Token | tests |
Token ID | 5254 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
fell | +0.024 |
ihad | +0.021 |
iaries | +0.021 |
ATES | +0.020 |
inges | +0.020 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.013 |
lear | -0.013 |
Token | undertaken |
Token ID | 21846 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
rade | +0.113 |
Braun | +0.106 |
synchronized | +0.103 |
Larson | +0.103 |
lear | +0.103 |
Neg logit contributions | |
fell | -0.150 |
ihad | -0.130 |
iaries | -0.129 |
inges | -0.127 |
ATES | -0.127 |
Token | after |
Token ID | 706 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
rade | +0.141 |
Braun | +0.134 |
synchronized | +0.131 |
Larson | +0.130 |
lear | +0.129 |
Neg logit contributions | |
fell | -0.175 |
ihad | -0.150 |
iaries | -0.150 |
inges | -0.147 |
ATES | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
lear | +0.001 |
Neg logit contributions | |
fell | -0.001 |
ihad | -0.001 |
iaries | -0.001 |
inges | -0.001 |
ATES | -0.001 |
Token | Gren |
Token ID | 19674 |
Feature activation | +4.24e-04 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
inges | +0.013 |
ATES | +0.013 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.013 |
synchronized | -0.013 |
Larson | -0.013 |
prolifer | -0.013 |
Token | fell |
Token ID | 23299 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
fell | +0.000 |
ATES | -0.000 |
iaries | -0.000 |
ihad | -0.000 |
inges | -0.000 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
oulder | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
Token | Tower |
Token ID | 8765 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
fell | +0.390 |
ihad | +0.319 |
iaries | +0.319 |
inges | +0.310 |
ATES | +0.309 |
Neg logit contributions | |
rade | -0.496 |
Braun | -0.477 |
synchronized | -0.469 |
Larson | -0.466 |
prolifer | -0.464 |
Token | fire |
Token ID | 2046 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
fell | +0.066 |
ihad | +0.055 |
iaries | +0.055 |
inges | +0.053 |
ATES | +0.053 |
Neg logit contributions | |
rade | -0.073 |
Braun | -0.070 |
synchronized | -0.069 |
Larson | -0.069 |
prolifer | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
fell | +0.035 |
ihad | +0.030 |
iaries | +0.029 |
inges | +0.029 |
ATES | +0.029 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
Larson | -0.024 |
lear | -0.024 |
Token | according |
Token ID | 1864 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
fell | +0.018 |
ihad | +0.015 |
iaries | +0.015 |
ATES | +0.015 |
inges | +0.015 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.012 |
synchronized | -0.011 |
Larson | -0.011 |
lear | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
fell | +0.031 |
ihad | +0.027 |
iaries | +0.027 |
inges | +0.026 |
ATES | +0.026 |
Neg logit contributions | |
rade | -0.027 |
Braun | -0.026 |
synchronized | -0.025 |
Larson | -0.025 |
prolifer | -0.025 |
Token | fire |
Token ID | 2046 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
rade | +0.010 |
Braun | +0.009 |
synchronized | +0.009 |
Larson | +0.009 |
lear | +0.009 |
Neg logit contributions | |
fell | -0.009 |
ihad | -0.008 |
iaries | -0.008 |
inges | -0.007 |
ATES | -0.007 |
Token | last |
Token ID | 938 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
lear | +0.002 |
Larson | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | month |
Token ID | 1227 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
rade | +0.020 |
Braun | +0.019 |
synchronized | +0.019 |
Larson | +0.019 |
lear | +0.019 |
Neg logit contributions | |
fell | -0.030 |
ihad | -0.025 |
iaries | -0.025 |
inges | -0.025 |
ATES | -0.025 |
Token | at |
Token ID | 379 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
rade | +0.028 |
Braun | +0.027 |
synchronized | +0.026 |
Larson | +0.026 |
lear | +0.026 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.034 |
