
itt | -0.059 |
printer | -0.056 |
Token | line |
Token ID | 1627 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
cient | +0.062 |
clay | +0.062 |
itt | +0.060 |
cuc | +0.058 |
lear | +0.054 |
Neg logit contributions | |
steep | -0.055 |
Josh | -0.054 |
forget | -0.054 |
also | -0.051 |
Josh | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Josh | +0.049 |
steep | +0.049 |
forget | +0.048 |
Josh | +0.046 |
also | +0.046 |
Neg logit contributions | |
cient | -0.044 |
clay | -0.042 |
itt | -0.042 |
cuc | -0.040 |
lear | -0.036 |
Token | Billy |
Token ID | 15890 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
steep | +0.013 |
Josh | +0.013 |
forget | +0.012 |
Josh | +0.012 |
also | +0.012 |
Neg logit contributions | |
cient | -0.018 |
itt | -0.017 |
clay | -0.017 |
cuc | -0.017 |
lear | -0.015 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
cient | +0.009 |
clay | +0.009 |
itt | +0.009 |
cuc | +0.008 |
lear | +0.008 |
Neg logit contributions | |
steep | -0.008 |
Josh | -0.008 |
forget | -0.008 |
Josh | -0.007 |
Sof | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Josh | +0.021 |
Dan | +0.021 |
also | +0.021 |
about | +0.020 |
Matt | +0.019 |
Neg logit contributions | |
cient | -0.039 |
itt | -0.038 |
lder | -0.035 |
P | -0.034 |
ase | -0.033 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.15e+00 |
Pos logit contributions | |
clay | +0.078 |
cient | +0.075 |
itt | +0.074 |
cuc | +0.073 |
lear | +0.070 |
Neg logit contributions | |
steep | -0.042 |
Josh | -0.042 |
forget | -0.040 |
annie | -0.038 |
also | -0.038 |
Token | ement |
Token ID | 972 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Josh | +0.332 |
Josh | +0.321 |
steep | +0.314 |
Dan | +0.313 |
also | +0.306 |
Neg logit contributions | |
cient | -0.434 |
itt | -0.402 |
clay | -0.397 |
cuc | -0.393 |
lear | -0.373 |
Token | as |
Token ID | 355 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
cient | +0.055 |
itt | +0.052 |
clay | +0.052 |
cuc | +0.049 |
lear | +0.045 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.059 |
forget | -0.058 |
also | -0.056 |
Josh | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
cient | +0.032 |
clay | +0.032 |
itt | +0.031 |
cuc | +0.030 |
lear | +0.028 |
Neg logit contributions | |
steep | -0.025 |
Josh | -0.025 |
forget | -0.025 |
also | -0.023 |
Josh | -0.023 |
Token | ro |
Token ID | 686 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
steep | +0.017 |
Josh | +0.017 |
forget | +0.017 |
also | +0.017 |
Josh | +0.016 |
Neg logit contributions | |
cient | -0.015 |
itt | -0.015 |
clay | -0.014 |
cuc | -0.013 |
ware | -0.012 |
Token | oster |
Token ID | 6197 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
clay | +0.003 |
cuc | +0.003 |
cient | +0.003 |
lear | +0.003 |
beans | +0.003 |
Neg logit contributions | |
Josh | -0.004 |
steep | -0.004 |
also | -0.004 |
adow | -0.004 |
Josh | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
steep | +0.018 |
Josh | +0.018 |
forget | +0.017 |
ill | +0.017 |
annie | +0.016 |
Neg logit contributions | |
clay | -0.018 |
cient | -0.018 |
itt | -0.018 |
cuc | -0.017 |
lear | -0.017 |
Token | little |
Token ID | 1310 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
forget | +0.017 |
steep | +0.016 |
also | +0.016 |
Josh | +0.016 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.015 |
cuc | -0.014 |
clay | -0.014 |
lder | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
cient | +0.066 |
itt | +0.063 |
clay | +0.058 |
cuc | +0.057 |
lder | +0.053 |
Neg logit contributions | |
steep | -0.072 |
forget | -0.071 |
Josh | -0.068 |
Josh | -0.068 |
also | -0.068 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
steep | +0.010 |
Josh | +0.010 |
forget | +0.010 |
Josh | +0.009 |
Sof | +0.009 |
Neg logit contributions | |
cient | -0.011 |
itt | -0.010 |
clay | -0.010 |
cuc | -0.009 |
lear | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Josh | +0.025 |
Dan | +0.024 |
Mary | +0.024 |
forget | +0.024 |
Sof | +0.023 |
Neg logit contributions | |
cient | -0.039 |
itt | -0.037 |
cuc | -0.034 |
lder | -0.034 |
clay | -0.033 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
clay | +0.069 |
cient | +0.065 |
itt | +0.064 |
cuc | +0.062 |
lear | +0.061 |
Neg logit contributions | |
Josh | -0.046 |
steep | -0.046 |
forget | -0.043 |
annie | -0.042 |
also | -0.041 |
Token | ement |
Token ID | 972 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Josh | +0.318 |
Josh | +0.305 |
steep | +0.298 |
ill | +0.298 |
also | +0.296 |
Neg logit contributions | |
cient | -0.448 |
cuc | -0.409 |
itt | -0.408 |
clay | -0.403 |
lear | -0.384 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
cient | +0.058 |
itt | +0.055 |
clay | +0.055 |
cuc | +0.052 |
lear | +0.047 |
Neg logit contributions | |
steep | -0.062 |
Josh | -0.061 |
forget | -0.061 |
also | -0.059 |
Josh | -0.059 |
Token | Mama |
Token ID | 40084 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
steep | +0.006 |
Josh | +0.006 |
forget | +0.005 |
also | +0.005 |
Josh | +0.005 |
Neg logit contributions | |
cient | -0.007 |
itt | -0.007 |
clay | -0.007 |
cuc | -0.007 |
lear | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
steep | +0.050 |
forget | +0.047 |
Josh | +0.047 |
Sof | +0.044 |
existed | +0.044 |
Neg logit contributions | |
cient | -0.051 |
itt | -0.049 |
clay | -0.049 |
cuc | -0.047 |
lear | -0.044 |
Token | fingers |
Token ID | 9353 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
steep | +0.071 |
forget | +0.070 |
Josh | +0.070 |
also | +0.068 |
Josh | +0.067 |
Neg logit contributions | |
cient | -0.092 |
itt | -0.089 |
clay | -0.087 |
cuc | -0.085 |
ware | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
cient | +0.057 |
itt | +0.053 |
clay | +0.051 |
cuc | +0.051 |
lder | +0.048 |
Neg logit contributions | |
steep | -0.047 |
forget | -0.044 |
also | -0.044 |
ill | -0.041 |
Josh | -0.041 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
steep | +0.014 |
Josh | +0.013 |
forget | +0.013 |
Josh | +0.013 |
also | +0.013 |
Neg logit contributions | |
cient | -0.018 |
itt | -0.017 |
clay | -0.017 |
cuc | -0.017 |
lear | -0.015 |
Token | my |
Token ID | 1820 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
cient | +0.021 |
clay | +0.021 |
itt | +0.021 |
d | +0.020 |
lder | +0.018 |
Neg logit contributions | |
steep | -0.018 |
Sof | -0.017 |
Josh | -0.017 |
Dan | -0.016 |
Noah | -0.016 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
steep | +0.031 |
Josh | +0.031 |
forget | +0.030 |
Josh | +0.029 |
Sof | +0.028 |
Neg logit contributions | |
cient | -0.038 |
clay | -0.037 |
itt | -0.037 |
cuc | -0.035 |
lear | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
also | +0.024 |
forget | +0.023 |
steep | +0.023 |
Josh | +0.023 |
Josh | +0.023 |
Neg logit contributions | |
cient | -0.034 |
itt | -0.032 |
cuc | -0.030 |
clay | -0.030 |
lder | -0.029 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
clay | +0.066 |
cient | +0.064 |
itt | +0.063 |
cuc | +0.061 |
lear | +0.058 |
Neg logit contributions | |
Josh | -0.058 |
steep | -0.058 |
forget | -0.056 |
Josh | -0.054 |
also | -0.053 |
Token | ement |
Token ID | 972 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Josh | +0.338 |
Josh | +0.326 |
steep | +0.319 |
also | +0.316 |
Dan | +0.315 |
Neg logit contributions | |
cient | -0.430 |
itt | -0.394 |
clay | -0.390 |
cuc | -0.389 |
lear | -0.366 |
Token | as |
Token ID | 355 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
cient | +0.059 |
itt | +0.056 |
clay | +0.056 |
cuc | +0.053 |
lear | +0.048 |
Neg logit contributions | |
steep | -0.058 |
Josh | -0.057 |
forget | -0.057 |
also | -0.055 |
Josh | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
clay | +0.032 |
cient | +0.032 |
itt | +0.031 |
cuc | +0.030 |
lear | +0.028 |
Neg logit contributions | |
steep | -0.026 |
Josh | -0.025 |
forget | -0.025 |
Josh | -0.023 |
also | -0.023 |
Token | black |
Token ID | 2042 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
steep | +0.011 |
Josh | +0.011 |
forget | +0.010 |
also | +0.010 |
Josh | +0.010 |
Neg logit contributions | |
cient | -0.010 |
clay | -0.010 |
itt | -0.010 |
cuc | -0.009 |
lear | -0.008 |
Token | board |
Token ID | 3526 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
cient | +0.031 |
itt | +0.026 |
clay | +0.026 |
cuc | +0.025 |
lder | +0.024 |
Neg logit contributions | |
Dan | -0.038 |
Josh | -0.037 |
ill | -0.037 |
Josh | -0.037 |
steep | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
steep | +0.023 |
forget | +0.023 |
Josh | +0.021 |
existed | +0.021 |
Sof | +0.021 |
Neg logit contributions | |
itt | -0.027 |
cient | -0.026 |
clay | -0.026 |
cuc | -0.024 |
d | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
steep | +0.016 |
Josh | +0.016 |
forget | +0.015 |
Josh | +0.014 |
also | +0.014 |
Neg logit contributions | |
cient | -0.032 |
itt | -0.031 |
clay | -0.031 |
cuc | -0.030 |
lear | -0.028 |
Token | boy |
Token ID | 2933 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
also | +0.001 |
forget | +0.000 |
steep | +0.000 |
Josh | +0.000 |
Josh | +0.000 |
Neg logit contributions | |
cient | -0.001 |
itt | -0.001 |
sc | -0.001 |
ocol | -0.001 |
cuc | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
steep | +0.041 |
Josh | +0.040 |
forget | +0.040 |
Josh | +0.038 |
also | +0.037 |
Neg logit contributions | |
cient | -0.049 |
itt | -0.047 |
clay | -0.047 |
cuc | -0.045 |
lear | -0.042 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
clay | +0.069 |
cient | +0.069 |
cuc | +0.065 |
itt | +0.063 |
lear | +0.060 |
Neg logit contributions | |
Josh | -0.076 |
steep | -0.072 |
forget | -0.072 |
Josh | -0.069 |
annie | -0.067 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
cient | +0.076 |
itt | +0.072 |
clay | +0.070 |
cuc | +0.067 |
ware | +0.063 |
Neg logit contributions | |
Josh | -0.055 |
forget | -0.054 |
steep | -0.054 |
also | -0.052 |
Josh | -0.052 |
Token | ement |
Token ID | 972 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Josh | +0.346 |
steep | +0.331 |
Josh | +0.329 |
also | +0.323 |
Dan | +0.319 |
Neg logit contributions | |
cient | -0.421 |
itt | -0.389 |
clay | -0.388 |
cuc | -0.380 |
lear | -0.354 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
cient | +0.062 |
itt | +0.059 |
clay | +0.058 |
cuc | +0.056 |
sc | +0.051 |
Neg logit contributions | |
steep | -0.052 |
forget | -0.051 |
Josh | -0.051 |
also | -0.050 |
Josh | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
steep | +0.001 |
Josh | +0.001 |
forget | +0.001 |
also | +0.001 |
Josh | +0.001 |
Neg logit contributions | |
cient | -0.001 |
itt | -0.001 |
clay | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | thanked |
Token ID | 26280 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
steep | +0.018 |
Josh | +0.018 |
forget | +0.018 |
Josh | +0.017 |
Sof | +0.017 |
Neg logit contributions | |
cient | -0.020 |
clay | -0.020 |
itt | -0.019 |
cuc | -0.019 |
lear | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
cient | +0.051 |
itt | +0.049 |
clay | +0.048 |
cuc | +0.046 |
sc | +0.044 |
Neg logit contributions | |
Josh | -0.029 |
Josh | -0.028 |
forget | -0.028 |
also | -0.028 |
Dan | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
cient | +0.061 |
itt | +0.060 |
clay | +0.058 |
cuc | +0.055 |
lear | +0.050 |
Neg logit contributions | |
steep | -0.059 |
Josh | -0.058 |
forget | -0.057 |
Josh | -0.057 |
also | -0.056 |
Token | Tiger |
Token ID | 17030 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
steep | +0.013 |
forget | +0.013 |
Josh | +0.013 |
also | +0.012 |
ill | +0.012 |
Neg logit contributions | |
cient | -0.014 |
clay | -0.013 |
itt | -0.013 |
cuc | -0.012 |
lear | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
steep | +0.054 |
Josh | +0.053 |
forget | +0.053 |
Josh | +0.050 |
also | +0.049 |
Neg logit contributions | |
cient | -0.065 |
itt | -0.061 |
clay | -0.061 |
cuc | -0.058 |
lear | -0.054 |
Token | around |
Token ID | 1088 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
cient | +0.035 |
clay | +0.034 |
cuc | +0.031 |
itt | +0.029 |
soldiers | +0.027 |
Neg logit contributions | |
Josh | -0.050 |
forget | -0.046 |
Josh | -0.045 |
steep | -0.044 |
Dan | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
cient | +0.046 |
itt | +0.045 |
clay | +0.043 |
cuc | +0.042 |
lder | +0.039 |
Neg logit contributions | |
steep | -0.033 |
Josh | -0.032 |
forget | -0.031 |
also | -0.031 |
Josh | -0.030 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
clay | +0.068 |
cuc | +0.062 |
cient | +0.061 |
lear | +0.059 |
itt | +0.059 |
Neg logit contributions | |
steep | -0.049 |
Josh | -0.048 |
ibi | -0.047 |
annie | -0.047 |
forget | -0.047 |
Token | ement |
Token ID | 972 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Josh | +0.377 |
steep | +0.376 |
forget | +0.364 |
Josh | +0.359 |
also | +0.357 |
Neg logit contributions | |
cient | -0.381 |
itt | -0.360 |
clay | -0.359 |
cuc | -0.344 |
lear | -0.316 |
Token | and |
Token ID | 290 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
cient | +0.056 |
clay | +0.054 |
itt | +0.053 |
cuc | +0.050 |
lear | +0.047 |
Neg logit contributions | |
Josh | -0.064 |
steep | -0.064 |
forget | -0.063 |
also | -0.060 |
Josh | -0.059 |
Token | he |
Token ID | 339 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Josh | +0.024 |
steep | +0.023 |
ill | +0.022 |
forget | +0.022 |
ibi | +0.022 |
Neg logit contributions | |
cient | -0.023 |
clay | -0.020 |
cuc | -0.020 |
ted | -0.020 |
itt | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
steep | +0.043 |
Josh | +0.041 |
ibi | +0.039 |
forget | +0.039 |
ill | +0.039 |
Neg logit contributions | |
cient | -0.037 |
cuc | -0.033 |
itt | -0.032 |
clay | -0.031 |
d | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
clay | +0.084 |
cient | +0.083 |
itt | +0.081 |
cuc | +0.075 |
soldiers | +0.071 |
Neg logit contributions | |
Josh | -0.118 |
forget | -0.118 |
ibi | -0.115 |
ill | -0.113 |
steep | -0.111 |
Token | was |
Token ID | 373 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
steep | +0.037 |
Josh | +0.035 |
forget | +0.035 |
Josh | +0.033 |
Sof | +0.033 |
Neg logit contributions | |
cient | -0.042 |
itt | -0.039 |
clay | -0.039 |
cuc | -0.037 |
lear | -0.035 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
clay | +0.022 |
cient | +0.020 |
te | +0.018 |
itt | +0.018 |
d | +0.018 |
Neg logit contributions | |
Josh | -0.028 |
steep | -0.028 |
ibi | -0.027 |
forget | -0.027 |
existed | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
steep | +0.093 |
Josh | +0.093 |
also | +0.091 |
forget | +0.090 |
Josh | +0.089 |
Neg logit contributions | |
cient | -0.116 |
itt | -0.111 |
clay | -0.108 |
cuc | -0.104 |
lear | -0.097 |
Token | wonder |
Token ID | 4240 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
clay | +0.052 |
cient | +0.050 |
itt | +0.048 |
cuc | +0.047 |
lear | +0.043 |
Neg logit contributions | |
Josh | -0.048 |
steep | -0.047 |
forget | -0.045 |
Josh | -0.044 |
ill | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Josh | +0.065 |
forget | +0.062 |
steep | +0.061 |
Phill | +0.058 |
ibi | +0.058 |
Neg logit contributions | |
cient | -0.053 |
clay | -0.053 |
cuc | -0.049 |
itt | -0.048 |
lear | -0.044 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
Josh | +0.019 |
steep | +0.018 |
ill | +0.018 |
Phill | +0.017 |
annie | +0.017 |
Neg logit contributions | |
cient | -0.020 |
clay | -0.020 |
cuc | -0.019 |
itt | -0.017 |
lear | -0.017 |
Token | ement |
Token ID | 972 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Josh | +0.364 |
steep | +0.363 |
forget | +0.348 |
Josh | +0.348 |
also | +0.348 |
Neg logit contributions | |
cient | -0.393 |
itt | -0.372 |
clay | -0.370 |
cuc | -0.357 |
lear | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
cient | +0.051 |
clay | +0.047 |
itt | +0.047 |
cuc | +0.044 |
lear | +0.040 |
Neg logit contributions | |
Josh | -0.069 |
steep | -0.068 |
forget | -0.068 |
also | -0.064 |
Josh | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
forget | +0.008 |
steep | +0.008 |
Josh | +0.008 |
ill | +0.008 |
also | +0.008 |
Neg logit contributions | |
cient | -0.011 |
clay | -0.010 |
itt | -0.010 |
cuc | -0.010 |
lear | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
steep | +0.021 |
Josh | +0.021 |
ill | +0.020 |
forget | +0.020 |
Josh | +0.020 |
Neg logit contributions | |
cient | -0.021 |
clay | -0.019 |
itt | -0.019 |
cuc | -0.019 |
lear | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
clay | +0.027 |
cient | +0.027 |
cuc | +0.024 |
itt | +0.024 |
te | +0.023 |
Neg logit contributions | |
steep | -0.026 |
Josh | -0.026 |
forget | -0.026 |
ibi | -0.025 |
ill | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
forget | +0.008 |
Josh | +0.008 |
steep | +0.008 |
Sof | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
clay | -0.007 |
cient | -0.007 |
itt | -0.006 |
cuc | -0.006 |
lear | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
steep | +0.022 |
Josh | +0.021 |
forget | +0.021 |
also | +0.020 |
Josh | +0.020 |
Neg logit contributions | |
cient | -0.028 |
itt | -0.027 |
clay | -0.027 |
cuc | -0.025 |
lear | -0.024 |