iaries | -0.034 |
inges | -0.033 |
ATES | -0.033 |
Token | Gren |
Token ID | 19674 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
rade | +0.015 |
Braun | +0.014 |
synchronized | +0.014 |
Larson | +0.014 |
prolifer | +0.014 |
Neg logit contributions | |
fell | -0.016 |
ihad | -0.014 |
iaries | -0.014 |
ATES | -0.014 |
inges | -0.014 |
Token | fell |
Token ID | 23299 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
oulder | +0.009 |
lear | +0.009 |
synchronized | +0.009 |
Neg logit contributions | |
fell | -0.000 |
iaries | +0.001 |
ATES | +0.001 |
ihad | +0.001 |
inges | +0.001 |
Token | Tower |
Token ID | 8765 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
fell | +0.388 |
ihad | +0.323 |
iaries | +0.322 |
ATES | +0.314 |
inges | +0.313 |
Neg logit contributions | |
rade | -0.482 |
Braun | -0.463 |
synchronized | -0.453 |
Larson | -0.451 |
prolifer | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
fell | +0.073 |
ihad | +0.063 |
iaries | +0.063 |
inges | +0.061 |
ATES | +0.061 |
Neg logit contributions | |
rade | -0.053 |
Braun | -0.050 |
synchronized | -0.049 |
Larson | -0.049 |
prolifer | -0.048 |
Token | which |
Token ID | 543 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
fell | +0.010 |
ihad | +0.008 |
iaries | +0.008 |
ATES | +0.008 |
inges | +0.008 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.006 |
lear | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
rade | +0.032 |
Braun | +0.030 |
synchronized | +0.029 |
lear | +0.029 |
Larson | +0.029 |
Neg logit contributions | |
fell | -0.043 |
ihad | -0.037 |
iaries | -0.037 |
inges | -0.036 |
ATES | -0.036 |
Token | London |
Token ID | 3576 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
fell | +0.066 |
ihad | +0.057 |
iaries | +0.057 |
inges | +0.056 |
ATES | +0.056 |
Neg logit contributions | |
rade | -0.046 |
Braun | -0.044 |
synchronized | -0.042 |
Larson | -0.042 |
lear | -0.042 |
Token | assessment |
Token ID | 8922 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
rade | +0.048 |
Braun | +0.045 |
synchronized | +0.044 |
Larson | +0.044 |
lear | +0.044 |
Neg logit contributions | |
fell | -0.059 |
ihad | -0.050 |
iaries | -0.050 |
inges | -0.049 |
ATES | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.012 |
iaries | +0.012 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.013 |
lear | -0.013 |
Larson | -0.013 |
Token | slavery |
Token ID | 13503 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
fell | +0.026 |
ihad | +0.022 |
iaries | +0.022 |
ATES | +0.021 |
inges | +0.021 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
lear | -0.024 |
Larson | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
fell | +0.072 |
ihad | +0.062 |
iaries | +0.061 |
inges | +0.060 |
ATES | +0.060 |
Neg logit contributions | |
rade | -0.055 |
Braun | -0.052 |
synchronized | -0.051 |
lear | -0.050 |
Larson | -0.050 |
Token | Advoc |
Token ID | 37866 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
fell | +0.005 |
ihad | +0.005 |
iaries | +0.004 |
ATES | +0.004 |
inges | +0.004 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
synchronized | -0.005 |
prolifer | -0.004 |
Larson | -0.004 |
Token | ates |
Token ID | 689 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
rade | +0.029 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
prolifer | +0.028 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.007 |
iaries | -0.007 |
inges | -0.007 |
ATES | -0.007 |
Token | struggled |
Token ID | 11615 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
fell | +0.439 |
ihad | +0.376 |
iaries | +0.376 |
inges | +0.367 |
ATES | +0.366 |
Neg logit contributions | |
rade | -0.359 |
Braun | -0.338 |
synchronized | -0.330 |
Larson | -0.327 |
lear | -0.327 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
fell | +0.124 |
ihad | +0.107 |
iaries | +0.106 |
inges | +0.104 |
ATES | +0.104 |
Neg logit contributions | |
rade | -0.103 |
Braun | -0.098 |
synchronized | -0.096 |
Larson | -0.095 |
lear | -0.095 |
Token | overcome |
Token ID | 10980 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
fell | +0.024 |
iaries | +0.020 |
ihad | +0.020 |
ATES | +0.020 |
inges | +0.020 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
Larson | -0.018 |
lear | -0.018 |
Token | fierce |
Token ID | 14800 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.006 |
iaries | +0.006 |
inges | +0.006 |
ATES | +0.006 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
lear | -0.006 |
Larson | -0.006 |
Token | opposition |
Token ID | 5471 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
rade | +0.045 |
Braun | +0.043 |
synchronized | +0.042 |
lear | +0.042 |
Larson | +0.042 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.032 |
iaries | -0.032 |
inges | -0.031 |
ATES | -0.031 |
Token | T |
Token ID | 309 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.016 |
synchronized | +0.016 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.016 |
iaries | -0.016 |
ATES | -0.016 |
inges | -0.016 |
Token | OC |
Token ID | 4503 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
Larson | +0.016 |
prolifer | +0.016 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.008 |
ATES | -0.008 |
Token | IN |
Token ID | 3268 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
fell | +0.060 |
ihad | +0.050 |
iaries | +0.050 |
ATES | +0.049 |
inges | +0.048 |
Neg logit contributions | |
rade | -0.070 |
Braun | -0.067 |
synchronized | -0.066 |
Larson | -0.065 |
prolifer | -0.065 |
Token | IT |
Token ID | 2043 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
fell | +0.009 |
ihad | +0.007 |
iaries | +0.007 |
inges | +0.007 |
ATES | +0.007 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
rade | +0.093 |
Braun | +0.089 |
synchronized | +0.088 |
Larson | +0.087 |
prolifer | +0.087 |
Neg logit contributions | |
fell | -0.091 |
iaries | -0.077 |
ihad | -0.077 |
inges | -0.076 |
ATES | -0.074 |
Token | ATES |
Token ID | 29462 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
rade | +0.040 |
Braun | +0.038 |
synchronized | +0.038 |
Larson | +0.038 |
prolifer | +0.037 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.015 |
iaries | -0.015 |
inges | -0.014 |
ATES | -0.013 |
Token | D |
Token ID | 360 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
fell | +0.357 |
ihad | +0.301 |
iaries | +0.300 |
ATES | +0.295 |
inges | +0.293 |
Neg logit contributions | |
rade | -0.357 |
Braun | -0.341 |
synchronized | -0.336 |
prolifer | -0.332 |
Larson | -0.332 |
Token | UST |
Token ID | 7759 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.010 |
iaries | +0.010 |
inges | +0.010 |
ATES | +0.010 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.021 |
synchronized | -0.020 |
Larson | -0.020 |
oulder | -0.020 |
Token | W |
Token ID | 54 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
fell | +0.178 |
ihad | +0.152 |
iaries | +0.150 |
ATES | +0.150 |
inges | +0.148 |
Neg logit contributions | |
rade | -0.146 |
Braun | -0.140 |
synchronized | -0.137 |
prolifer | -0.136 |
Larson | -0.135 |
Token | UN |
Token ID | 4944 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
rade | +0.101 |
Braun | +0.098 |
synchronized | +0.096 |
Larson | +0.095 |
prolifer | +0.095 |
Neg logit contributions | |
fell | -0.073 |
iaries | -0.060 |
ihad | -0.060 |
inges | -0.058 |
ATES | -0.058 |
Token | FOR |
Token ID | 7473 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.041 |
iaries | +0.040 |
ATES | +0.040 |
inges | +0.039 |
Neg logit contributions | |
rade | -0.045 |
Braun | -0.043 |
synchronized | -0.042 |
prolifer | -0.042 |
Larson | -0.042 |
Token | determining |