Token | always |
Token ID | 1464 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
cient | +0.075 |
itt | +0.073 |
clay | +0.071 |
cuc | +0.068 |
ware | +0.063 |
Neg logit contributions | |
forget | -0.060 |
steep | -0.060 |
also | -0.059 |
Josh | -0.058 |
Josh | -0.056 |
Token | stare |
Token ID | 24170 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
steep | +0.003 |
Josh | +0.003 |
forget | +0.003 |
Josh | +0.003 |
Sof | +0.003 |
Neg logit contributions | |
cient | -0.004 |
clay | -0.004 |
itt | -0.004 |
cuc | -0.004 |
lear | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
steep | +0.020 |
forget | +0.019 |
Josh | +0.019 |
also | +0.019 |
Josh | +0.019 |
Neg logit contributions | |
cient | -0.023 |
itt | -0.023 |
clay | -0.022 |
cuc | -0.021 |
lear | -0.020 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
cient | +0.067 |
clay | +0.067 |
itt | +0.064 |
cuc | +0.063 |
lear | +0.057 |
Neg logit contributions | |
steep | -0.057 |
Josh | -0.057 |
forget | -0.056 |
also | -0.053 |
Josh | -0.053 |
Token | ement |
Token ID | 972 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Josh | +0.302 |
Josh | +0.293 |
ill | +0.285 |
steep | +0.285 |
Dan | +0.283 |
Neg logit contributions | |
cient | -0.445 |
itt | -0.420 |
clay | -0.408 |
cuc | -0.407 |
sc | -0.392 |
Token | at |
Token ID | 379 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
cient | +0.062 |
itt | +0.060 |
clay | +0.059 |
cuc | +0.057 |
lear | +0.052 |
Neg logit contributions | |
steep | -0.055 |
forget | -0.054 |
Josh | -0.054 |
Josh | -0.052 |
also | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
cient | +0.008 |
itt | +0.007 |
clay | +0.007 |
cuc | +0.007 |
lear | +0.006 |
Neg logit contributions | |
steep | -0.006 |
Josh | -0.006 |
forget | -0.006 |
also | -0.006 |
Josh | -0.006 |
Token | l |
Token ID | 300 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
steep | +0.022 |
forget | +0.021 |
also | +0.020 |
Josh | +0.020 |
Josh | +0.019 |
Neg logit contributions | |
itt | -0.026 |
cient | -0.026 |
clay | -0.024 |
cuc | -0.023 |
lear | -0.022 |
Token | ily |
Token ID | 813 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
cient | +0.029 |
clay | +0.028 |
cuc | +0.027 |
itt | +0.026 |
lear | +0.025 |
Neg logit contributions | |
Josh | -0.024 |
steep | -0.023 |
also | -0.023 |
Sof | -0.022 |
ill | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
steep | +0.000 |
Josh | +0.000 |
forget | +0.000 |
Sof | +0.000 |
Josh | +0.000 |
Neg logit contributions | |
cient | -0.000 |
itt | -0.000 |
clay | -0.000 |
cuc | -0.000 |
lear | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
steep | +0.019 |
Josh | +0.019 |
forget | +0.018 |
Josh | +0.018 |
also | +0.018 |
Neg logit contributions | |
cient | -0.019 |
clay | -0.019 |
itt | -0.018 |
cuc | -0.018 |
lear | -0.016 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
steep | +0.005 |
forget | +0.005 |
Josh | +0.005 |
also | +0.005 |
Josh | +0.005 |
Neg logit contributions | |
cient | -0.009 |
itt | -0.009 |
clay | -0.009 |
cuc | -0.009 |
sc | -0.008 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
steep | +0.060 |
Josh | +0.059 |
forget | +0.056 |
Sof | +0.056 |
Josh | +0.055 |
Neg logit contributions | |
cient | -0.056 |
itt | -0.053 |
clay | -0.050 |
lear | -0.047 |
cuc | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Josh | +0.022 |
also | +0.021 |
steep | +0.020 |
forget | +0.020 |
Dan | +0.020 |
Neg logit contributions | |
itt | -0.038 |
cient | -0.038 |
cuc | -0.035 |
P | -0.034 |
lder | -0.034 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
clay | +0.085 |
cient | +0.083 |
itt | +0.081 |
cuc | +0.079 |
lear | +0.079 |
Neg logit contributions | |
steep | -0.038 |
Josh | -0.038 |
forget | -0.036 |
annie | -0.035 |
existed | -0.034 |
Token | ement |
Token ID | 972 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Josh | +0.346 |
steep | +0.336 |
Josh | +0.331 |
also | +0.325 |
forget | +0.320 |
Neg logit contributions | |
cient | -0.416 |
itt | -0.389 |
clay | -0.384 |
cuc | -0.381 |
lear | -0.353 |
Token | , |
Token ID | 11 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
cient | +0.061 |
itt | +0.058 |
clay | +0.058 |
cuc | +0.055 |
lear | +0.050 |
Neg logit contributions | |
steep | -0.063 |
Josh | -0.062 |
forget | -0.062 |
also | -0.060 |
Josh | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
cient | +0.005 |
clay | +0.005 |
cuc | +0.005 |
itt | +0.005 |
lear | +0.004 |
Neg logit contributions | |
Josh | -0.005 |
steep | -0.005 |
forget | -0.004 |
annie | -0.004 |
existed | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
steep | +0.017 |
Josh | +0.017 |
forget | +0.016 |
annie | +0.016 |
ill | +0.016 |
Neg logit contributions | |
cient | -0.019 |
clay | -0.018 |
itt | -0.018 |
cuc | -0.017 |
lear | -0.016 |
Token | knight |
Token ID | 22062 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
steep | +0.018 |
forget | +0.018 |
Josh | +0.018 |
also | +0.018 |
Josh | +0.017 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.016 |
clay | -0.015 |
cuc | -0.015 |
sc | -0.014 |
Token | watched |
Token ID | 7342 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.007 |
Josh | +0.007 |
Sof | +0.007 |
Neg logit contributions | |
cient | -0.009 |
itt | -0.009 |
clay | -0.009 |
cuc | -0.008 |
lear | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
steep | +0.026 |
forget | +0.025 |
Josh | +0.025 |
Josh | +0.025 |
also | +0.025 |
Neg logit contributions | |
cient | -0.037 |
itt | -0.036 |
clay | -0.034 |
cuc | -0.034 |
lder | -0.032 |
Token | k |
Token ID | 479 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
steep | +0.022 |
forget | +0.022 |
Josh | +0.021 |
also | +0.021 |
Josh | +0.020 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.016 |
clay | -0.015 |
cuc | -0.015 |
ware | -0.013 |
Token | ite |
Token ID | 578 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
cient | +0.013 |
cuc | +0.013 |
clay | +0.012 |
itt | +0.012 |
ware | +0.011 |
Neg logit contributions | |
steep | -0.005 |
forget | -0.005 |
Josh | -0.005 |
also | -0.005 |
Sof | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Josh | +0.026 |
steep | +0.025 |
Josh | +0.024 |
forget | +0.024 |
Dan | +0.023 |
Neg logit contributions | |
cient | -0.024 |
clay | -0.024 |
itt | -0.022 |
cuc | -0.022 |
lear | -0.020 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
clay | +0.073 |
cient | +0.065 |
cuc | +0.063 |
itt | +0.063 |
lear | +0.063 |
Neg logit contributions | |
steep | -0.050 |
Josh | -0.050 |
annie | -0.047 |
forget | -0.047 |
existed | -0.046 |
Token | ement |
Token ID | 972 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Josh | +0.356 |
steep | +0.353 |
Josh | +0.339 |
forget | +0.338 |
also | +0.337 |
Neg logit contributions | |
cient | -0.402 |
itt | -0.376 |
clay | -0.373 |
cuc | -0.366 |
lear | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
cient | +0.056 |
clay | +0.054 |
itt | +0.053 |
cuc | +0.049 |
lear | +0.046 |
Neg logit contributions | |
Josh | -0.070 |
steep | -0.069 |
forget | -0.067 |
Josh | -0.065 |
also | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
clay | +0.005 |
cient | +0.005 |
cuc | +0.005 |
lear | +0.004 |
itt | +0.004 |
Neg logit contributions | |
Josh | -0.005 |
steep | -0.005 |
annie | -0.004 |
forget | -0.004 |
Phill | -0.004 |
Token | Little |
Token ID | 7703 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
steep | +0.016 |
Josh | +0.016 |
Phill | +0.015 |
forget | +0.015 |
ibi | +0.015 |
Neg logit contributions | |
cient | -0.014 |
clay | -0.014 |
cuc | -0.013 |
itt | -0.013 |
ted | -0.013 |
Token | Joe |
Token ID | 5689 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
steep | +0.061 |
forget | +0.059 |
Josh | +0.058 |
also | +0.055 |
annie | +0.051 |
Neg logit contributions | |
cient | -0.133 |
clay | -0.128 |
itt | -0.125 |
cuc | -0.121 |
lder | -0.116 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
cient | +0.042 |
clay | +0.041 |
itt | +0.039 |
cuc | +0.039 |
lear | +0.036 |
Neg logit contributions | |
Josh | -0.036 |
steep | -0.035 |
forget | -0.034 |
Josh | -0.033 |
ill | -0.032 |
Token | hard |
Token ID | 1327 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
cient | +0.103 |
itt | +0.098 |
clay | +0.096 |
cuc | +0.092 |
lear | +0.084 |
Neg logit contributions | |
steep | -0.109 |
Josh | -0.105 |
forget | -0.104 |
also | -0.102 |
Josh | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
cient | +0.121 |
itt | +0.114 |
clay | +0.111 |
cuc | +0.107 |
lder | +0.100 |
Neg logit contributions | |
steep | -0.100 |
forget | -0.095 |
Josh | -0.093 |
also | -0.092 |
Josh | -0.090 |
Token | The |
Token ID | 383 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
steep | +0.001 |
Josh | +0.001 |
forget | +0.001 |
also | +0.001 |
Josh | +0.001 |
Neg logit contributions | |
cient | -0.001 |
itt | -0.001 |
clay | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
cient | +0.100 |
itt | +0.094 |
clay | +0.087 |
cuc | +0.086 |
lder | +0.083 |
Neg logit contributions | |
steep | -0.098 |
forget | -0.097 |
also | -0.096 |
Josh | -0.090 |
Josh | -0.086 |
Token | ho |
Token ID | 8873 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
cient | +0.039 |
itt | +0.038 |
clay | +0.038 |
cuc | +0.036 |
lear | +0.034 |
Neg logit contributions | |
steep | -0.030 |
Josh | -0.030 |
forget | -0.029 |
also | -0.029 |
Josh | -0.028 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
cient | +0.452 |
clay | +0.434 |
itt | +0.426 |
cuc | +0.407 |
lear | +0.368 |
Neg logit contributions | |
steep | -0.508 |
Josh | -0.503 |
forget | -0.499 |
also | -0.484 |
Josh | -0.479 |
Token | was |
Token ID | 373 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
cient | +0.102 |
itt | +0.099 |
clay | +0.098 |
cuc | +0.094 |
lear | +0.087 |
Neg logit contributions | |
steep | -0.075 |
forget | -0.074 |
Josh | -0.074 |
also | -0.071 |
Josh | -0.070 |
Token | spoiled |
Token ID | 34781 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
clay | +0.033 |
cient | +0.029 |
cuc | +0.029 |
itt | +0.028 |
dough | +0.026 |
Neg logit contributions | |
Josh | -0.032 |
forget | -0.030 |
Josh | -0.029 |
annie | -0.029 |
Sof | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +6.36e-03 |
Pos logit contributions | |
cient | +0.043 |
clay | +0.042 |
itt | +0.041 |
cuc | +0.039 |
lear | +0.036 |
Neg logit contributions | |
Josh | -0.037 |
steep | -0.037 |
forget | -0.036 |
Josh | -0.034 |
also | -0.034 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
steep | +0.000 |
Josh | +0.000 |
forget | +0.000 |
also | +0.000 |
Josh | +0.000 |
Neg logit contributions | |
cient | -0.000 |
itt | -0.000 |
clay | -0.000 |
cuc | -0.000 |
lear | -0.000 |
Token | busy |
Token ID | 8179 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
cient | +0.034 |
itt | +0.032 |
clay | +0.032 |
cuc | +0.031 |
lear | +0.028 |
Neg logit contributions | |
steep | -0.029 |
forget | -0.028 |
Josh | -0.028 |
also | -0.028 |
Josh | -0.027 |
Token | working |
Token ID | 1762 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
cient | +0.024 |
itt | +0.023 |
clay | +0.022 |
cuc | +0.021 |
lear | +0.020 |
Neg logit contributions | |
steep | -0.023 |
forget | -0.022 |
Josh | -0.022 |
also | -0.022 |
Josh | -0.021 |
Token | when |
Token ID | 618 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
cient | +0.096 |
itt | +0.089 |
clay | +0.084 |
cuc | +0.084 |
lder | +0.080 |
Neg logit contributions | |
steep | -0.069 |
also | -0.063 |
Josh | -0.060 |
forget | -0.060 |
Josh | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
cient | +0.048 |
clay | +0.047 |
itt | +0.046 |
cuc | +0.044 |
lear | +0.041 |
Neg logit contributions | |
steep | -0.038 |
Josh | -0.038 |
forget | -0.038 |
also | -0.035 |
Josh | -0.035 |
Token | grass |
Token ID | 8701 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
cient | +0.000 |
itt | +0.000 |
clay | +0.000 |
cuc | +0.000 |
ware | +0.000 |
Neg logit contributions | |
steep | -0.000 |
forget | -0.000 |
also | -0.000 |
Josh | -0.000 |
Josh | -0.000 |
Token | ho |
Token ID | 8873 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
cient | +0.023 |
itt | +0.023 |
clay | +0.022 |
cuc | +0.021 |
lear | +0.020 |
Neg logit contributions | |
steep | -0.024 |
Josh | -0.023 |
forget | -0.023 |
also | -0.022 |
Josh | -0.022 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
cient | +0.525 |
clay | +0.518 |
itt | +0.505 |
cuc | +0.489 |
lear | +0.454 |
Neg logit contributions | |
steep | -0.351 |
forget | -0.348 |
Josh | -0.347 |
also | -0.336 |
Josh | -0.326 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
cient | +0.068 |
clay | +0.065 |
itt | +0.065 |
cuc | +0.062 |
lear | +0.057 |
Neg logit contributions | |
steep | -0.057 |
Josh | -0.057 |
forget | -0.055 |
Josh | -0.053 |
also | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.017 |
cuc | +0.017 |
lear | +0.017 |
Neg logit contributions | |
steep | -0.013 |
Josh | -0.013 |
Josh | -0.012 |
Dan | -0.012 |
also | -0.012 |
Token | switch |
Token ID | 5078 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
cient | +0.023 |
clay | +0.022 |
itt | +0.022 |
cuc | +0.021 |
lear | +0.019 |
Neg logit contributions | |
Josh | -0.024 |
steep | -0.024 |
forget | -0.023 |
Josh | -0.023 |
also | -0.023 |
Token | next |
Token ID | 1306 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
steep | +0.069 |
Josh | +0.067 |
forget | +0.067 |
also | +0.065 |
Josh | +0.064 |
Neg logit contributions | |
cient | -0.070 |
itt | -0.067 |
clay | -0.066 |
cuc | -0.063 |
lear | -0.058 |
Token | It |
Token ID | 1026 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
cient | +0.043 |
itt | +0.041 |
clay | +0.040 |
cuc | +0.038 |
lear | +0.034 |
Neg logit contributions | |
Josh | -0.050 |
steep | -0.049 |
forget | -0.048 |
also | -0.047 |
Josh | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
itt | +0.023 |
cient | +0.022 |
clay | +0.021 |
cuc | +0.021 |
lear | +0.020 |
Neg logit contributions | |
also | -0.015 |
forget | -0.014 |
steep | -0.014 |
Josh | -0.014 |
Josh | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
clay | +0.010 |
cuc | +0.008 |
cient | +0.008 |
wine | +0.008 |
war | +0.008 |
Neg logit contributions | |
Josh | -0.012 |
ill | -0.011 |
forget | -0.011 |
annie | -0.011 |
steep | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Josh | +0.156 |
steep | +0.152 |
forget | +0.149 |
Josh | +0.143 |
also | +0.141 |
Neg logit contributions | |
cient | -0.142 |
clay | -0.141 |
itt | -0.131 |
cuc | -0.129 |
printer | -0.117 |
Token | grass |
Token ID | 8701 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
cient | +0.026 |
itt | +0.026 |
ted | +0.022 |
clay | +0.022 |
led | +0.022 |
Neg logit contributions | |
forget | -0.026 |
steep | -0.026 |
also | -0.025 |
Josh | -0.024 |
Dan | -0.024 |
Token | ho |
Token ID | 8873 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
cient | +0.028 |
itt | +0.027 |
clay | +0.027 |
cuc | +0.025 |
lear | +0.023 |
Neg logit contributions | |
steep | -0.028 |
forget | -0.028 |
Josh | -0.027 |
also | -0.027 |
Josh | -0.026 |
Token | pper |
Token ID | 2848 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
clay | +0.603 |
cient | +0.601 |
itt | +0.579 |
cuc | +0.576 |
lear | +0.542 |
Neg logit contributions | |
forget | -0.246 |
steep | -0.236 |
Josh | -0.230 |
also | -0.226 |
Josh | -0.216 |
Token | or |
Token ID | 393 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
cient | +0.046 |
itt | +0.044 |
clay | +0.044 |
cuc | +0.041 |
lear | +0.038 |
Neg logit contributions | |
steep | -0.045 |
forget | -0.044 |
Josh | -0.044 |
also | -0.042 |
Josh | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
forget | +0.071 |
steep | +0.071 |
also | +0.069 |
Josh | +0.068 |
Josh | +0.067 |
Neg logit contributions | |
cient | -0.083 |
itt | -0.080 |
clay | -0.075 |
cuc | -0.072 |
lder | -0.070 |
Token | cricket |
Token ID | 18836 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
cient | +0.025 |
itt | +0.024 |
clay | +0.021 |
ted | +0.020 |
cuc | +0.020 |
Neg logit contributions | |
steep | -0.027 |
forget | -0.027 |
also | -0.026 |
Josh | -0.025 |
Dan | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
cient | +0.037 |
itt | +0.036 |
clay | +0.035 |
cuc | +0.033 |
lear | +0.031 |
Neg logit contributions | |
steep | -0.030 |
forget | -0.030 |
also | -0.029 |
Josh | -0.028 |
Josh | -0.028 |
Token | ried |
Token ID | 2228 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
cient | +0.035 |
clay | +0.034 |
itt | +0.034 |
cuc | +0.033 |
lear | +0.030 |
Neg logit contributions | |
steep | -0.035 |
Josh | -0.034 |
forget | -0.034 |
also | -0.033 |
Josh | -0.033 |
Token | ly |
Token ID | 306 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
cient | +0.014 |
itt | +0.014 |
clay | +0.013 |
cuc | +0.013 |
lear | +0.012 |
Neg logit contributions | |
steep | -0.015 |
Josh | -0.015 |
forget | -0.015 |
Josh | -0.015 |
also | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
cient | +0.146 |
clay | +0.141 |
itt | +0.141 |
cuc | +0.135 |
lear | +0.124 |
Neg logit contributions | |
steep | -0.114 |
Josh | -0.112 |
forget | -0.111 |
Josh | -0.108 |
also | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
cient | +0.011 |
clay | +0.010 |
itt | +0.010 |
cuc | +0.010 |
lear | +0.009 |
Neg logit contributions | |
Josh | -0.010 |
steep | -0.009 |
forget | -0.009 |
annie | -0.009 |
ill | -0.009 |
Token | grass |
Token ID | 8701 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
steep | +0.002 |
forget | +0.002 |
Josh | +0.002 |
also | +0.002 |
Josh | +0.002 |
Neg logit contributions | |
cient | -0.002 |
itt | -0.002 |
clay | -0.002 |
cuc | -0.002 |
ware | -0.002 |
Token | ho |
Token ID | 8873 |
Feature activation | -8.02e+00 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.015 |
Neg logit contributions | |
steep | -0.022 |
forget | -0.022 |
Josh | -0.022 |
also | -0.021 |
Josh | -0.021 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
cient | +0.574 |
clay | +0.571 |
itt | +0.551 |
cuc | +0.541 |
printer | +0.507 |
Neg logit contributions | |
steep | -0.274 |
forget | -0.271 |
Josh | -0.271 |
also | -0.260 |
Josh | -0.248 |
Token | rushed |
Token ID | 13999 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
cient | +0.060 |
clay | +0.057 |
itt | +0.057 |
cuc | +0.055 |
lear | +0.051 |
Neg logit contributions | |
steep | -0.046 |
Josh | -0.046 |
forget | -0.045 |
Josh | -0.043 |
also | -0.043 |
Token | over |
Token ID | 625 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.007 |
Josh | +0.007 |
also | +0.007 |
forget | +0.007 |
Neg logit contributions | |
cient | -0.010 |
itt | -0.009 |
clay | -0.009 |
cuc | -0.009 |
lder | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
cient | +0.009 |
itt | +0.008 |
clay | +0.008 |
cuc | +0.008 |
lder | +0.007 |
Neg logit contributions | |
steep | -0.008 |
Josh | -0.008 |
forget | -0.008 |
Josh | -0.008 |
also | -0.008 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
steep | +0.013 |
Josh | +0.013 |
forget | +0.013 |
Josh | +0.012 |
also | +0.012 |
Neg logit contributions | |
cient | -0.015 |
clay | -0.014 |
itt | -0.014 |
cuc | -0.014 |
lear | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
cient | +0.051 |
clay | +0.051 |
itt | +0.050 |
cuc | +0.047 |
lear | +0.043 |
Neg logit contributions | |
steep | -0.049 |
Josh | -0.049 |
forget | -0.049 |
Josh | -0.046 |
also | -0.045 |
Token | great |
Token ID | 1049 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
cient | +0.016 |
itt | +0.015 |
clay | +0.015 |
cuc | +0.014 |
lear | +0.013 |
Neg logit contributions | |
steep | -0.014 |
Josh | -0.014 |
forget | -0.014 |
also | -0.013 |
Josh | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
steep | +0.051 |
forget | +0.050 |
Josh | +0.047 |
also | +0.047 |
Josh | +0.045 |
Neg logit contributions | |
cient | -0.068 |
itt | -0.063 |
clay | -0.059 |
cuc | -0.057 |
ted | -0.056 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
steep | +0.026 |
forget | +0.026 |
Josh | +0.026 |
also | +0.025 |
Josh | +0.024 |
Neg logit contributions | |
cient | -0.037 |
itt | -0.036 |
clay | -0.036 |
cuc | -0.034 |
lear | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
cient | +0.202 |
itt | +0.193 |
clay | +0.191 |
cuc | +0.183 |
lear | +0.170 |
Neg logit contributions | |
steep | -0.151 |
Josh | -0.150 |
forget | -0.149 |
Josh | -0.143 |
also | -0.143 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
cient | +0.074 |
clay | +0.071 |
cuc | +0.067 |
soldiers | +0.065 |
ware | +0.063 |
Neg logit contributions | |
Josh | -0.071 |
Mary | -0.068 |
also | -0.068 |
Dan | -0.067 |
steep | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
cient | +0.446 |
clay | +0.431 |
itt | +0.424 |
cuc | +0.407 |
lear | +0.372 |
Neg logit contributions | |
steep | -0.399 |
Josh | -0.398 |
forget | -0.398 |
also | -0.381 |
Josh | -0.379 |
Token | they |
Token ID | 484 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
cient | +0.004 |
clay | +0.004 |
itt | +0.004 |
cuc | +0.004 |
lear | +0.003 |
Neg logit contributions | |
steep | -0.003 |
Josh | -0.003 |
forget | -0.003 |
Josh | -0.003 |
also | -0.003 |
Token | gained |
Token ID | 8618 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
cient | +0.050 |
itt | +0.048 |
clay | +0.048 |
cuc | +0.046 |
lear | +0.042 |
Neg logit contributions | |
steep | -0.046 |
forget | -0.045 |
Josh | -0.045 |
also | -0.044 |
Josh | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
steep | +0.017 |
forget | +0.016 |
Josh | +0.016 |
also | +0.016 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.020 |
itt | -0.019 |
clay | -0.018 |
cuc | -0.018 |
lear | -0.016 |
Token | avocado |
Token ID | 40377 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
forget | +0.016 |
steep | +0.016 |
also | +0.016 |
Josh | +0.014 |
ill | +0.014 |
Neg logit contributions | |
cient | -0.019 |
itt | -0.018 |
clay | -0.016 |
ted | -0.016 |
sc | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Josh | +0.087 |
forget | +0.082 |
steep | +0.082 |
Phill | +0.079 |
Dan | +0.078 |
Neg logit contributions | |
clay | -0.039 |
itt | -0.036 |
cient | -0.034 |
d | -0.032 |
printer | -0.031 |
Token | She |
Token ID | 1375 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
cient | +0.011 |
itt | +0.011 |
clay | +0.011 |
cuc | +0.010 |
printer | +0.009 |
Neg logit contributions | |
steep | -0.010 |
forget | -0.010 |
Josh | -0.009 |
also | -0.009 |
annie | -0.009 |
Token | used |
Token ID | 973 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
cient | +0.006 |
itt | +0.006 |
clay | +0.006 |
cuc | +0.005 |
printer | +0.005 |
Neg logit contributions | |
steep | -0.006 |
Josh | -0.006 |
forget | -0.005 |
Josh | -0.005 |
Sof | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
cient | +0.082 |
itt | +0.077 |
clay | +0.075 |
cuc | +0.073 |
lder | +0.069 |
Neg logit contributions | |
steep | -0.062 |
Josh | -0.060 |
forget | -0.059 |
also | -0.059 |
Josh | -0.058 |
Token | m |
Token ID | 285 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
cient | +0.027 |
itt | +0.025 |
clay | +0.024 |
cuc | +0.024 |
ted | +0.023 |
Neg logit contributions | |
steep | -0.022 |
forget | -0.022 |
also | -0.021 |
Josh | -0.021 |
Josh | -0.020 |
Token | itt |
Token ID | 715 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
steep | +0.019 |
Josh | +0.019 |
forget | +0.019 |
also | +0.018 |
Josh | +0.018 |
Neg logit contributions | |
cient | -0.013 |
clay | -0.012 |
itt | -0.012 |
cuc | -0.011 |
lear | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
cient | +0.460 |
clay | +0.423 |
itt | +0.409 |
cuc | +0.398 |
lder | +0.383 |
Neg logit contributions | |
steep | -0.384 |
forget | -0.380 |
Josh | -0.372 |
also | -0.372 |
Josh | -0.366 |
Token | take |
Token ID | 1011 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
cient | +0.022 |
itt | +0.021 |
clay | +0.021 |
cuc | +0.020 |
lear | +0.018 |
Neg logit contributions | |
steep | -0.021 |
Josh | -0.021 |
forget | -0.021 |
also | -0.020 |
Josh | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Josh | +0.025 |
Dan | +0.024 |
Mary | +0.024 |
Sof | +0.024 |
Matt | +0.022 |
Neg logit contributions | |
cient | -0.044 |
cuc | -0.039 |
itt | -0.038 |
lder | -0.038 |
clay | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
cient | +0.120 |
itt | +0.113 |
clay | +0.113 |
cuc | +0.108 |
lear | +0.100 |
Neg logit contributions | |
steep | -0.103 |
Josh | -0.102 |
forget | -0.101 |
also | -0.098 |
Josh | -0.098 |
Token | pan |
Token ID | 3425 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
cient | +0.001 |
itt | +0.000 |
cuc | +0.000 |
ted | +0.000 |
clay | +0.000 |
Neg logit contributions | |
forget | -0.001 |
also | -0.001 |
steep | -0.001 |
Josh | -0.000 |
Josh | -0.000 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
steep | +0.086 |
Josh | +0.086 |
forget | +0.084 |
Josh | +0.080 |
also | +0.080 |
Neg logit contributions | |
cient | -0.131 |
clay | -0.126 |
itt | -0.126 |
cuc | -0.120 |
lear | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
steep | +0.006 |
Josh | +0.005 |
forget | +0.005 |
also | +0.005 |
Josh | +0.005 |
Neg logit contributions | |
cient | -0.007 |
itt | -0.007 |
clay | -0.007 |
cuc | -0.007 |
lear | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
steep | +0.014 |
forget | +0.014 |
Josh | +0.013 |
also | +0.012 |
Josh | +0.012 |
Neg logit contributions | |
cient | -0.019 |
itt | -0.019 |
clay | -0.018 |
cuc | -0.017 |
lear | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
steep | +0.010 |
Josh | +0.010 |
forget | +0.010 |
also | +0.010 |
Josh | +0.009 |
Neg logit contributions | |
cient | -0.021 |
itt | -0.020 |
clay | -0.020 |
cuc | -0.019 |
lear | -0.018 |
Token | grass |
Token ID | 8701 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
cient | +0.008 |
itt | +0.008 |
clay | +0.008 |
cuc | +0.007 |
sc | +0.007 |
Neg logit contributions | |
steep | -0.008 |
forget | -0.008 |
also | -0.008 |
Josh | -0.008 |
Josh | -0.007 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
cient | +0.015 |
itt | +0.014 |
clay | +0.014 |
cuc | +0.013 |
lear | +0.012 |
Neg logit contributions | |
steep | -0.027 |
Josh | -0.027 |
forget | -0.026 |
also | -0.026 |
Josh | -0.026 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
cient | +0.520 |
itt | +0.501 |
clay | +0.501 |
cuc | +0.480 |
lear | +0.449 |
Neg logit contributions | |
steep | -0.314 |
Josh | -0.310 |
forget | -0.305 |
also | -0.290 |
Josh | -0.290 |
Token | said |
Token ID | 531 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
cient | +0.055 |
itt | +0.053 |
clay | +0.053 |
cuc | +0.050 |
lear | +0.046 |
Neg logit contributions | |
steep | -0.043 |
Josh | -0.042 |
forget | -0.041 |
Josh | -0.040 |
also | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
also | +0.004 |
steep | +0.004 |
Dan | +0.003 |
Josh | +0.003 |
Sof | +0.003 |
Neg logit contributions | |
cient | -0.006 |
itt | -0.006 |
clay | -0.006 |
cuc | -0.006 |
ands | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
itt | +0.011 |
cient | +0.011 |
clay | +0.011 |
ands | +0.010 |
tant | +0.010 |
Neg logit contributions | |
also | -0.007 |
Josh | -0.006 |
steep | -0.006 |
Dan | -0.006 |
Josh | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.016 |
Neg logit contributions | |
steep | -0.016 |
Josh | -0.016 |
forget | -0.016 |
Josh | -0.015 |
also | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
steep | +0.044 |
forget | +0.042 |
Josh | +0.042 |
also | +0.041 |
Josh | +0.040 |
Neg logit contributions | |
cient | -0.057 |
itt | -0.054 |
clay | -0.053 |
cuc | -0.052 |
lear | -0.048 |
Token | pointed |
Token ID | 6235 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
steep | +0.006 |
Josh | +0.006 |
forget | +0.006 |
Josh | +0.006 |
also | +0.006 |
Neg logit contributions | |
cient | -0.007 |
clay | -0.007 |
itt | -0.007 |
cuc | -0.006 |
lear | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Josh | +0.092 |
forget | +0.090 |
steep | +0.090 |
also | +0.084 |
annie | +0.084 |
Neg logit contributions | |
clay | -0.069 |
cient | -0.068 |
itt | -0.064 |
cuc | -0.063 |
lear | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
cient | +0.016 |
itt | +0.015 |
cuc | +0.014 |
clay | +0.014 |
lder | +0.014 |
Neg logit contributions | |
also | -0.008 |
steep | -0.008 |
Sof | -0.007 |
Josh | -0.007 |
Josh | -0.007 |
Token | grass |
Token ID | 8701 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
Josh | +0.002 |
steep | +0.002 |
forget | +0.002 |
Josh | +0.002 |
also | +0.002 |
Neg logit contributions | |
cient | -0.001 |
clay | -0.001 |
itt | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
cient | +0.038 |
itt | +0.036 |
clay | +0.035 |
cuc | +0.034 |
lear | +0.031 |
Neg logit contributions | |
steep | -0.040 |
Josh | -0.039 |
forget | -0.039 |
also | -0.038 |
Josh | -0.038 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
cient | +0.517 |
clay | +0.503 |
itt | +0.490 |
cuc | +0.479 |
lear | +0.447 |
Neg logit contributions | |
steep | -0.311 |
Josh | -0.311 |
forget | -0.307 |
also | -0.301 |
Josh | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
cient | +0.055 |
itt | +0.053 |
clay | +0.052 |
cuc | +0.049 |
lear | +0.045 |
Neg logit contributions | |
steep | -0.058 |
forget | -0.057 |
Josh | -0.056 |
also | -0.055 |
Josh | -0.054 |
Token | He |
Token ID | 679 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
cient | +0.023 |
itt | +0.022 |
clay | +0.021 |
cuc | +0.020 |
lder | +0.020 |
Neg logit contributions | |
steep | -0.012 |
Josh | -0.011 |
Dan | -0.011 |
Josh | -0.011 |
Sof | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
cient | +0.013 |
clay | +0.012 |
cuc | +0.012 |
itt | +0.012 |
te | +0.011 |
Neg logit contributions | |
steep | -0.011 |
Josh | -0.011 |
forget | -0.011 |
Josh | -0.010 |
adow | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
cient | +0.011 |
itt | +0.011 |
clay | +0.011 |
cuc | +0.010 |
sc | +0.010 |
Neg logit contributions | |
steep | -0.008 |
Sof | -0.008 |
Dan | -0.008 |
Josh | -0.008 |
also | -0.008 |
Token | we |
Token ID | 356 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Josh | +0.056 |
steep | +0.054 |
forget | +0.052 |
ill | +0.052 |
Josh | +0.051 |
Neg logit contributions | |
cient | -0.051 |
itt | -0.050 |
clay | -0.050 |
cuc | -0.045 |
lder | -0.042 |
Token | call |
Token ID | 869 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
itt | +0.036 |
cient | +0.036 |
clay | +0.036 |
cuc | +0.035 |
lear | +0.032 |
Neg logit contributions | |
also | -0.028 |
steep | -0.027 |
forget | -0.027 |
Josh | -0.024 |
existed | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
itt | +0.066 |
cient | +0.066 |
cuc | +0.064 |
clay | +0.063 |
ware | +0.059 |
Neg logit contributions | |
Josh | -0.047 |
steep | -0.046 |
forget | -0.046 |
Josh | -0.046 |
also | -0.045 |
Token | " |
Token ID | 366 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
steep | +0.025 |
forget | +0.024 |
Josh | +0.024 |
also | +0.024 |
Josh | +0.024 |
Neg logit contributions | |
itt | -0.031 |
cient | -0.031 |
clay | -0.030 |
cuc | -0.029 |
ware | -0.027 |
Token | e |
Token ID | 68 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
cient | +0.011 |
clay | +0.011 |
itt | +0.011 |
cuc | +0.011 |
printer | +0.009 |
Neg logit contributions | |
Josh | -0.012 |
steep | -0.012 |
forget | -0.012 |
also | -0.012 |
Josh | -0.011 |
Token | lder |
Token ID | 6499 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
itt | +0.204 |
clay | +0.175 |
cuc | +0.173 |
ware | +0.155 |
sc | +0.155 |
Neg logit contributions | |
Josh | -0.348 |
Josh | -0.340 |
forget | -0.335 |
Mary | -0.333 |
Dan | -0.332 |
Token | ly |
Token ID | 306 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
clay | +0.280 |
itt | +0.278 |
cient | +0.270 |
cuc | +0.240 |
ware | +0.213 |
Neg logit contributions | |
steep | -0.534 |
Josh | -0.528 |
Josh | -0.526 |
forget | -0.517 |
Dan | -0.515 |
Token | ". |
Token ID | 1911 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
itt | +0.139 |
clay | +0.137 |
cient | +0.131 |
cuc | +0.131 |
ware | +0.127 |
Neg logit contributions | |
forget | -0.113 |
Josh | -0.111 |
Mary | -0.111 |
Sof | -0.109 |
steep | -0.109 |
Token | One |
Token ID | 1881 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
steep | +0.022 |
Josh | +0.022 |
forget | +0.022 |
also | +0.021 |
Josh | +0.021 |
Neg logit contributions | |
cient | -0.027 |
itt | -0.026 |
clay | -0.025 |
cuc | -0.024 |
lear | -0.022 |
Token | day |
Token ID | 1110 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
cient | +0.006 |
itt | +0.005 |
clay | +0.005 |
cuc | +0.005 |
lear | +0.004 |
Neg logit contributions | |
steep | -0.007 |
forget | -0.007 |
Josh | -0.007 |
also | -0.007 |
Josh | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
cient | +0.174 |
itt | +0.161 |
clay | +0.157 |
cuc | +0.155 |
ands | +0.153 |
Neg logit contributions | |
Josh | -0.074 |
Dan | -0.073 |
Mary | -0.073 |
Sof | -0.070 |
steep | -0.066 |
Token | an |
Token ID | 281 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
cient | +0.037 |
clay | +0.035 |
itt | +0.035 |
cuc | +0.033 |
lear | +0.031 |
Neg logit contributions | |
steep | -0.036 |
Josh | -0.035 |
forget | -0.035 |
also | -0.034 |
Josh | -0.034 |
Token | ant |
Token ID | 1885 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
steep | +0.077 |
Josh | +0.077 |
forget | +0.076 |
Josh | +0.073 |
also | +0.072 |
Neg logit contributions | |
cient | -0.092 |
clay | -0.088 |
itt | -0.088 |
cuc | -0.084 |
lear | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
cient | +0.056 |
itt | +0.052 |
clay | +0.052 |
cuc | +0.049 |
lear | +0.044 |
Neg logit contributions | |
steep | -0.079 |
Josh | -0.078 |
forget | -0.077 |
also | -0.075 |
Josh | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
steep | +0.012 |
Josh | +0.012 |
forget | +0.012 |
Josh | +0.011 |
also | +0.011 |
Neg logit contributions | |
cient | -0.015 |
clay | -0.015 |
itt | -0.015 |
cuc | -0.014 |
lear | -0.013 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
cient | +0.025 |
itt | +0.023 |
clay | +0.022 |
ted | +0.022 |
ware | +0.021 |
Neg logit contributions | |
steep | -0.023 |
also | -0.023 |
forget | -0.022 |
Josh | -0.021 |
Dan | -0.020 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
cient | +0.030 |
itt | +0.028 |