Token ID | 13213 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
rade | +0.027 |
Braun | +0.026 |
synchronized | +0.025 |
Larson | +0.025 |
lear | +0.025 |
Neg logit contributions | |
fell | -0.032 |
ihad | -0.028 |
iaries | -0.028 |
ATES | -0.027 |
inges | -0.027 |
Token | environmental |
Token ID | 6142 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
fell | +0.052 |
ihad | +0.045 |
iaries | +0.045 |
ATES | +0.045 |
inges | +0.044 |
Neg logit contributions | |
rade | -0.033 |
Braun | -0.031 |
synchronized | -0.030 |
Larson | -0.030 |
lear | -0.030 |
Token | racism |
Token ID | 10713 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
rade | +0.051 |
Braun | +0.048 |
synchronized | +0.047 |
Larson | +0.047 |
prolifer | +0.046 |
Neg logit contributions | |
fell | -0.067 |
ihad | -0.058 |
iaries | -0.058 |
ATES | -0.057 |
inges | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
fell | +0.050 |
ihad | +0.043 |
iaries | +0.043 |
inges | +0.042 |
ATES | +0.042 |
Neg logit contributions | |
rade | -0.037 |
Braun | -0.035 |
synchronized | -0.034 |
lear | -0.034 |
Larson | -0.034 |
Token | Advoc |
Token ID | 37866 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.008 |
iaries | -0.008 |
inges | -0.008 |
ATES | -0.008 |
Token | ates |
Token ID | 689 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
rade | +0.085 |
Braun | +0.083 |
synchronized | +0.082 |
Larson | +0.081 |
prolifer | +0.081 |
Neg logit contributions | |
fell | -0.030 |
ihad | -0.021 |
iaries | -0.021 |
ATES | -0.020 |
inges | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
fell | +0.404 |
ihad | +0.349 |
iaries | +0.347 |
inges | +0.339 |
ATES | +0.339 |
Neg logit contributions | |
rade | -0.307 |
Braun | -0.290 |
synchronized | -0.283 |
Larson | -0.279 |
lear | -0.279 |
Token | recipient |
Token ID | 17800 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.014 |
prolifer | -0.014 |
Token | agencies |
Token ID | 5942 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
fell | +0.081 |
ihad | +0.069 |
iaries | +0.068 |
inges | +0.067 |
ATES | +0.067 |
Neg logit contributions | |
rade | -0.078 |
Braun | -0.075 |
synchronized | -0.074 |
prolifer | -0.073 |
Larson | -0.073 |
Token | alike |
Token ID | 12936 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
fell | +0.044 |
ihad | +0.038 |
iaries | +0.038 |
ATES | +0.037 |
inges | +0.037 |
Neg logit contributions | |
rade | -0.036 |
Braun | -0.034 |
synchronized | -0.033 |
Larson | -0.033 |
lear | -0.032 |
Token | have |
Token ID | 423 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.010 |
Larson | +0.010 |
synchronized | +0.010 |
lear | +0.010 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.011 |
iaries | -0.011 |
inges | -0.011 |
ATES | -0.011 |
Token | get |
Token ID | 651 |
Feature activation | -8.67e-04 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.001 |
ihad | -0.001 |
iaries | -0.001 |
ATES | -0.001 |
inges | -0.001 |
Token | my |
Token ID | 616 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.000 |
Neg logit contributions | |
fell | -0.001 |
iaries | -0.001 |
ihad | -0.001 |
inges | -0.001 |
ATES | -0.001 |
Token | here |
Token ID | 994 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
fell | +0.074 |
iaries | +0.063 |
ihad | +0.062 |
inges | +0.061 |
ATES | +0.061 |
Neg logit contributions | |
rade | -0.072 |
Braun | -0.069 |
synchronized | -0.068 |
Larson | -0.067 |
prolifer | -0.067 |
Token | IM |
Token ID | 8959 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.011 |
synchronized | +0.011 |
Larson | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.015 |
ihad | -0.013 |
iaries | -0.013 |
inges | -0.012 |
ATES | -0.012 |
Token | M |
Token ID | 44 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.011 |
synchronized | +0.011 |
Larson | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.012 |