cuc | +0.028 |
clay | +0.028 |
lear | +0.025 |
Neg logit contributions | |
steep | -0.034 |
also | -0.034 |
forget | -0.032 |
Sof | -0.032 |
Dan | -0.031 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
cient | +0.510 |
clay | +0.496 |
itt | +0.491 |
cuc | +0.475 |
lear | +0.442 |
Neg logit contributions | |
steep | -0.317 |
Josh | -0.314 |
forget | -0.310 |
also | -0.296 |
Josh | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
cient | +0.066 |
itt | +0.063 |
clay | +0.062 |
cuc | +0.061 |
tant | +0.058 |
Neg logit contributions | |
also | -0.055 |
steep | -0.052 |
forget | -0.050 |
Josh | -0.048 |
Sof | -0.048 |
Token | The |
Token ID | 383 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Josh | +0.001 |
forget | +0.001 |
steep | +0.001 |
annie | +0.001 |
Josh | +0.001 |
Neg logit contributions | |
cient | -0.001 |
clay | -0.001 |
itt | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | ant |
Token ID | 1885 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
cient | +0.092 |
clay | +0.091 |
itt | +0.085 |
cuc | +0.083 |
lear | +0.074 |
Neg logit contributions | |
Josh | -0.129 |
Josh | -0.123 |
forget | -0.122 |
steep | -0.121 |
ill | -0.120 |
Token | was |
Token ID | 373 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
cient | +0.062 |
clay | +0.060 |
itt | +0.060 |
cuc | +0.054 |
lder | +0.050 |
Neg logit contributions | |
Josh | -0.077 |
forget | -0.074 |
steep | -0.074 |
Josh | -0.074 |
ill | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
cient | +0.056 |
itt | +0.053 |
clay | +0.053 |
cuc | +0.051 |
lder | +0.047 |
Neg logit contributions | |
steep | -0.035 |
Josh | -0.034 |
forget | -0.034 |
Josh | -0.033 |
also | -0.032 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
steep | +0.016 |
Josh | +0.016 |
forget | +0.016 |
ill | +0.015 |
Sof | +0.015 |
Neg logit contributions | |
cient | -0.015 |
clay | -0.014 |
itt | -0.014 |
cuc | -0.014 |
ted | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
cient | +0.025 |
itt | +0.024 |
clay | +0.024 |
cuc | +0.023 |
lear | +0.021 |
Neg logit contributions | |
steep | -0.022 |
Josh | -0.022 |
forget | -0.021 |
also | -0.021 |
Josh | -0.021 |
Token | huge |
Token ID | 3236 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
cient | +0.021 |
clay | +0.020 |
itt | +0.020 |
cuc | +0.019 |
lear | +0.017 |
Neg logit contributions | |
Josh | -0.024 |
steep | -0.023 |
forget | -0.023 |
Josh | -0.022 |
also | -0.022 |
Token | grass |
Token ID | 8701 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
steep | +0.048 |
Josh | +0.048 |
forget | +0.047 |
also | +0.046 |
Josh | +0.046 |
Neg logit contributions | |
cient | -0.041 |
clay | -0.039 |
itt | -0.039 |
cuc | -0.036 |
lear | -0.033 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
cient | +0.019 |
clay | +0.018 |
itt | +0.018 |
cuc | +0.017 |
lear | +0.015 |
Neg logit contributions | |
Josh | -0.033 |
steep | -0.033 |
forget | -0.032 |
Josh | -0.031 |
also | -0.031 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cient | +0.564 |
clay | +0.558 |
itt | +0.538 |
cuc | +0.528 |
printer | +0.496 |
Neg logit contributions | |
steep | -0.256 |
Josh | -0.255 |
forget | -0.252 |
also | -0.243 |
Josh | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
cient | +0.051 |
clay | +0.051 |
itt | +0.049 |
cuc | +0.047 |
printer | +0.042 |
Neg logit contributions | |
Josh | -0.058 |
steep | -0.056 |
forget | -0.055 |
Josh | -0.054 |
annie | -0.052 |
Token | who |
Token ID | 508 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
clay | +0.009 |
cuc | +0.008 |
cient | +0.008 |
itt | +0.007 |
printer | +0.007 |
Neg logit contributions | |
Josh | -0.008 |
ill | -0.007 |
forget | -0.007 |
annie | -0.007 |
adow | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
cient | +0.044 |
itt | +0.043 |
clay | +0.042 |
cuc | +0.040 |
ted | +0.036 |
Neg logit contributions | |
forget | -0.040 |
steep | -0.040 |
Josh | -0.040 |
Josh | -0.037 |
ill | -0.037 |
Token | been |
Token ID | 587 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Josh | +0.057 |
steep | +0.056 |
forget | +0.056 |
Josh | +0.053 |
ill | +0.052 |
Neg logit contributions | |
clay | -0.066 |
cient | -0.065 |
itt | -0.063 |
cuc | -0.063 |
printer | -0.057 |
Token | ." |
Token ID | 526 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Josh | +0.049 |
forget | +0.048 |
steep | +0.048 |
Josh | +0.046 |
also | +0.046 |
Neg logit contributions | |
cient | -0.045 |
itt | -0.044 |
clay | -0.044 |
cuc | -0.040 |
lear | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.016 |
Neg logit contributions | |
steep | -0.013 |
Josh | -0.013 |
forget | -0.013 |
also | -0.012 |
Josh | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
steep | +0.012 |
forget | +0.012 |
Josh | +0.011 |
existed | +0.011 |
Josh | +0.011 |
Neg logit contributions | |
itt | -0.014 |
cient | -0.014 |
clay | -0.014 |
cuc | -0.013 |
lder | -0.012 |
Token | The |
Token ID | 464 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
steep | +0.009 |
forget | +0.009 |
Josh | +0.008 |
Josh | +0.008 |
also | +0.008 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.016 |
clay | -0.016 |
cuc | -0.015 |
lear | -0.014 |
Token | grass |
Token ID | 8701 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
cient | +0.011 |
itt | +0.010 |
clay | +0.010 |
cuc | +0.009 |
sc | +0.009 |
Neg logit contributions | |
steep | -0.011 |
also | -0.010 |
forget | -0.010 |
Josh | -0.010 |
Josh | -0.010 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.015 |
Neg logit contributions | |
steep | -0.030 |
Josh | -0.029 |
forget | -0.029 |
also | -0.029 |
Josh | -0.028 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
cient | +0.512 |
clay | +0.494 |
itt | +0.493 |
cuc | +0.474 |
lear | +0.442 |
Neg logit contributions | |
steep | -0.310 |
Josh | -0.306 |
forget | -0.301 |
also | -0.287 |
Josh | -0.286 |
Token | sighed |
Token ID | 21893 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
cient | +0.057 |
itt | +0.055 |
clay | +0.055 |
cuc | +0.052 |
lear | +0.049 |
Neg logit contributions | |
steep | -0.040 |
Josh | -0.039 |
forget | -0.039 |
also | -0.038 |
Josh | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
steep | +0.044 |
Josh | +0.044 |
forget | +0.044 |
Josh | +0.042 |
also | +0.041 |
Neg logit contributions | |
cient | -0.052 |
clay | -0.051 |
itt | -0.050 |
cuc | -0.048 |
lear | -0.044 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
steep | +0.011 |
Josh | +0.010 |
forget | +0.010 |
also | +0.010 |
Josh | +0.010 |
Neg logit contributions | |
cient | -0.018 |
itt | -0.017 |
clay | -0.017 |
cuc | -0.016 |
lear | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Josh | +0.091 |
steep | +0.090 |
forget | +0.089 |
Josh | +0.085 |
also | +0.084 |
Neg logit contributions | |
cient | -0.071 |
clay | -0.068 |
itt | -0.066 |
cuc | -0.063 |
lear | -0.059 |
Token | put |
Token ID | 1234 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
cient | +0.010 |
itt | +0.010 |
clay | +0.010 |
cuc | +0.010 |
lear | +0.009 |
Neg logit contributions | |
steep | -0.009 |
Josh | -0.009 |
forget | -0.008 |
Josh | -0.008 |
Sof | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
steep | +0.023 |
Josh | +0.023 |
also | +0.022 |
Josh | +0.022 |
Dan | +0.022 |
Neg logit contributions | |
cient | -0.033 |
itt | -0.030 |
clay | -0.030 |
cuc | -0.029 |
lder | -0.029 |
Token | an |
Token ID | 281 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Josh | +0.052 |
Sof | +0.050 |
Dan | +0.050 |
also | +0.049 |
Mary | +0.049 |
Neg logit contributions | |
cient | -0.093 |
itt | -0.082 |
cuc | -0.079 |
lder | -0.076 |
sc | -0.076 |
Token | oven |
Token ID | 14361 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
steep | +0.087 |
also | +0.083 |
Josh | +0.083 |
forget | +0.083 |
Josh | +0.080 |
Neg logit contributions | |
cient | -0.101 |
itt | -0.096 |
clay | -0.092 |
cuc | -0.089 |
lear | -0.083 |
Token | m |
Token ID | 285 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
cient | +0.240 |
clay | +0.233 |
itt | +0.231 |
cuc | +0.219 |
lear | +0.204 |
Neg logit contributions | |
Josh | -0.236 |
steep | -0.235 |
forget | -0.233 |
also | -0.220 |
Josh | -0.219 |
Token | itt |
Token ID | 715 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
Josh | +0.018 |
steep | +0.018 |
Josh | +0.018 |
forget | +0.018 |
Dan | +0.017 |
Neg logit contributions | |
cient | -0.011 |
clay | -0.011 |
cuc | -0.010 |
itt | -0.010 |
lear | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
cient | +0.412 |
clay | +0.388 |
itt | +0.385 |
cuc | +0.369 |
lder | +0.344 |
Neg logit contributions | |
steep | -0.406 |
forget | -0.396 |
Josh | -0.393 |
also | -0.387 |
Josh | -0.384 |
Token | a |
Token ID | 257 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
also | +0.011 |
forget | +0.011 |
steep | +0.011 |
Josh | +0.011 |
Josh | +0.011 |
Neg logit contributions | |
cient | -0.015 |
clay | -0.014 |
itt | -0.014 |
cuc | -0.014 |
lear | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
cient | +0.024 |
ted | +0.022 |
itt | +0.022 |
clay | +0.020 |
lear | +0.020 |
Neg logit contributions | |
steep | -0.024 |
forget | -0.023 |
also | -0.023 |
Josh | -0.021 |
Josh | -0.021 |
Token | pron |
Token ID | 31186 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
cient | +0.025 |
ted | +0.023 |
itt | +0.023 |
led | +0.020 |
clay | +0.020 |
Neg logit contributions | |
steep | -0.026 |
also | -0.024 |
forget | -0.024 |
Josh | -0.022 |
Josh | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
cient | +0.204 |
itt | +0.193 |
clay | +0.189 |
cuc | +0.183 |
lder | +0.164 |
Neg logit contributions | |
steep | -0.181 |
forget | -0.175 |
Josh | -0.175 |
also | -0.173 |
Josh | -0.170 |
Token | " |
Token ID | 366 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
cient | +0.000 |
clay | +0.000 |
itt | +0.000 |
cuc | +0.000 |
lear | +0.000 |
Neg logit contributions | |
forget | -0.000 |
Josh | -0.000 |
steep | -0.000 |
annie | -0.000 |
existed | -0.000 |
Token | Is |
Token ID | 3792 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.019 |
clay | +0.019 |
cuc | +0.018 |
lear | +0.017 |
Neg logit contributions | |
steep | -0.018 |
forget | -0.017 |
Josh | -0.017 |
Josh | -0.017 |
also | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Josh | +0.060 |
forget | +0.058 |
steep | +0.058 |
ill | +0.055 |
Josh | +0.054 |
Neg logit contributions | |
cient | -0.063 |
clay | -0.059 |
itt | -0.059 |
cuc | -0.056 |
contest | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
cient | +0.031 |
clay | +0.029 |
cuc | +0.027 |
itt | +0.026 |
contest | +0.025 |
Neg logit contributions | |
Josh | -0.038 |
steep | -0.036 |
Josh | -0.034 |
forget | -0.034 |
Matt | -0.034 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
cient | +0.026 |
itt | +0.025 |
clay | +0.024 |
cuc | +0.023 |
ted | +0.022 |
Neg logit contributions | |
steep | -0.026 |
forget | -0.026 |
also | -0.025 |
Josh | -0.024 |
Josh | -0.023 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
cient | +0.033 |
clay | +0.031 |
itt | +0.029 |
cuc | +0.029 |
contest | +0.028 |
Neg logit contributions | |
Josh | -0.039 |
steep | -0.036 |
Josh | -0.036 |
forget | -0.035 |
Matt | -0.034 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
cient | +0.514 |
clay | +0.509 |
itt | +0.498 |
cuc | +0.483 |
lear | +0.452 |
Neg logit contributions | |
steep | -0.294 |
forget | -0.292 |
Josh | -0.289 |
also | -0.279 |
Josh | -0.270 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
cient | +0.054 |
clay | +0.050 |
cuc | +0.048 |
itt | +0.047 |
contest | +0.044 |
Neg logit contributions | |
Josh | -0.048 |
steep | -0.046 |
Josh | -0.044 |
forget | -0.043 |
Matt | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
itt | +0.003 |
clay | +0.003 |
cuc | +0.003 |
cient | +0.003 |
te | +0.003 |
Neg logit contributions | |
steep | -0.005 |
forget | -0.005 |
annie | -0.005 |
Josh | -0.005 |
existed | -0.005 |
Token | guesses |
Token ID | 44774 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
steep | +0.008 |
Josh | +0.008 |
forget | +0.008 |
ill | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
cient | -0.008 |
clay | -0.008 |
cuc | -0.008 |
itt | -0.008 |
te | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Josh | +0.047 |
forget | +0.047 |
steep | +0.047 |
Josh | +0.043 |
also | +0.043 |
Neg logit contributions | |
clay | -0.031 |
cient | -0.031 |
itt | -0.030 |
cuc | -0.028 |
lear | -0.025 |
Token | 't |
Token ID | 470 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
steep | +0.004 |
also | +0.004 |
Josh | +0.004 |
Dan | +0.004 |
Sof | +0.004 |
Neg logit contributions | |
cient | -0.006 |
itt | -0.005 |
clay | -0.005 |
cuc | -0.005 |
sc | -0.005 |
Token | know |
Token ID | 760 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
cient | +0.172 |
clay | +0.168 |
itt | +0.160 |
cuc | +0.156 |
lear | +0.152 |
Neg logit contributions | |
Josh | -0.131 |
steep | -0.127 |
Josh | -0.119 |
Sof | -0.113 |
forget | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
cient | +0.003 |
clay | +0.003 |
itt | +0.002 |
cuc | +0.002 |
lear | +0.002 |
Neg logit contributions | |
Josh | -0.002 |
steep | -0.002 |
forget | -0.002 |
also | -0.002 |
Josh | -0.002 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
cient | +0.044 |
itt | +0.042 |
clay | +0.040 |
cuc | +0.039 |
lder | +0.036 |
Neg logit contributions | |
steep | -0.047 |
forget | -0.046 |
also | -0.045 |
Josh | -0.044 |
Josh | -0.043 |
Token | in |
Token ID | 259 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
clay | +0.094 |
cient | +0.093 |
cuc | +0.090 |
lear | +0.082 |
te | +0.082 |
Neg logit contributions | |
also | -0.095 |
Josh | -0.090 |
steep | -0.087 |
forget | -0.087 |
annie | -0.083 |
Token | oc |
Token ID | 420 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
cient | +0.108 |
itt | +0.106 |
clay | +0.106 |
cuc | +0.092 |
lear | +0.081 |
Neg logit contributions | |
steep | -0.261 |
forget | -0.259 |
also | -0.257 |
Josh | -0.255 |
Josh | -0.252 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
sc | +0.342 |
Mid | +0.331 |
tea | +0.326 |
clay | +0.320 |
cient | +0.308 |
Neg logit contributions | |
Dan | -0.407 |
Josh | -0.402 |
Josh | -0.395 |
Noah | -0.387 |
Matt | -0.377 |
Token | was |
Token ID | 373 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
cient | +0.180 |
itt | +0.176 |
clay | +0.174 |
cuc | +0.166 |
lear | +0.155 |
Neg logit contributions | |
steep | -0.133 |
forget | -0.131 |
Josh | -0.130 |
also | -0.127 |
Josh | -0.125 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
cient | +0.037 |
clay | +0.037 |
itt | +0.036 |
cuc | +0.035 |
lear | +0.032 |
Neg logit contributions | |
Josh | -0.027 |
steep | -0.026 |
forget | -0.026 |
Josh | -0.025 |
also | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
cient | +0.069 |
itt | +0.067 |
clay | +0.065 |
cuc | +0.063 |
lear | +0.058 |
Neg logit contributions | |
steep | -0.058 |
forget | -0.056 |
Josh | -0.055 |
also | -0.054 |
Josh | -0.054 |
Token | Can |
Token ID | 1680 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
cient | +0.005 |
clay | +0.004 |
itt | +0.004 |
cuc | +0.004 |
lear | +0.004 |
Neg logit contributions | |
steep | -0.004 |
forget | -0.004 |
Josh | -0.004 |
also | -0.004 |
Josh | -0.004 |
Token | elly |
Token ID | 6148 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
cient | +0.060 |
clay | +0.056 |
cuc | +0.054 |
itt | +0.054 |
printer | +0.050 |
Neg logit contributions | |
steep | -0.051 |
ill | -0.050 |
Josh | -0.049 |
forget | -0.048 |
Dan | -0.047 |
Token | anymore |
Token ID | 7471 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
steep | +0.009 |
Josh | +0.009 |
forget | +0.009 |
also | +0.009 |
Josh | +0.009 |
Neg logit contributions | |
cient | -0.011 |
itt | -0.011 |
clay | -0.011 |
cuc | -0.010 |
lear | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Josh | +0.148 |
steep | +0.148 |
forget | +0.142 |
Josh | +0.136 |
also | +0.136 |
Neg logit contributions | |
cient | -0.117 |
clay | -0.116 |
itt | -0.112 |
cuc | -0.107 |
lear | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Josh | +0.018 |
steep | +0.017 |
ill | +0.016 |
forget | +0.016 |
Josh | +0.016 |
Neg logit contributions | |
cient | -0.020 |
clay | -0.020 |
itt | -0.019 |
cuc | -0.019 |
war | -0.017 |
Token | l |
Token ID | 300 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
steep | +0.010 |
forget | +0.010 |
Josh | +0.010 |
also | +0.009 |
Josh | +0.009 |
Neg logit contributions | |
cient | -0.010 |
itt | -0.009 |
clay | -0.009 |
cuc | -0.009 |
lear | -0.008 |
Token | itt |
Token ID | 715 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
cient | +0.038 |
clay | +0.036 |
cuc | +0.034 |
itt | +0.032 |
printer | +0.032 |
Neg logit contributions | |
steep | -0.030 |
Josh | -0.030 |
also | -0.029 |
Dan | -0.029 |
ill | -0.029 |
Token | lest |
Token ID | 32712 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
cient | +0.324 |
clay | +0.298 |
itt | +0.288 |
cuc | +0.277 |
lear | +0.264 |
Neg logit contributions | |
forget | -0.489 |
also | -0.481 |
steep | -0.473 |
Josh | -0.458 |
Josh | -0.453 |
Token | ones |
Token ID | 3392 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
cient | +0.240 |
itt | +0.227 |
clay | +0.223 |
cuc | +0.213 |
lder | +0.198 |
Neg logit contributions | |
forget | -0.249 |
steep | -0.247 |
Josh | -0.242 |
also | -0.241 |
Josh | -0.236 |
Token | can |
Token ID | 460 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
cient | +0.002 |
clay | +0.001 |
itt | +0.001 |
cuc | +0.001 |
lear | +0.001 |
Neg logit contributions | |
Josh | -0.001 |
steep | -0.001 |
forget | -0.001 |
Josh | -0.001 |
Sof | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
cient | +0.058 |
clay | +0.057 |
itt | +0.056 |
cuc | +0.053 |
lear | +0.049 |
Neg logit contributions | |
Josh | -0.049 |
steep | -0.049 |
Josh | -0.046 |
forget | -0.046 |
Sof | -0.044 |
Token | up |
Token ID | 510 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
steep | +0.057 |
forget | +0.056 |
Josh | +0.055 |
also | +0.054 |
Josh | +0.053 |
Neg logit contributions | |
cient | -0.050 |
itt | -0.048 |
clay | -0.047 |
cuc | -0.045 |
lear | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
forget | +0.033 |
Josh | +0.032 |
steep | +0.031 |
Phill | +0.030 |
ibi | +0.030 |
Neg logit contributions | |
itt | -0.019 |
clay | -0.018 |
cient | -0.016 |
cuc | -0.015 |
d | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
forget | +0.004 |
annie | +0.004 |
adow | +0.004 |
steep | +0.004 |
consider | +0.004 |
Neg logit contributions | |
itt | -0.002 |
clay | -0.002 |
d | -0.002 |
ted | -0.002 |
Some | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
clay | +0.040 |
cient | +0.038 |
d | +0.036 |
sc | +0.036 |
ted | +0.035 |
Neg logit contributions | |
adow | -0.089 |
Josh | -0.089 |
forget | -0.087 |
ax | -0.085 |
ill | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
clay | +0.020 |
cuc | +0.016 |
soldiers | +0.015 |
fire | +0.015 |
printer | +0.014 |
Neg logit contributions | |
forget | -0.038 |
Josh | -0.037 |
adow | -0.036 |
existed | -0.035 |
annie | -0.035 |
Token | grass |
Token ID | 8701 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
cient | +0.012 |
clay | +0.011 |
itt | +0.011 |
cuc | +0.011 |
lear | +0.010 |
Neg logit contributions | |
Josh | -0.012 |
steep | -0.011 |
forget | -0.011 |
Josh | -0.011 |
also | -0.011 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
clay | +0.017 |
cient | +0.017 |
itt | +0.017 |
cuc | +0.016 |
printer | +0.015 |
Neg logit contributions | |
Josh | -0.022 |
forget | -0.021 |
steep | -0.021 |
Josh | -0.021 |
annie | -0.020 |
Token | pper |
Token ID | 2848 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
cient | +0.510 |
itt | +0.492 |
clay | +0.490 |
cuc | +0.470 |
lear | +0.440 |
Neg logit contributions | |
steep | -0.304 |
Josh | -0.300 |
forget | -0.295 |
also | -0.280 |
Josh | -0.280 |
Token | ! |
Token ID | 0 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
cient | +0.042 |
clay | +0.042 |
itt | +0.040 |
cuc | +0.039 |
printer | +0.035 |
Neg logit contributions | |
Josh | -0.044 |
steep | -0.042 |
forget | -0.041 |
Josh | -0.040 |
annie | -0.039 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
forget | +0.030 |
annie | +0.029 |
adow | +0.028 |
existed | +0.026 |
steep | +0.025 |
Neg logit contributions | |
itt | -0.027 |
clay | -0.026 |
ted | -0.024 |
cient | -0.023 |
d | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
steep | +0.148 |
Josh | +0.144 |
forget | +0.143 |
Sof | +0.136 |
existed | +0.134 |
Neg logit contributions | |
cient | -0.113 |
clay | -0.109 |
itt | -0.107 |
d | -0.103 |
cuc | -0.102 |
Token | so |
Token ID | 523 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
clay | +0.024 |
te | +0.021 |
itt | +0.021 |
d | +0.020 |
cient | +0.019 |
Neg logit contributions | |
existed | -0.032 |
Josh | -0.032 |
steep | -0.031 |
forget | -0.031 |
annie | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
clay | +0.009 |
cient | +0.009 |
itt | +0.009 |
cuc | +0.009 |
lear | +0.008 |
Neg logit contributions | |
forget | -0.008 |
Josh | -0.008 |
steep | -0.008 |
Josh | -0.008 |
also | -0.008 |
Token | picked |
Token ID | 6497 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
steep | +0.012 |
Josh | +0.012 |
forget | +0.011 |
Josh | +0.011 |
also | +0.011 |
Neg logit contributions | |
cient | -0.012 |
itt | -0.012 |
clay | -0.012 |
cuc | -0.011 |
printer | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
cient | +0.064 |
itt | +0.061 |
clay | +0.061 |
cuc | +0.058 |
lear | +0.053 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.060 |
forget | -0.059 |
also | -0.057 |
Josh | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
cient | +0.008 |
clay | +0.008 |
itt | +0.008 |
cuc | +0.007 |
lear | +0.007 |
Neg logit contributions | |
Josh | -0.007 |
steep | -0.007 |
forget | -0.007 |
Josh | -0.007 |
also | -0.007 |
Token | grass |
Token ID | 8701 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
cient | +0.022 |
clay | +0.021 |
itt | +0.021 |
cuc | +0.020 |
lear | +0.018 |
Neg logit contributions | |
Josh | -0.023 |
steep | -0.023 |
forget | -0.023 |
Josh | -0.022 |
also | -0.022 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
cient | +0.024 |
clay | +0.024 |
itt | +0.023 |
cuc | +0.022 |
lear | +0.020 |
Neg logit contributions | |
Josh | -0.031 |
forget | -0.030 |
steep | -0.030 |
Josh | -0.029 |
also | -0.029 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
cient | +0.527 |
clay | +0.517 |
itt | +0.499 |
cuc | +0.490 |
lear | +0.457 |
Neg logit contributions | |
Josh | -0.282 |
steep | -0.281 |
forget | -0.279 |
also | -0.269 |
Josh | -0.265 |
Token | ! |
Token ID | 0 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
cient | +0.052 |
clay | +0.050 |
itt | +0.050 |
cuc | +0.048 |
lear | +0.043 |
Neg logit contributions | |
steep | -0.052 |
Josh | -0.052 |
forget | -0.051 |
Josh | -0.049 |
also | -0.048 |
Token | Both |
Token ID | 5747 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
forget | +0.025 |
Josh | +0.024 |
steep | +0.024 |
annie | +0.023 |
also | +0.022 |
Neg logit contributions | |
cient | -0.033 |
clay | -0.032 |
itt | -0.032 |
cuc | -0.031 |
lder | -0.028 |
Token | friends |
Token ID | 2460 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Josh | +0.067 |
steep | +0.065 |
forget | +0.064 |
annie | +0.062 |
Josh | +0.060 |
Neg logit contributions | |
clay | -0.071 |
cient | -0.069 |
itt | -0.068 |
cuc | -0.065 |
ted | -0.061 |
Token | were |
Token ID | 547 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
steep | +0.015 |
Josh | +0.014 |
forget | +0.014 |
also | +0.014 |
Josh | +0.014 |
Neg logit contributions | |
cient | -0.019 |
itt | -0.018 |
clay | -0.018 |
cuc | -0.017 |
lear | -0.016 |
Token | introduced |
Token ID | 5495 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
cient | +0.036 |
itt | +0.035 |
clay | +0.034 |
cuc | +0.033 |
lear | +0.031 |
Neg logit contributions | |
steep | -0.030 |
forget | -0.030 |
Josh | -0.029 |
also | -0.029 |
Josh | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
cient | +0.079 |
clay | +0.076 |
itt | +0.076 |
cuc | +0.072 |
lear | +0.067 |
Neg logit contributions | |
steep | -0.063 |
Josh | -0.063 |
forget | -0.062 |
also | -0.059 |
Josh | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
itt | +0.033 |
cient | +0.032 |
clay | +0.029 |
cuc | +0.029 |
lder | +0.028 |
Neg logit contributions | |
steep | -0.022 |
Josh | -0.022 |
forget | -0.022 |
Josh | -0.022 |
also | -0.022 |
Token | smooth |
Token ID | 7209 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
itt | +0.022 |
cient | +0.021 |
clay | +0.020 |
ted | +0.019 |
cuc | +0.019 |
Neg logit contributions | |
forget | -0.019 |
steep | -0.019 |
also | -0.018 |
Josh | -0.017 |
Sof | -0.017 |
Token | grass |
Token ID | 8701 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
steep | +0.030 |
forget | +0.029 |
also | +0.028 |
Josh | +0.027 |
Sof | +0.026 |
Neg logit contributions | |
itt | -0.033 |
cient | -0.032 |
clay | -0.028 |
cuc | -0.027 |
lder | -0.026 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
cient | +0.024 |
itt | +0.023 |
clay | +0.023 |
cuc | +0.021 |
lder | +0.020 |
Neg logit contributions | |
steep | -0.023 |
forget | -0.022 |
also | -0.022 |
Josh | -0.022 |
Dan | -0.022 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
cient | +0.498 |
clay | +0.495 |
itt | +0.479 |
cuc | +0.465 |
lear | +0.437 |
Neg logit contributions | |
steep | -0.300 |
forget | -0.299 |
Josh | -0.299 |
also | -0.288 |
Josh | -0.280 |
Token | called |
Token ID | 1444 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
itt | +0.052 |
cient | +0.052 |
clay | +0.050 |
cuc | +0.047 |
lder | +0.045 |
Neg logit contributions | |
also | -0.044 |
forget | -0.044 |
steep | -0.044 |
Sof | -0.041 |
Josh | -0.041 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Josh | +0.017 |
Dan | +0.017 |
Sof | +0.017 |
steep | +0.017 |
Josh | +0.016 |
Neg logit contributions | |
cient | -0.025 |
itt | -0.024 |
clay | -0.023 |
cuc | -0.022 |
lder | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
steep | +0.095 |
Josh | +0.094 |
forget | +0.094 |
also | +0.092 |
Josh | +0.091 |
Neg logit contributions | |
cient | -0.093 |
itt | -0.091 |
clay | -0.089 |
cuc | -0.084 |
lear | -0.078 |
Token | Ted |
Token ID | 11396 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
steep | +0.007 |
forget | +0.007 |
Josh | +0.006 |
annie | +0.006 |
existed | +0.006 |
Neg logit contributions | |
cient | -0.008 |
clay | -0.008 |
itt | -0.007 |
cuc | -0.007 |
lder | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
steep | +0.217 |
forget | +0.213 |
Josh | +0.213 |
also | +0.207 |
Josh | +0.204 |
Neg logit contributions | |
cient | -0.146 |
clay | -0.137 |
itt | -0.137 |
cuc | -0.127 |
lder | -0.115 |
Token | � |
Token ID | 129 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
also | +0.111 |
annie | +0.110 |
steep | +0.109 |
forget | +0.109 |
existed | +0.107 |
Neg logit contributions | |
itt | -0.105 |
cient | -0.099 |
lder | -0.092 |
� | -0.084 |
d | -0.083 |
Token | � |
Token ID | 241 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
forget | +0.213 |
steep | +0.206 |
Josh | +0.206 |
ill | +0.204 |
existed | +0.196 |
Neg logit contributions | |
cient | -0.171 |
clay | -0.159 |
itt | -0.150 |
cuc | -0.142 |
lder | -0.140 |
Token | Gr |
Token ID | 8642 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
forget | +0.045 |
steep | +0.043 |
adow | +0.041 |
annie | +0.040 |
Josh | +0.040 |
Neg logit contributions | |
itt | -0.042 |
lear | -0.039 |
clay | -0.039 |
d | -0.038 |
cient | -0.037 |
Token | ass |
Token ID | 562 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
cient | +0.193 |
clay | +0.184 |
itt | +0.182 |
cuc | +0.177 |
lear | +0.162 |
Neg logit contributions | |
steep | -0.140 |
Josh | -0.140 |
forget | -0.139 |
Josh | -0.133 |
also | -0.132 |
Token | ho |
Token ID | 8873 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
steep | +0.031 |
Josh | +0.030 |
forget | +0.030 |
also | +0.029 |
Josh | +0.029 |
Neg logit contributions | |
cient | -0.037 |
itt | -0.035 |
clay | -0.035 |
cuc | -0.034 |
lear | -0.031 |
Token | pper |
Token ID | 2848 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
cient | +0.380 |
itt | +0.366 |
clay | +0.316 |
lder | +0.315 |
cuc | +0.308 |
Neg logit contributions | |
steep | -0.442 |
forget | -0.415 |
Josh | -0.415 |
also | -0.396 |
Josh | -0.394 |
Token | , |
Token ID | 11 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
cient | +0.047 |
clay | +0.044 |
itt | +0.043 |
cuc | +0.042 |
lder | +0.038 |
Neg logit contributions | |
steep | -0.041 |
Josh | -0.041 |
forget | -0.039 |
Josh | -0.037 |
also | -0.037 |
Token | let |
Token ID | 1309 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
cient | +0.010 |
clay | +0.010 |
itt | +0.010 |
cuc | +0.009 |
printer | +0.009 |
Neg logit contributions | |
steep | -0.009 |
Josh | -0.009 |
ill | -0.009 |
annie | -0.009 |
forget | -0.009 |
Token | â |
Token ID | 22940 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
steep | +0.104 |
forget | +0.100 |
Josh | +0.099 |
also | +0.095 |
Josh | +0.092 |
Neg logit contributions | |
cient | -0.107 |
clay | -0.100 |
itt | -0.100 |
cuc | -0.094 |
lear | -0.087 |
Token | € |
Token ID | 26391 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
steep | +0.095 |
Josh | +0.094 |
forget | +0.093 |
also | +0.088 |
Josh | +0.088 |
Neg logit contributions | |
cient | -0.156 |
clay | -0.150 |
itt | -0.150 |
cuc | -0.144 |
lear | -0.134 |
Token | mother |
Token ID | 2802 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
cient | +0.002 |
clay | +0.002 |
itt | +0.002 |
cuc | +0.002 |
lear | +0.002 |
Neg logit contributions | |
steep | -0.002 |
Josh | -0.002 |
ill | -0.002 |
forget | -0.002 |
existed | -0.002 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
steep | +0.086 |
Josh | +0.082 |
forget | +0.081 |
Josh | +0.075 |
Sof | +0.075 |
Neg logit contributions | |
cient | -0.117 |
itt | -0.114 |
clay | -0.112 |
cuc | -0.107 |
lear | -0.101 |
Token | too |
Token ID | 1165 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
cient | +0.066 |
clay | +0.065 |
cuc | +0.062 |
itt | +0.059 |
lear | +0.057 |
Neg logit contributions | |
Josh | -0.077 |
steep | -0.076 |
forget | -0.074 |
Josh | -0.070 |
Sof | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
Josh | +0.055 |
steep | +0.054 |
forget | +0.053 |
Josh | +0.050 |
Sof | +0.050 |
Neg logit contributions | |
cient | -0.043 |
clay | -0.042 |
itt | -0.042 |
cuc | -0.039 |
lear | -0.037 |
Token | � |
Token ID | 6184 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
forget | +0.003 |
steep | +0.003 |
Josh | +0.003 |
also | +0.002 |
annie | +0.002 |
Neg logit contributions | |
cient | -0.002 |
itt | -0.002 |
clay | -0.002 |
cuc | -0.002 |
lear | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
clay | +0.032 |
cient | +0.032 |
itt | +0.031 |
cuc | +0.030 |
soldiers | +0.027 |
Neg logit contributions | |
Josh | -0.034 |
steep | -0.034 |
forget | -0.032 |
Josh | -0.032 |
Dan | -0.031 |
Token | € |
Token ID | 26391 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
steep | +0.184 |
Josh | +0.183 |
forget | +0.179 |
Josh | +0.174 |
also | +0.173 |
Neg logit contributions | |
cient | -0.170 |
clay | -0.162 |
itt | -0.161 |
cuc | -0.153 |
lear | -0.139 |
Token | � |
Token ID | 129 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
steep | +0.101 |
forget | +0.100 |
also | +0.099 |
existed | +0.093 |
Sof | +0.092 |
Neg logit contributions | |
itt | -0.105 |
cient | -0.102 |
lder | -0.092 |
clay | -0.083 |
� | -0.083 |
Token | � |
Token ID | 241 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
steep | +0.194 |
Josh | +0.192 |
forget | +0.191 |
also | +0.184 |
Josh | +0.183 |
Neg logit contributions | |
cient | -0.175 |
clay | -0.167 |
itt | -0.167 |
cuc | -0.157 |
lear | -0.144 |
Token | That |
Token ID | 2504 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
forget | +0.042 |
steep | +0.041 |
Josh | +0.037 |
existed | +0.036 |
ill | +0.036 |
Neg logit contributions | |
itt | -0.041 |
lear | -0.038 |
clay | -0.037 |
d | -0.037 |
cient | -0.036 |
Token | â |
Token ID | 22940 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Josh | +0.029 |
steep | +0.028 |
forget | +0.027 |
ill | +0.027 |
Sof | +0.027 |
Neg logit contributions | |
cient | -0.026 |
clay | -0.024 |
itt | -0.023 |
cuc | -0.023 |
printer | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
steep | +0.002 |
forget | +0.002 |
Josh | +0.002 |
also | +0.002 |
annie | +0.002 |
Neg logit contributions | |
cient | -0.002 |
clay | -0.002 |
itt | -0.002 |
cuc | -0.002 |
lear | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
forget | +0.016 |
steep | +0.015 |
existed | +0.014 |
Josh | +0.013 |
annie | +0.013 |
Neg logit contributions | |
itt | -0.013 |
clay | -0.012 |
cient | -0.012 |
d | -0.011 |
cuc | -0.011 |
Token | Joe |
Token ID | 19585 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
steep | +0.010 |
forget | +0.010 |
Josh | +0.010 |
Josh | +0.009 |
also | +0.009 |
Neg logit contributions | |
cient | -0.014 |
itt | -0.014 |
clay | -0.014 |
cuc | -0.013 |
lear | -0.012 |
Token | y |
Token ID | 88 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
cient | +0.002 |
itt | +0.002 |
clay | +0.002 |
cuc | +0.002 |
lear | +0.002 |
Neg logit contributions | |
steep | -0.002 |
Josh | -0.002 |
forget | -0.002 |
Josh | -0.002 |
Sof | -0.002 |
Token | dreamed |
Token ID | 27947 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
cient | +0.126 |
clay | +0.121 |
itt | +0.119 |
cuc | +0.115 |
lear | +0.107 |
Neg logit contributions | |
steep | -0.108 |
Josh | -0.106 |
forget | -0.104 |
Josh | -0.099 |
Sof | -0.097 |
Token | about |
Token ID | 546 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
steep | +0.065 |
Josh | +0.062 |
forget | +0.061 |
also | +0.060 |
Josh | +0.059 |
Neg logit contributions | |
cient | -0.105 |
itt | -0.100 |
clay | -0.099 |
cuc | -0.097 |
lder | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Josh | +0.229 |
steep | +0.228 |
forget | +0.223 |
Josh | +0.212 |
ill | +0.208 |
Neg logit contributions | |
cient | -0.235 |
clay | -0.235 |
itt | -0.224 |
cuc | -0.221 |
lear | -0.199 |
Token | fridge |
Token ID | 25772 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
cient | +0.005 |
itt | +0.005 |
clay | +0.005 |
cuc | +0.005 |
lder | +0.004 |
Neg logit contributions | |
steep | -0.005 |
forget | -0.005 |
Josh | -0.005 |
also | -0.005 |
Josh | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
cient | +0.077 |
clay | +0.075 |
itt | +0.072 |
cuc | +0.070 |
contest | +0.064 |
Neg logit contributions | |
Josh | -0.080 |
steep | -0.077 |
forget | -0.075 |
Josh | -0.073 |
also | -0.071 |
Token | weeks |
Token ID | 2745 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
cient | +0.086 |
itt | +0.079 |
clay | +0.076 |
cuc | +0.075 |
sc | +0.073 |
Neg logit contributions | |
Josh | -0.057 |
Josh | -0.056 |
Dan | -0.055 |
also | -0.055 |
steep | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
cient | +0.049 |
itt | +0.047 |
clay | +0.047 |
cuc | +0.044 |
lear | +0.041 |
Neg logit contributions | |
steep | -0.046 |
Josh | -0.046 |
forget | -0.045 |
also | -0.042 |
Josh | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
steep | +0.023 |
forget | +0.022 |
Josh | +0.022 |
also | +0.022 |
Josh | +0.021 |
Neg logit contributions | |
cient | -0.033 |
itt | -0.032 |
clay | -0.031 |
cuc | -0.030 |
lear | -0.029 |
Token | sprinkled |
Token ID | 49692 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
also | +0.015 |
steep | +0.015 |
forget | +0.015 |
Josh | +0.015 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.021 |
itt | -0.020 |
clay | -0.019 |
contest | -0.018 |
lder | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
also | +0.008 |
steep | +0.008 |
Dan | +0.007 |
Josh | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
cient | -0.016 |
lder | -0.014 |
itt | -0.014 |
clay | -0.014 |
lear | -0.013 |
Token | around |
Token ID | 1088 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
cient | +0.042 |
itt | +0.040 |
cuc | +0.038 |
clay | +0.038 |
lder | +0.038 |
Neg logit contributions | |
steep | -0.028 |
also | -0.026 |
existed | -0.024 |
forget | -0.024 |
Sof | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
cient | +0.054 |
itt | +0.051 |
clay | +0.048 |
cuc | +0.047 |
lder | +0.047 |
Neg logit contributions | |
Josh | -0.030 |
steep | -0.030 |
Dan | -0.029 |
Josh | -0.029 |
also | -0.029 |
Token | base |
Token ID | 2779 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
steep | +0.012 |
forget | +0.011 |
Josh | +0.011 |
also | +0.011 |
Josh | +0.011 |
Neg logit contributions | |
cient | -0.012 |
itt | -0.011 |
clay | -0.011 |
cuc | -0.010 |
lear | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Josh | +0.173 |
steep | +0.170 |
forget | +0.169 |
Josh | +0.161 |
also | +0.159 |
Neg logit contributions | |
cient | -0.158 |
clay | -0.157 |
itt | -0.155 |
cuc | -0.145 |
lear | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Josh | +0.048 |
also | +0.048 |
steep | +0.047 |
Josh | +0.047 |
Dan | +0.046 |
Neg logit contributions | |
cient | -0.085 |
itt | -0.080 |
clay | -0.077 |
cuc | -0.074 |
lder | -0.073 |
Token | tree |
Token ID | 5509 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
steep | +0.010 |
forget | +0.010 |
also | +0.010 |
Josh | +0.009 |
Josh | +0.009 |
Neg logit contributions | |
cient | -0.011 |
itt | -0.010 |
clay | -0.010 |
cuc | -0.010 |
lear | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
steep | +0.003 |
forget | +0.003 |
Josh | +0.003 |
also | +0.003 |
Josh | +0.003 |
Neg logit contributions | |
cient | -0.003 |
itt | -0.003 |
clay | -0.003 |
cuc | -0.003 |
lear | -0.002 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
steep | +0.006 |
Josh | +0.006 |
forget | +0.006 |
Josh | +0.006 |
also | +0.006 |
Neg logit contributions | |
cient | -0.008 |
clay | -0.008 |
itt | -0.008 |
cuc | -0.008 |
lear | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
cient | +0.072 |
sc | +0.069 |
itt | +0.066 |
lear | +0.066 |
mer | +0.064 |
Neg logit contributions | |
also | -0.033 |
Mary | -0.030 |
Josh | -0.029 |
Sof | -0.029 |
Kim | -0.029 |
Token | toys |
Token ID | 14958 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
also | +0.034 |
steep | +0.034 |
forget | +0.033 |
Josh | +0.030 |
Josh | +0.030 |
Neg logit contributions | |
cient | -0.036 |
itt | -0.035 |
cuc | -0.034 |
lear | -0.032 |
sc | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
steep | +0.035 |
also | +0.035 |
forget | +0.034 |
Josh | +0.031 |
ill | +0.030 |
Neg logit contributions | |
cient | -0.052 |
itt | -0.050 |
clay | -0.048 |
cuc | -0.047 |
lder | -0.044 |
Token | look |
Token ID | 804 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Josh | +0.027 |
steep | +0.027 |
Josh | +0.025 |
ill | +0.025 |
forget | +0.025 |
Neg logit contributions | |
cient | -0.024 |
clay | -0.023 |
itt | -0.022 |
cuc | -0.022 |
lear | -0.020 |
Token | at |
Token ID | 379 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
itt | +0.006 |
cient | +0.006 |
clay | +0.006 |
cuc | +0.005 |
lear | +0.005 |
Neg logit contributions | |
steep | -0.005 |
forget | -0.005 |
also | -0.005 |
Josh | -0.004 |
Josh | -0.004 |
Token | herself |
Token ID | 5223 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
steep | +0.001 |
Josh | +0.001 |
forget | +0.001 |
also | +0.001 |
Josh | +0.001 |
Neg logit contributions | |
cient | -0.001 |
itt | -0.001 |
clay | -0.001 |
cuc | -0.001 |
lear | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
also | +0.142 |
steep | +0.137 |
forget | +0.128 |
adow | +0.117 |
existed | +0.116 |
Neg logit contributions | |
cient | -0.181 |
itt | -0.176 |
cuc | -0.170 |
clay | -0.163 |
lear | -0.160 |
Token | the |
Token ID | 262 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
clay | +0.060 |
cient | +0.057 |
itt | +0.056 |
cuc | +0.054 |
printer | +0.050 |
Neg logit contributions | |
steep | -0.060 |
Josh | -0.059 |
forget | -0.057 |
Josh | -0.055 |
also | -0.054 |
Token | big |
Token ID | 1263 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
steep | +0.021 |
also | +0.019 |
forget | +0.019 |
Josh | +0.016 |
Mary | +0.015 |
Neg logit contributions | |
cient | -0.031 |
itt | -0.030 |
cuc | -0.030 |
lear | -0.030 |
ware | -0.028 |
Token | mirror |
Token ID | 10162 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
steep | +0.032 |
forget | +0.031 |
Josh | +0.031 |
also | +0.029 |
Josh | +0.029 |
Neg logit contributions | |
cient | -0.035 |
itt | -0.034 |
clay | -0.033 |
cuc | -0.032 |
lear | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
cient | +0.019 |
clay | +0.018 |
itt | +0.018 |
cuc | +0.017 |
lear | +0.016 |
Neg logit contributions | |
forget | -0.016 |
steep | -0.016 |
also | -0.016 |
Josh | -0.016 |
Josh | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
cient | +0.105 |
itt | +0.101 |
clay | +0.100 |
cuc | +0.096 |
lear | +0.090 |
Neg logit contributions | |
steep | -0.071 |
Josh | -0.069 |
forget | -0.068 |
also | -0.066 |
Josh | -0.066 |
Token | would |
Token ID | 561 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
cient | +0.033 |
itt | +0.032 |
clay | +0.032 |
cuc | +0.030 |
lear | +0.028 |
Neg logit contributions | |
steep | -0.025 |
Josh | -0.024 |
forget | -0.024 |
also | -0.024 |
Josh | -0.023 |
Token | be |
Token ID | 307 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
clay | +0.078 |
cient | +0.077 |
cuc | +0.073 |
itt | +0.068 |
contest | +0.068 |
Neg logit contributions | |
Josh | -0.062 |
Josh | -0.058 |
steep | -0.057 |
Dan | -0.054 |
ill | -0.053 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Josh | +0.060 |
forget | +0.057 |
steep | +0.056 |
Josh | +0.056 |
ill | +0.054 |
Neg logit contributions | |
clay | -0.057 |
cient | -0.054 |
cuc | -0.053 |
itt | -0.049 |
soldiers | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
Josh | +0.071 |
steep | +0.070 |
forget | +0.069 |
Josh | +0.067 |
also | +0.066 |
Neg logit contributions | |
cient | -0.056 |
clay | -0.054 |
itt | -0.053 |
cuc | -0.050 |
lear | -0.046 |
Token | leave |
Token ID | 2666 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
cient | +0.029 |
itt | +0.028 |
clay | +0.027 |
cuc | +0.026 |
lear | +0.024 |
Neg logit contributions | |
steep | -0.026 |
forget | -0.026 |
Josh | -0.026 |
also | -0.025 |
Josh | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
steep | +0.214 |
Josh | +0.212 |
forget | +0.210 |
also | +0.201 |
Josh | +0.201 |
Neg logit contributions | |
cient | -0.243 |
itt | -0.232 |
clay | -0.232 |
cuc | -0.221 |
lear | -0.204 |
Token | home |
Token ID | 1363 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
steep | +0.004 |
forget | +0.004 |
Josh | +0.004 |
also | +0.003 |
Josh | +0.003 |
Neg logit contributions | |
cient | -0.003 |
itt | -0.003 |
clay | -0.003 |
cuc | -0.003 |
lear | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Josh | +0.008 |
steep | +0.008 |
Josh | +0.008 |
forget | +0.007 |
Dan | +0.007 |
Neg logit contributions | |
cient | -0.006 |
clay | -0.005 |
itt | -0.005 |
cuc | -0.005 |
soldiers | -0.004 |
Token | explore |
Token ID | 7301 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Josh | +0.012 |
steep | +0.012 |
ill | +0.011 |
Josh | +0.011 |
Sof | +0.011 |
Neg logit contributions | |
clay | -0.010 |
cient | -0.010 |
cuc | -0.010 |
itt | -0.009 |
lear | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
Josh | +0.166 |
steep | +0.165 |
forget | +0.163 |
Josh | +0.156 |
also | +0.155 |
Neg logit contributions | |
cient | -0.178 |
clay | -0.172 |
itt | -0.170 |
cuc | -0.163 |
lear | -0.148 |
Token | good |
Token ID | 922 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
steep | +0.047 |
forget | +0.045 |
also | +0.045 |
Josh | +0.043 |
Dan | +0.041 |
Neg logit contributions | |
cient | -0.070 |
itt | -0.066 |
clay | -0.065 |
cuc | -0.063 |
lear | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
cient | +0.006 |
clay | +0.006 |
itt | +0.006 |
cuc | +0.006 |
lear | +0.005 |
Neg logit contributions | |
Josh | -0.007 |
steep | -0.007 |
forget | -0.007 |
Josh | -0.006 |
also | -0.006 |
Token | stars |
Token ID | 5788 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
also | +0.016 |
forget | +0.016 |
steep | +0.015 |
Mary | +0.013 |
Josh | +0.013 |
Neg logit contributions | |
cient | -0.016 |
ted | -0.014 |
itt | -0.014 |
sc | -0.013 |
lear | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
cient | +0.049 |
itt | +0.047 |
clay | +0.047 |
cuc | +0.045 |
lear | +0.042 |
Neg logit contributions | |
steep | -0.035 |
forget | -0.034 |
Josh | -0.034 |
also | -0.033 |
Josh | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
Josh | +0.023 |
steep | +0.022 |
forget | +0.021 |
Josh | +0.021 |
Sof | +0.021 |
Neg logit contributions | |
cient | -0.019 |
clay | -0.019 |
itt | -0.018 |
cuc | -0.018 |
printer | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Josh | +0.003 |
Sof | +0.003 |
Dan | +0.003 |
Mary | +0.003 |
also | +0.003 |
Neg logit contributions | |
cient | -0.005 |
cuc | -0.004 |
itt | -0.004 |
clay | -0.004 |
trigger | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
steep | +0.016 |
forget | +0.016 |
Josh | +0.016 |
Josh | +0.015 |
ill | +0.014 |
Neg logit contributions | |
cient | -0.020 |
itt | -0.020 |
clay | -0.020 |
cuc | -0.018 |
lder | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
also | +0.010 |
Josh | +0.010 |
forget | +0.009 |
steep | +0.009 |
Mary | +0.008 |
Neg logit contributions | |
cient | -0.027 |
itt | -0.025 |
clay | -0.025 |
cuc | -0.025 |
ware | -0.024 |
Token | little |
Token ID | 1310 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
cient | +0.005 |
itt | +0.005 |
sc | +0.005 |
cuc | +0.005 |
ted | +0.004 |
Neg logit contributions | |
also | -0.005 |
forget | -0.004 |
steep | -0.004 |
Josh | -0.003 |
Mary | -0.003 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
cient | +0.090 |
itt | +0.087 |
cuc | +0.077 |
clay | +0.076 |
lder | +0.073 |
Neg logit contributions | |
forget | -0.078 |
also | -0.074 |
steep | -0.072 |
ill | -0.068 |
Sof | -0.068 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
steep | +0.012 |
Josh | +0.012 |
forget | +0.012 |
also | +0.011 |
Josh | +0.011 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.016 |
clay | -0.016 |
cuc | -0.015 |
lear | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
cient | +0.016 |
clay | +0.016 |
itt | +0.015 |
cuc | +0.015 |
lear | +0.014 |
Neg logit contributions | |
steep | -0.020 |
Josh | -0.020 |
forget | -0.019 |
Josh | -0.019 |
also | -0.019 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
steep | +0.022 |
forget | +0.022 |
Josh | +0.021 |
also | +0.021 |
Josh | +0.020 |
Neg logit contributions | |
cient | -0.024 |
itt | -0.023 |
clay | -0.023 |
cuc | -0.022 |
lear | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Josh | +0.043 |
steep | +0.043 |
forget | +0.040 |
Josh | +0.039 |
also | +0.038 |
Neg logit contributions | |
cient | -0.044 |
clay | -0.043 |
itt | -0.041 |
cuc | -0.040 |
lear | -0.037 |
Token | kept |
Token ID | 4030 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
steep | +0.022 |
Josh | +0.022 |
forget | +0.021 |
Josh | +0.020 |
also | +0.020 |
Neg logit contributions | |
cient | -0.026 |
clay | -0.025 |
itt | -0.024 |
cuc | -0.023 |
lear | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
also | +0.036 |
forget | +0.035 |
Josh | +0.034 |
steep | +0.034 |
Dan | +0.034 |
Neg logit contributions | |
cient | -0.048 |
itt | -0.045 |
clay | -0.042 |
cuc | -0.041 |
lder | -0.041 |
Token | gem |
Token ID | 16840 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
steep | +0.015 |
forget | +0.015 |
Josh | +0.014 |
also | +0.014 |
Josh | +0.014 |
Neg logit contributions | |
cient | -0.012 |
itt | -0.011 |
clay | -0.011 |
cuc | -0.010 |
lear | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Josh | +0.019 |
Josh | +0.018 |
steep | +0.018 |
forget | +0.017 |
Dan | +0.017 |
Neg logit contributions | |
clay | -0.015 |
cient | -0.015 |
itt | -0.014 |
cuc | -0.014 |
ware | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
cient | +0.047 |
itt | +0.045 |
clay | +0.045 |
cuc | +0.043 |
lear | +0.039 |
Neg logit contributions | |
steep | -0.049 |
Josh | -0.048 |
forget | -0.048 |
also | -0.046 |
Josh | -0.046 |
Token | all |
Token ID | 477 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
steep | +0.026 |
Josh | +0.026 |
forget | +0.025 |
Josh | +0.025 |
also | +0.025 |
Neg logit contributions | |
cient | -0.024 |
clay | -0.023 |
itt | -0.023 |
cuc | -0.022 |
lear | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
clay | +0.020 |
cient | +0.019 |
itt | +0.019 |
cuc | +0.018 |
lear | +0.017 |
Neg logit contributions | |
Josh | -0.022 |
steep | -0.021 |
forget | -0.021 |
Josh | -0.021 |
Dan | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
steep | +0.016 |
forget | +0.016 |
Josh | +0.016 |
also | +0.016 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.018 |
itt | -0.017 |
clay | -0.016 |
cuc | -0.016 |
lder | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
steep | +0.004 |
Josh | +0.004 |
forget | +0.004 |
Josh | +0.004 |
also | +0.004 |
Neg logit contributions | |
cient | -0.004 |
itt | -0.004 |
clay | -0.004 |
cuc | -0.004 |
lear | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.015 |
Neg logit contributions | |
steep | -0.021 |
Josh | -0.021 |
forget | -0.020 |
also | -0.020 |
Josh | -0.020 |
Token | Thank |
Token ID | 10449 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
cient | +0.019 |
itt | +0.018 |
clay | +0.018 |
cuc | +0.017 |
lear | +0.016 |
Neg logit contributions | |
steep | -0.023 |
forget | -0.022 |
Josh | -0.022 |
Josh | -0.021 |
also | -0.021 |
Token | you |
Token ID | 345 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
cient | +0.143 |
clay | +0.138 |
cuc | +0.134 |
tant | +0.127 |
ware | +0.124 |
Neg logit contributions | |
Josh | -0.109 |
Josh | -0.104 |
Dan | -0.103 |
also | -0.100 |
forget | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
cient | +0.114 |
itt | +0.109 |
clay | +0.109 |
cuc | +0.103 |
lear | +0.094 |
Neg logit contributions | |
steep | -0.115 |
Josh | -0.114 |
forget | -0.113 |
Josh | -0.109 |
also | -0.109 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
cient | +0.022 |
clay | +0.022 |
itt | +0.021 |
cuc | +0.021 |
lear | +0.020 |
Neg logit contributions | |
steep | -0.018 |
Josh | -0.018 |
forget | -0.017 |
Josh | -0.016 |
existed | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
steep | +0.066 |
Josh | +0.066 |
forget | +0.064 |
Josh | +0.060 |
Sof | +0.060 |
Neg logit contributions | |
cient | -0.033 |
clay | -0.031 |
itt | -0.029 |
cuc | -0.028 |
soldiers | -0.026 |
Token | That |
Token ID | 1320 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
cient | +0.013 |
itt | +0.012 |
clay | +0.012 |
cuc | +0.011 |
lear | +0.010 |
Neg logit contributions | |
steep | -0.015 |
Josh | -0.014 |
forget | -0.014 |
also | -0.014 |
Josh | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
also | +0.037 |
forget | +0.037 |
Josh | +0.036 |
steep | +0.036 |
Josh | +0.035 |
Neg logit contributions | |
itt | -0.052 |
cient | -0.052 |
clay | -0.049 |
cuc | -0.048 |
tant | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
clay | +0.032 |
cient | +0.030 |
war | +0.028 |
cuc | +0.028 |
wine | +0.026 |
Neg logit contributions | |
ill | -0.052 |
Josh | -0.050 |
forget | -0.049 |
hole | -0.048 |
adow | -0.046 |
Token | best |
Token ID | 1266 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
forget | +0.007 |
steep | +0.006 |
Josh | +0.006 |
also | +0.006 |
Josh | +0.006 |
Neg logit contributions | |
cient | -0.011 |
itt | -0.011 |
clay | -0.010 |
cuc | -0.010 |
lder | -0.009 |
Token | look |
Token ID | 804 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
cient | +0.073 |
clay | +0.073 |
itt | +0.068 |
cuc | +0.068 |
contest | +0.063 |
Neg logit contributions | |
Josh | -0.060 |
steep | -0.057 |
Josh | -0.057 |
Dan | -0.054 |
Sof | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
clay | +0.003 |
cient | +0.003 |
cuc | +0.003 |
war | +0.003 |
soldiers | +0.003 |
Neg logit contributions | |
Josh | -0.003 |
Josh | -0.003 |
Dan | -0.003 |
Matt | -0.003 |
Mary | -0.003 |
Token | most |
Token ID | 749 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
steep | +0.024 |
forget | +0.023 |
also | +0.022 |
Josh | +0.021 |
Josh | +0.021 |
Neg logit contributions | |
cient | -0.022 |
itt | -0.021 |
cuc | -0.019 |
lder | -0.019 |
clay | -0.019 |
Token | attractive |
Token ID | 10966 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Josh | +0.119 |
steep | +0.113 |
Josh | +0.111 |
forget | +0.111 |
Sof | +0.107 |
Neg logit contributions | |
clay | -0.138 |
cient | -0.135 |
itt | -0.131 |
cuc | -0.129 |
lear | -0.118 |
Token | on |
Token ID | 319 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
steep | +0.025 |
forget | +0.025 |
also | +0.024 |
Josh | +0.024 |
Josh | +0.024 |
Neg logit contributions | |
cient | -0.023 |
itt | -0.021 |
cuc | -0.019 |
lder | -0.018 |
clay | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
steep | +0.066 |
Josh | +0.065 |
forget | +0.064 |
also | +0.063 |
Josh | +0.062 |
Neg logit contributions | |
cient | -0.087 |
itt | -0.083 |
clay | -0.080 |
cuc | -0.079 |
lear | -0.073 |
Token | shelf |
Token ID | 18316 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
steep | +0.017 |
forget | +0.016 |
also | +0.015 |
Josh | +0.015 |
Josh | +0.014 |
Neg logit contributions | |
cient | -0.026 |
itt | -0.025 |
cuc | -0.023 |
clay | -0.023 |
lder | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Josh | +0.094 |
steep | +0.091 |
forget | +0.089 |
Josh | +0.087 |
Dan | +0.084 |
Neg logit contributions | |
cient | -0.065 |
clay | -0.064 |
itt | -0.063 |
cuc | -0.059 |
printer | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
steep | +0.010 |
Sof | +0.010 |
also | +0.010 |
Josh | +0.010 |
forget | +0.010 |
Neg logit contributions | |
cient | -0.025 |
itt | -0.025 |
cuc | -0.024 |
clay | -0.024 |
ware | -0.022 |
Token | put |
Token ID | 1234 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
steep | +0.019 |
Josh | +0.019 |
forget | +0.019 |
also | +0.018 |
Josh | +0.018 |
Neg logit contributions | |
cient | -0.024 |
itt | -0.023 |
clay | -0.023 |
cuc | -0.022 |
lear | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
also | +0.018 |
steep | +0.017 |
Josh | +0.017 |
Josh | +0.016 |
Sof | +0.016 |
Neg logit contributions | |
cient | -0.038 |
itt | -0.036 |
lder | -0.034 |
cuc | -0.034 |
clay | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
steep | +0.071 |
also | +0.064 |
forget | +0.064 |
Josh | +0.063 |
ill | +0.061 |
Neg logit contributions | |
cient | -0.090 |
itt | -0.086 |
cuc | -0.083 |
clay | -0.083 |
lear | -0.076 |
Token | I |
Token ID | 314 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
steep | +0.034 |
forget | +0.034 |
Josh | +0.034 |
also | +0.032 |
Josh | +0.032 |
Neg logit contributions | |
cient | -0.038 |
clay | -0.037 |
itt | -0.036 |
cuc | -0.036 |
lear | -0.032 |
Token | hope |
Token ID | 2911 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
steep | +0.062 |
forget | +0.061 |
Josh | +0.060 |
also | +0.059 |
Josh | +0.057 |
Neg logit contributions | |
cient | -0.076 |
clay | -0.073 |
itt | -0.073 |
cuc | -0.070 |
lear | -0.064 |
Token | my |
Token ID | 616 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
cient | +0.022 |
clay | +0.022 |
itt | +0.020 |
cuc | +0.019 |
war | +0.018 |
Neg logit contributions | |
Josh | -0.027 |
steep | -0.025 |
Josh | -0.025 |
forget | -0.024 |
ill | -0.024 |
Token | crops |
Token ID | 14450 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
steep | +0.062 |
forget | +0.060 |
also | +0.057 |
Josh | +0.057 |
Josh | +0.056 |
Neg logit contributions | |
itt | -0.058 |
cient | -0.057 |
clay | -0.056 |
cuc | -0.055 |
ware | -0.051 |
Token | don |
Token ID | 836 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Josh | +0.036 |
steep | +0.036 |
forget | +0.035 |
Josh | +0.034 |
also | +0.034 |
Neg logit contributions | |
cient | -0.047 |
clay | -0.045 |
itt | -0.045 |
cuc | -0.043 |
lear | -0.040 |
Token | 't |
Token ID | 470 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
also | +0.016 |
steep | +0.016 |
forget | +0.016 |
Josh | +0.016 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.014 |
clay | -0.013 |
cuc | -0.013 |
itt | -0.013 |
lear | -0.012 |
Token | get |
Token ID | 651 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
Josh | +0.008 |
steep | +0.007 |
Josh | +0.007 |
Dan | +0.007 |
forget | +0.007 |
Neg logit contributions | |
cient | -0.009 |
clay | -0.009 |
itt | -0.009 |
cuc | -0.008 |
lear | -0.008 |
Token | ruined |
Token ID | 20484 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
steep | +0.030 |
forget | +0.028 |
also | +0.028 |
existed | +0.024 |
Sof | +0.022 |
Neg logit contributions | |
itt | -0.046 |
cient | -0.046 |
lear | -0.043 |
cuc | -0.042 |
lder | -0.042 |
Token | ." |
Token ID | 526 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
cient | +0.016 |
itt | +0.015 |
clay | +0.015 |
cuc | +0.014 |
lear | +0.013 |
Neg logit contributions | |
steep | -0.017 |
forget | -0.016 |
Josh | -0.016 |
also | -0.016 |
Josh | -0.016 |
Token | |
Token ID | 220 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
cient | +0.009 |
itt | +0.008 |
clay | +0.008 |
cuc | +0.008 |
lear | +0.008 |
Neg logit contributions | |
Josh | -0.004 |
steep | -0.004 |
forget | -0.004 |
Josh | -0.004 |
also | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
also | +0.020 |
steep | +0.020 |
forget | +0.019 |
Sof | +0.018 |
Dan | +0.018 |
Neg logit contributions | |
cient | -0.024 |
itt | -0.024 |
lear | -0.022 |
printer | -0.021 |
lder | -0.021 |
Token | instead |
Token ID | 2427 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
cient | +0.118 |
itt | +0.115 |
clay | +0.112 |
cuc | +0.105 |
lear | +0.101 |
Neg logit contributions | |
steep | -0.118 |
forget | -0.116 |
Josh | -0.113 |
also | -0.113 |
Josh | -0.109 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
cient | +0.041 |
clay | +0.039 |
itt | +0.039 |
cuc | +0.036 |
lear | +0.033 |
Neg logit contributions | |
Josh | -0.045 |
steep | -0.045 |
forget | -0.044 |
Josh | -0.043 |
also | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
also | +0.007 |
Josh | +0.005 |
Dan | +0.005 |
forget | +0.005 |
Sof | +0.005 |
Neg logit contributions | |
cient | -0.033 |
ocol | -0.033 |
lear | -0.032 |
itt | -0.032 |
ware | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Josh | +0.009 |
steep | +0.009 |
also | +0.008 |
forget | +0.008 |
Josh | +0.008 |
Neg logit contributions | |
cient | -0.018 |
clay | -0.017 |
itt | -0.017 |
cuc | -0.017 |
lear | -0.016 |
Token | B |
Token ID | 33 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
also | +0.014 |
steep | +0.013 |
forget | +0.013 |
Josh | +0.013 |
consider | +0.012 |
Neg logit contributions | |
itt | -0.013 |
cient | -0.013 |
clay | -0.012 |
ocol | -0.012 |
lear | -0.012 |
Token | enny |
Token ID | 11870 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
cient | +0.189 |
clay | +0.185 |
itt | +0.179 |
cuc | +0.178 |
printer | +0.162 |
Neg logit contributions | |
Josh | -0.135 |
steep | -0.134 |
forget | -0.132 |
ill | -0.127 |
Josh | -0.126 |
Token | was |
Token ID | 373 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
cient | +0.017 |
itt | +0.016 |
clay | +0.016 |
cuc | +0.015 |
ocol | +0.014 |
Neg logit contributions | |
also | -0.010 |
forget | -0.010 |
Josh | -0.010 |
steep | -0.010 |
Josh | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
clay | +0.035 |
cient | +0.029 |
te | +0.029 |
cuc | +0.028 |
itt | +0.027 |
Neg logit contributions | |
Josh | -0.047 |
Matt | -0.043 |
annie | -0.043 |
ibi | -0.043 |
steep | -0.043 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
cient | +0.007 |
clay | +0.006 |
itt | +0.006 |
cuc | +0.006 |
lder | +0.006 |
Neg logit contributions | |
Josh | -0.006 |
steep | -0.005 |
Josh | -0.005 |
forget | -0.005 |
annie | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Josh | +0.080 |
steep | +0.078 |
forget | +0.077 |
Josh | +0.074 |
also | +0.071 |
Neg logit contributions | |
clay | -0.076 |
cient | -0.075 |
itt | -0.074 |
cuc | -0.070 |
lear | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
cient | +0.026 |
itt | +0.025 |
clay | +0.025 |
cuc | +0.024 |
lear | +0.022 |
Neg logit contributions | |
steep | -0.017 |
Josh | -0.017 |
forget | -0.017 |
also | -0.016 |
Josh | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
forget | +0.001 |
steep | +0.001 |
Josh | +0.001 |
existed | +0.001 |
annie | +0.001 |
Neg logit contributions | |
itt | -0.001 |
clay | -0.001 |
cient | -0.001 |
cuc | -0.001 |
d | -0.001 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
itt | +0.000 |
clay | +0.000 |
cient | +0.000 |
cuc | +0.000 |
lder | +0.000 |
Neg logit contributions | |
steep | -0.000 |
forget | -0.000 |
existed | -0.000 |
Sof | -0.000 |
Josh | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
steep | +0.058 |
Josh | +0.057 |
forget | +0.056 |
Josh | +0.054 |
also | +0.053 |
Neg logit contributions | |
cient | -0.072 |
clay | -0.070 |
itt | -0.069 |
cuc | -0.067 |
lear | -0.062 |
Token | Anna |
Token ID | 11735 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
steep | +0.007 |
forget | +0.007 |
Josh | +0.007 |
also | +0.007 |
Josh | +0.007 |
Neg logit contributions | |
cient | -0.012 |
itt | -0.012 |
clay | -0.011 |
cuc | -0.011 |
lder | -0.010 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
steep | +0.035 |
Josh | +0.035 |
forget | +0.033 |
Josh | +0.033 |
also | +0.031 |
Neg logit contributions | |
cient | -0.043 |
clay | -0.041 |
itt | -0.041 |
cuc | -0.040 |
lear | -0.037 |
Token | each |
Token ID | 1123 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
cient | +0.073 |
clay | +0.071 |
itt | +0.069 |
cuc | +0.066 |
lear | +0.061 |
Neg logit contributions | |
steep | -0.074 |
Josh | -0.074 |
forget | -0.072 |
also | -0.069 |
Josh | -0.069 |
Token | other |
Token ID | 584 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
cient | +0.103 |
itt | +0.098 |
cuc | +0.092 |
clay | +0.089 |
ware | +0.086 |
Neg logit contributions | |
also | -0.089 |
forget | -0.088 |
Josh | -0.084 |
steep | -0.083 |
Josh | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
cient | +0.006 |
itt | +0.006 |
clay | +0.005 |
cuc | +0.005 |
lear | +0.005 |
Neg logit contributions | |
steep | -0.006 |
forget | -0.006 |
Josh | -0.005 |
also | -0.005 |
Josh | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
clay | +0.012 |
itt | +0.010 |
cient | +0.010 |
cuc | +0.009 |
lear | +0.008 |
Neg logit contributions | |
annie | -0.027 |
forget | -0.026 |
Josh | -0.026 |
steep | -0.025 |
adow | -0.025 |
Token | are |
Token ID | 389 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
cient | +0.090 |
clay | +0.084 |
cuc | +0.081 |
itt | +0.080 |
lear | +0.078 |
Neg logit contributions | |
Josh | -0.081 |
steep | -0.078 |
Josh | -0.076 |
Matt | -0.072 |
existed | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
clay | +0.018 |
cient | +0.018 |
itt | +0.018 |
cuc | +0.017 |
printer | +0.015 |
Neg logit contributions | |
Josh | -0.030 |
forget | -0.029 |
steep | -0.029 |
Josh | -0.027 |
annie | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
forget | +0.016 |
Josh | +0.015 |
annie | +0.014 |
steep | +0.014 |
also | +0.014 |
Neg logit contributions | |
clay | -0.014 |
cient | -0.013 |
itt | -0.013 |
cuc | -0.013 |
printer | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
clay | +0.039 |
cient | +0.037 |
cuc | +0.035 |
d | +0.034 |
sc | +0.032 |
Neg logit contributions | |
Josh | -0.092 |
forget | -0.089 |
steep | -0.087 |
adow | -0.087 |
ax | -0.087 |
Token | made |
Token ID | 925 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
clay | +0.016 |
cuc | +0.014 |
wine | +0.012 |
beans | +0.012 |
fire | +0.012 |
Neg logit contributions | |
forget | -0.031 |
Josh | -0.031 |
adow | -0.029 |
annie | -0.029 |
ibi | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
cient | +0.009 |
itt | +0.009 |
clay | +0.009 |
cuc | +0.008 |
lear | +0.008 |
Neg logit contributions | |
steep | -0.007 |
Josh | -0.007 |
forget | -0.007 |
also | -0.006 |
Josh | -0.006 |
Token | rubber |
Token ID | 14239 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Josh | +0.086 |
forget | +0.084 |
steep | +0.083 |
Josh | +0.080 |
ill | +0.079 |
Neg logit contributions | |
clay | -0.060 |
cient | -0.058 |
cuc | -0.056 |
itt | -0.055 |
printer | -0.048 |
Token | ! |
Token ID | 0 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
cient | +0.112 |
itt | +0.103 |
lder | +0.097 |
clay | +0.089 |
cuc | +0.087 |
Neg logit contributions | |
steep | -0.110 |
forget | -0.108 |
also | -0.105 |
Dan | -0.101 |
ill | -0.098 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
forget | +0.038 |
Josh | +0.034 |
annie | +0.034 |
steep | +0.034 |
adow | +0.034 |
Neg logit contributions | |
clay | -0.040 |
itt | -0.040 |
cient | -0.039 |
cuc | -0.037 |
ted | -0.035 |
Token | picked |
Token ID | 6497 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
steep | +0.132 |
Josh | +0.129 |
forget | +0.127 |
Josh | +0.120 |
Sof | +0.119 |
Neg logit contributions | |
cient | -0.129 |
clay | -0.125 |
itt | -0.124 |
cuc | -0.120 |
lder | -0.109 |
Token | up |
Token ID | 510 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
cient | +0.050 |
clay | +0.049 |
itt | +0.048 |
cuc | +0.046 |
lear | +0.042 |
Neg logit contributions | |
steep | -0.041 |
Josh | -0.041 |
forget | -0.040 |
Josh | -0.038 |
also | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
forget | +0.002 |
steep | +0.002 |
Josh | +0.002 |
also | +0.002 |
Josh | +0.002 |
Neg logit contributions | |
cient | -0.002 |
clay | -0.002 |
itt | -0.002 |
cuc | -0.002 |
lear | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
cient | +0.073 |
itt | +0.069 |
clay | +0.064 |
lder | +0.063 |
lear | +0.061 |
Neg logit contributions | |
forget | -0.059 |
also | -0.056 |
Sof | -0.056 |
Dan | -0.056 |
Josh | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
cient | +0.109 |
itt | +0.104 |
clay | +0.104 |
cuc | +0.099 |
lear | +0.090 |
Neg logit contributions | |
steep | -0.116 |
Josh | -0.115 |
forget | -0.114 |
also | -0.110 |
Josh | -0.110 |
Token | Goodbye |
Token ID | 44442 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
cient | +0.014 |
itt | +0.014 |
clay | +0.013 |
cuc | +0.013 |
lear | +0.012 |
Neg logit contributions | |
steep | -0.016 |
Josh | -0.015 |
forget | -0.015 |
also | -0.015 |
Josh | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
steep | +0.010 |
forget | +0.009 |
Josh | +0.009 |
Josh | +0.009 |
also | +0.009 |
Neg logit contributions | |
cient | -0.010 |
itt | -0.010 |
clay | -0.010 |
cuc | -0.009 |
lear | -0.009 |
Token | cater |
Token ID | 20825 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
clay | +0.010 |
cient | +0.010 |
cuc | +0.009 |
itt | +0.008 |
lear | +0.008 |
Neg logit contributions | |
Josh | -0.020 |
steep | -0.020 |
Josh | -0.019 |
Matt | -0.018 |
existed | -0.018 |
Token | pillar |
Token ID | 41643 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
cient | +0.033 |
clay | +0.032 |
itt | +0.028 |
cuc | +0.028 |
printer | +0.027 |
Neg logit contributions | |
steep | -0.037 |
Josh | -0.036 |
forget | -0.036 |
also | -0.036 |
Sof | -0.036 |
Token | ." |
Token ID | 526 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
itt | +0.093 |
cient | +0.091 |
clay | +0.090 |
cuc | +0.086 |
tant | +0.081 |
Neg logit contributions | |
forget | -0.059 |
also | -0.057 |
steep | -0.055 |
adow | -0.054 |
Sof | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
cient | +0.035 |
itt | +0.033 |
clay | +0.033 |
cuc | +0.032 |
lear | +0.030 |
Neg logit contributions | |
steep | -0.020 |
Josh | -0.020 |
forget | -0.020 |
also | -0.019 |
Josh | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
steep | +0.007 |
forget | +0.006 |
Josh | +0.006 |
existed | +0.006 |
Josh | +0.006 |
Neg logit contributions | |
clay | -0.007 |
itt | -0.007 |
cient | -0.007 |
cuc | -0.007 |
d | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
steep | +0.005 |
Josh | +0.005 |
forget | +0.005 |
Josh | +0.004 |
existed | +0.004 |
Neg logit contributions | |
cient | -0.008 |
itt | -0.007 |
clay | -0.007 |
cuc | -0.007 |
lear | -0.007 |
Token | cater |
Token ID | 20825 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
cient | +0.010 |
itt | +0.010 |
clay | +0.010 |
cuc | +0.009 |
lear | +0.008 |
Neg logit contributions | |
steep | -0.014 |
forget | -0.014 |
Josh | -0.014 |
also | -0.013 |
Josh | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
forget | +0.004 |
steep | +0.004 |
also | +0.004 |
Josh | +0.004 |
Josh | +0.004 |
Neg logit contributions | |
itt | -0.005 |
cient | -0.005 |
clay | -0.005 |
cuc | -0.005 |
ware | -0.004 |
Token | Molly |
Token ID | 30236 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
cient | +0.027 |
itt | +0.026 |
clay | +0.025 |
cuc | +0.024 |
lear | +0.023 |
Neg logit contributions | |
Josh | -0.014 |
Josh | -0.014 |
forget | -0.014 |
also | -0.014 |
Dan | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
steep | +0.034 |
Josh | +0.034 |
forget | +0.034 |
also | +0.033 |
Josh | +0.032 |
Neg logit contributions | |
cient | -0.054 |
itt | -0.052 |
clay | -0.052 |
cuc | -0.049 |
lear | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
clay | +0.033 |
te | +0.027 |
itt | +0.027 |
cient | +0.025 |
fire | +0.025 |
Neg logit contributions | |
steep | -0.040 |
Josh | -0.039 |
existed | -0.039 |
ibi | -0.039 |
annie | -0.038 |
Token | little |
Token ID | 1310 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
cient | +0.025 |
itt | +0.024 |
clay | +0.022 |
ted | +0.022 |
ware | +0.022 |
Neg logit contributions | |
forget | -0.031 |
steep | -0.030 |
also | -0.029 |
Josh | -0.027 |
Josh | -0.026 |
Token | bit |
Token ID | 1643 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
cient | +0.103 |
itt | +0.100 |
clay | +0.098 |
cuc | +0.093 |
lder | +0.087 |
Neg logit contributions | |
steep | -0.072 |
forget | -0.071 |
Josh | -0.069 |
also | -0.068 |
Josh | -0.066 |
Token | relieved |
Token ID | 22598 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
cient | +0.234 |
itt | +0.224 |
clay | +0.222 |
cuc | +0.214 |
lder | +0.202 |
Neg logit contributions | |
steep | -0.123 |
forget | -0.117 |
also | -0.116 |
Josh | -0.114 |
Josh | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
steep | +0.111 |
Josh | +0.110 |
forget | +0.109 |
also | +0.104 |
Josh | +0.104 |
Neg logit contributions | |
cient | -0.123 |
itt | -0.117 |
clay | -0.117 |
cuc | -0.112 |
lear | -0.103 |
Token | Her |
Token ID | 2332 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
cient | +0.003 |
itt | +0.003 |
clay | +0.003 |
cuc | +0.003 |
lear | +0.003 |
Neg logit contributions | |
steep | -0.002 |
Josh | -0.002 |
forget | -0.002 |
also | -0.002 |
Josh | -0.002 |
Token | dad |
Token ID | 9955 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
clay | +0.039 |
itt | +0.038 |
printer | +0.036 |
cient | +0.036 |
lder | +0.035 |
Neg logit contributions | |
steep | -0.041 |
ill | -0.039 |
hole | -0.038 |
Sof | -0.036 |
existed | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
steep | +0.043 |
Josh | +0.042 |
forget | +0.041 |
Josh | +0.039 |
also | +0.038 |
Neg logit contributions | |
cient | -0.057 |
itt | -0.054 |
clay | -0.054 |
cuc | -0.052 |
lear | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
steep | +0.154 |
forget | +0.152 |
Josh | +0.148 |
annie | +0.146 |
ents | +0.144 |
Neg logit contributions | |
clay | -0.078 |
cient | -0.068 |
itt | -0.067 |
cuc | -0.058 |
contest | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
cient | +0.032 |
itt | +0.029 |
clay | +0.028 |
cuc | +0.028 |
lear | +0.026 |
Neg logit contributions | |
also | -0.023 |
steep | -0.023 |
Josh | -0.023 |
forget | -0.022 |
Josh | -0.022 |
Token | helpless |
Token ID | 21144 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
cient | +0.013 |
itt | +0.013 |
clay | +0.012 |
ted | +0.012 |
cuc | +0.011 |
Neg logit contributions | |
steep | -0.014 |
forget | -0.014 |
also | -0.014 |
Josh | -0.013 |
Josh | -0.012 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
itt | +0.033 |
cient | +0.032 |
clay | +0.030 |
sc | +0.029 |
cuc | +0.029 |
Neg logit contributions | |
steep | -0.036 |
forget | -0.034 |
also | -0.034 |
Sof | -0.032 |
Dan | -0.032 |
Token | in |
Token ID | 259 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
cient | +0.065 |
cuc | +0.063 |
clay | +0.061 |
lear | +0.057 |
sc | +0.055 |
Neg logit contributions | |
also | -0.069 |
Josh | -0.065 |
steep | -0.061 |
annie | -0.060 |
forget | -0.059 |
Token | oc |
Token ID | 420 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
cient | +0.103 |
itt | +0.100 |
clay | +0.100 |
cuc | +0.095 |
ocol | +0.091 |
Neg logit contributions | |
also | -0.168 |
forget | -0.154 |
steep | -0.154 |
Josh | -0.144 |
adow | -0.142 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
sc | +0.294 |
clay | +0.283 |
cient | +0.272 |
itt | +0.255 |
cuc | +0.252 |
Neg logit contributions | |
Dan | -0.370 |
Josh | -0.364 |
Josh | -0.363 |
Sof | -0.361 |
Noah | -0.355 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
cient | +0.154 |
itt | +0.149 |
cuc | +0.147 |
clay | +0.145 |
ware | +0.136 |
Neg logit contributions | |
also | -0.125 |
steep | -0.115 |
adow | -0.112 |
forget | -0.111 |
Dan | -0.109 |
Token | She |
Token ID | 1375 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
forget | +0.009 |
Josh | +0.009 |
steep | +0.009 |
also | +0.008 |
Josh | +0.008 |
Neg logit contributions | |
cient | -0.008 |
clay | -0.008 |
itt | -0.007 |
cuc | -0.007 |
lder | -0.006 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
also | +0.013 |
steep | +0.012 |
forget | +0.012 |
Josh | +0.011 |
existed | +0.010 |
Neg logit contributions | |
itt | -0.017 |
cient | -0.017 |
clay | -0.017 |
cuc | -0.016 |
lear | -0.016 |
Token | alone |
Token ID | 3436 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
steep | +0.070 |
also | +0.070 |
forget | +0.067 |
Josh | +0.067 |
Sof | +0.064 |
Neg logit contributions | |
cient | -0.078 |
itt | -0.074 |
clay | -0.073 |
cuc | -0.071 |
lear | -0.065 |
Token | play |
Token ID | 711 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
cient | +0.007 |
clay | +0.007 |
itt | +0.007 |
cuc | +0.007 |
lear | +0.006 |
Neg logit contributions | |
steep | -0.008 |
Josh | -0.008 |
forget | -0.008 |
Josh | -0.007 |
also | -0.007 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
also | +0.016 |
about | +0.014 |
steep | +0.012 |
there | +0.012 |
but | +0.012 |
Neg logit contributions | |
cient | -0.035 |
itt | -0.033 |
lder | -0.030 |
cuc | -0.030 |
trigger | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
cient | +0.099 |
itt | +0.092 |
cuc | +0.087 |
clay | +0.086 |
lder | +0.084 |
Neg logit contributions | |
also | -0.067 |
steep | -0.066 |
forget | -0.061 |
Josh | -0.060 |
Josh | -0.059 |
Token | pick |
Token ID | 2298 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Josh | +0.026 |
Josh | +0.023 |
annie | +0.023 |
ill | +0.023 |
steep | +0.023 |
Neg logit contributions | |
clay | -0.027 |
cient | -0.027 |
cuc | -0.025 |
itt | -0.024 |
lear | -0.023 |
Token | da |
Token ID | 12379 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
steep | +0.039 |
Josh | +0.038 |
forget | +0.038 |
also | +0.037 |
Josh | +0.037 |
Neg logit contributions | |
cient | -0.032 |
itt | -0.030 |
clay | -0.030 |
cuc | -0.028 |
lear | -0.026 |
Token | is |
Token ID | 271 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
steep | +0.057 |
Sof | +0.057 |
also | +0.056 |
forget | +0.056 |
Josh | +0.055 |
Neg logit contributions | |
cient | -0.038 |
clay | -0.036 |
itt | -0.034 |
lear | -0.032 |
cuc | -0.032 |
Token | ies |
Token ID | 444 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
cient | +0.370 |
itt | +0.343 |
clay | +0.340 |
printer | +0.324 |
war | +0.322 |
Neg logit contributions | |
Sof | -0.237 |
ill | -0.236 |
Dan | -0.232 |
also | -0.231 |
forget | -0.230 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
steep | +0.095 |
Josh | +0.094 |
forget | +0.093 |
also | +0.090 |
Josh | +0.089 |
Neg logit contributions | |
cient | -0.094 |
itt | -0.089 |
clay | -0.089 |
cuc | -0.084 |
lear | -0.077 |
Token | One |
Token ID | 1881 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
Josh | +0.016 |
steep | +0.016 |
forget | +0.016 |
annie | +0.015 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.013 |
clay | -0.013 |
itt | -0.012 |
cuc | -0.012 |
lear | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
cient | +0.010 |
clay | +0.010 |
itt | +0.009 |
cuc | +0.008 |
contest | +0.008 |
Neg logit contributions | |
Josh | -0.021 |
Josh | -0.020 |
steep | -0.019 |
forget | -0.019 |
Dan | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
cient | +0.180 |
clay | +0.163 |
itt | +0.161 |
cuc | +0.159 |
printer | +0.151 |
Neg logit contributions | |
Dan | -0.097 |
Josh | -0.096 |
Sof | -0.093 |
forget | -0.091 |
Josh | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
cient | +0.001 |
itt | +0.001 |
clay | +0.001 |
cuc | +0.001 |
lear | +0.001 |
Neg logit contributions | |
steep | -0.001 |
Josh | -0.001 |
forget | -0.001 |
also | -0.001 |
Josh | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
steep | +0.006 |
forget | +0.005 |
Josh | +0.005 |
also | +0.005 |
Josh | +0.005 |
Neg logit contributions | |
cient | -0.007 |
itt | -0.007 |
clay | -0.007 |
cuc | -0.006 |
lear | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
forget | +0.031 |
steep | +0.031 |
existed | +0.029 |
annie | +0.026 |
adow | +0.026 |
Neg logit contributions | |
itt | -0.028 |
cient | -0.025 |
d | -0.024 |
clay | -0.024 |
cuc | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
steep | +0.023 |
forget | +0.023 |
existed | +0.022 |
Sof | +0.020 |
annie | +0.020 |
Neg logit contributions | |
itt | -0.030 |
cient | -0.028 |
clay | -0.027 |
cuc | -0.027 |
lder | -0.026 |
Token | Exc |
Token ID | 40127 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
cient | +0.041 |
itt | +0.041 |
clay | +0.040 |
cuc | +0.039 |
lear | +0.036 |
Neg logit contributions | |
steep | -0.041 |
forget | -0.040 |
Josh | -0.038 |
Josh | -0.037 |
also | -0.037 |
Token | use |
Token ID | 1904 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
clay | +0.040 |
cient | +0.040 |
itt | +0.038 |
cuc | +0.034 |
soldiers | +0.029 |
Neg logit contributions | |
forget | -0.084 |
Josh | -0.084 |
steep | -0.083 |
also | -0.080 |
Josh | -0.080 |
Token | me |
Token ID | 502 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
cient | +0.240 |
clay | +0.214 |
itt | +0.211 |
cuc | +0.206 |
lder | +0.184 |
Neg logit contributions | |
steep | -0.399 |
forget | -0.383 |
Josh | -0.382 |
also | -0.371 |
existed | -0.362 |
Token | ," |
Token ID | 553 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
cient | +0.027 |
itt | +0.026 |
clay | +0.024 |
cuc | +0.023 |
lear | +0.021 |
Neg logit contributions | |
steep | -0.037 |
Josh | -0.037 |
forget | -0.035 |
also | -0.034 |
annie | -0.033 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
cient | +0.008 |
clay | +0.007 |
itt | +0.007 |
cuc | +0.007 |
printer | +0.007 |
Neg logit contributions | |
steep | -0.005 |
Josh | -0.005 |
forget | -0.005 |
existed | -0.005 |
annie | -0.004 |
Token | asked |
Token ID | 1965 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
steep | +0.065 |
Josh | +0.064 |
forget | +0.063 |
also | +0.060 |
Josh | +0.060 |
Neg logit contributions | |
cient | -0.115 |
itt | -0.111 |
clay | -0.111 |
cuc | -0.106 |
lear | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
steep | +0.003 |
Josh | +0.003 |
forget | +0.003 |
Josh | +0.003 |
also | +0.003 |
Neg logit contributions | |
cient | -0.003 |
itt | -0.003 |
clay | -0.003 |
cuc | -0.003 |
lear | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
cient | +0.011 |
itt | +0.010 |
clay | +0.010 |
cuc | +0.009 |
lear | +0.009 |
Neg logit contributions | |
steep | -0.010 |
Josh | -0.010 |
forget | -0.010 |
annie | -0.010 |
Josh | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
forget | +0.005 |
steep | +0.005 |
Josh | +0.005 |
existed | +0.005 |
ill | +0.005 |
Neg logit contributions | |
itt | -0.005 |
cient | -0.005 |
clay | -0.005 |
d | -0.004 |
cuc | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
steep | +0.003 |
Josh | +0.003 |
Josh | +0.003 |
forget | +0.003 |
Dan | +0.003 |
Neg logit contributions | |
itt | -0.004 |
cient | -0.004 |
clay | -0.004 |
cuc | -0.004 |
lear | -0.003 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
cient | +0.010 |
itt | +0.009 |
clay | +0.009 |
cuc | +0.008 |
sc | +0.008 |
Neg logit contributions | |
also | -0.011 |
forget | -0.011 |
steep | -0.011 |
Josh | -0.010 |
Josh | -0.009 |
Token | in |
Token ID | 259 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
cient | +0.056 |
clay | +0.052 |
cuc | +0.050 |
lear | +0.046 |
sc | +0.046 |
Neg logit contributions | |
also | -0.059 |
Josh | -0.057 |
forget | -0.052 |
steep | -0.052 |
Dan | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
cient | +0.095 |
clay | +0.092 |
itt | +0.083 |
cuc | +0.081 |
beans | +0.075 |
Neg logit contributions | |
also | -0.190 |
Josh | -0.184 |
forget | -0.177 |
steep | -0.177 |
Josh | -0.172 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
sc | +0.296 |
cient | +0.282 |
clay | +0.273 |
cuc | +0.266 |
itt | +0.257 |
Neg logit contributions | |
Josh | -0.352 |
Dan | -0.339 |
Noah | -0.338 |
Josh | -0.336 |
Sof | -0.327 |
Token | came |
Token ID | 1625 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
cient | +0.158 |
itt | +0.154 |
clay | +0.153 |
cuc | +0.145 |
lear | +0.132 |
Neg logit contributions | |
also | -0.099 |
steep | -0.096 |
forget | -0.096 |
Josh | -0.094 |
Josh | -0.089 |
Token | closer |
Token ID | 5699 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
cient | +0.100 |
clay | +0.096 |
itt | +0.095 |
cuc | +0.089 |
lear | +0.083 |
Neg logit contributions | |
steep | -0.105 |
Josh | -0.105 |
forget | -0.103 |
Josh | -0.099 |
also | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
cient | +0.029 |
clay | +0.028 |
itt | +0.027 |
cuc | +0.026 |
lear | +0.025 |
Neg logit contributions | |
Josh | -0.032 |
steep | -0.031 |
forget | -0.031 |
Josh | -0.029 |
also | -0.029 |
Token | closer |
Token ID | 5699 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
steep | +0.011 |
also | +0.010 |
forget | +0.010 |
Josh | +0.009 |
Josh | +0.009 |
Neg logit contributions | |
itt | -0.015 |
cient | -0.015 |
clay | -0.015 |
cuc | -0.013 |
lder | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
cient | +0.059 |
itt | +0.056 |
clay | +0.056 |
cuc | +0.053 |
lear | +0.050 |
Neg logit contributions | |
Josh | -0.040 |
steep | -0.039 |
forget | -0.038 |
Josh | -0.037 |
Sof | -0.036 |
Token | go |
Token ID | 467 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
cient | +0.001 |
clay | +0.001 |
itt | +0.001 |
cuc | +0.001 |
printer | +0.001 |
Neg logit contributions | |
Josh | -0.001 |
steep | -0.001 |
forget | -0.001 |
Josh | -0.001 |
Sof | -0.001 |
Token | see |
Token ID | 766 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Josh | +0.053 |
steep | +0.052 |
forget | +0.050 |
Josh | +0.049 |
Sof | +0.049 |
Neg logit contributions | |
cient | -0.044 |
clay | -0.042 |
itt | -0.041 |
cuc | -0.038 |
printer | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
steep | +0.070 |
Josh | +0.070 |
forget | +0.069 |
also | +0.065 |
Josh | +0.065 |
Neg logit contributions | |
cient | -0.082 |
clay | -0.079 |
itt | -0.078 |
cuc | -0.074 |
lear | -0.068 |
Token | fire |
Token ID | 2046 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
also | +0.026 |
steep | +0.025 |
forget | +0.024 |
Josh | +0.022 |
Josh | +0.021 |
Neg logit contributions | |
itt | -0.017 |
cient | -0.017 |
cuc | -0.015 |
lear | -0.015 |
ted | -0.015 |
Token | work |
Token ID | 1818 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
cient | +0.094 |
itt | +0.091 |
clay | +0.088 |
cuc | +0.085 |
lear | +0.074 |
Neg logit contributions | |
steep | -0.221 |
forget | -0.218 |
also | -0.217 |
Josh | -0.215 |
Josh | -0.212 |
Token | show |
Token ID | 905 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
cient | +0.350 |
itt | +0.348 |
clay | +0.327 |
cuc | +0.319 |
lear | +0.296 |
Neg logit contributions | |
forget | -0.354 |
steep | -0.353 |
also | -0.345 |
Josh | -0.331 |
Josh | -0.326 |
Token | . |
Token ID | 13 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
cient | +0.074 |
itt | +0.071 |
clay | +0.070 |
cuc | +0.068 |
lear | +0.061 |
Neg logit contributions | |
steep | -0.071 |
forget | -0.070 |
Josh | -0.070 |
also | -0.069 |
Josh | -0.068 |
Token | Sophie |
Token ID | 35331 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
steep | +0.003 |
Josh | +0.003 |
forget | +0.003 |
also | +0.002 |
Josh | +0.002 |
Neg logit contributions | |
cient | -0.004 |
clay | -0.003 |
itt | -0.003 |
cuc | -0.003 |
lear | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
also | +0.101 |
Josh | +0.099 |
forget | +0.098 |
steep | +0.097 |
Josh | +0.094 |
Neg logit contributions | |
cient | -0.149 |
clay | -0.146 |
itt | -0.145 |
cuc | -0.140 |
lear | -0.128 |
Token | her |
Token ID | 607 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
forget | +0.015 |
Josh | +0.015 |
steep | +0.015 |
also | +0.015 |
Josh | +0.015 |
Neg logit contributions | |
cient | -0.016 |
itt | -0.016 |
clay | -0.016 |
cuc | -0.015 |
sc | -0.014 |