ihad | -0.011 |
iaries | -0.010 |
ATES | -0.010 |
inges | -0.010 |
Token | IG |
Token ID | 3528 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
rade | +0.028 |
Braun | +0.027 |
synchronized | +0.026 |
Larson | +0.026 |
prolifer | +0.026 |
Neg logit contributions | |
fell | -0.015 |
ihad | -0.012 |
iaries | -0.012 |
inges | -0.011 |
ATES | -0.011 |
Token | RANT |
Token ID | 32506 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
fell | +0.479 |
ihad | +0.424 |
ATES | +0.421 |
iaries | +0.420 |
inges | +0.414 |
Neg logit contributions | |
rade | -0.227 |
Braun | -0.215 |
synchronized | -0.207 |
prolifer | -0.205 |
Larson | -0.204 |
Token | food |
Token ID | 2057 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
rade | +0.295 |
Braun | +0.281 |
synchronized | +0.275 |
Larson | +0.273 |
prolifer | +0.272 |
Neg logit contributions | |
fell | -0.320 |
iaries | -0.274 |
ihad | -0.272 |
inges | -0.267 |
ATES | -0.264 |
Token | from |
Token ID | 422 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.014 |
synchronized | +0.014 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.017 |
ihad | -0.015 |
iaries | -0.015 |
inges | -0.014 |
ATES | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
fell | +0.046 |
ihad | +0.040 |
iaries | +0.040 |
inges | +0.039 |
ATES | +0.039 |
Neg logit contributions | |
rade | -0.041 |
Braun | -0.039 |
synchronized | -0.038 |
Larson | -0.038 |
prolifer | -0.037 |
Token | good |
Token ID | 922 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
fell | +0.010 |
ihad | +0.008 |
iaries | +0.008 |
ATES | +0.008 |
inges | +0.008 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | Canada |
Token ID | 3340 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
fell | +0.023 |
ihad | +0.020 |
iaries | +0.020 |
ATES | +0.019 |
inges | +0.019 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.020 |
synchronized | -0.020 |
Larson | -0.020 |
prolifer | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
fell | +0.041 |
ihad | +0.035 |
iaries | +0.035 |
ATES | +0.034 |
inges | +0.034 |
Neg logit contributions | |
rade | -0.030 |
Braun | -0.028 |
synchronized | -0.027 |
Larson | -0.027 |
lear | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
rade | +0.043 |
Braun | +0.041 |
synchronized | +0.040 |
Larson | +0.040 |
prolifer | +0.040 |
Neg logit contributions | |
fell | -0.049 |
ihad | -0.042 |
iaries | -0.042 |
ATES | -0.041 |
inges | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
rade | +0.035 |
Braun | +0.033 |
synchronized | +0.032 |
Larson | +0.032 |
prolifer | +0.032 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.034 |
iaries | -0.034 |
inges | -0.033 |
ATES | -0.033 |
Token | App |
Token ID | 4677 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
rade | +0.032 |
Braun | +0.030 |
synchronized | +0.030 |
prolifer | +0.029 |
Larson | +0.029 |
Neg logit contributions | |
fell | -0.034 |
ihad | -0.029 |
iaries | -0.028 |
ATES | -0.028 |
inges | -0.028 |
Token | alach |
Token ID | 33786 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
fell | +0.042 |
ihad | +0.034 |
iaries | +0.034 |
inges | +0.033 |
ATES | +0.033 |
Neg logit contributions | |
rade | -0.060 |
Braun | -0.058 |
synchronized | -0.057 |
Larson | -0.057 |
prolifer | -0.057 |
Token | ia |
Token ID | 544 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
fell | +0.342 |
ihad | +0.288 |
iaries | +0.287 |
ATES | +0.281 |
inges | +0.281 |
Neg logit contributions | |
rade | -0.345 |
Braun | -0.330 |
synchronized | -0.323 |
Larson | -0.321 |
prolifer | -0.320 |
Token | and |
Token ID | 290 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
fell | +0.045 |
ihad | +0.039 |
iaries | +0.039 |
inges | +0.038 |
ATES | +0.038 |
Neg logit contributions | |
rade | -0.035 |
Braun | -0.033 |
synchronized | -0.033 |
Larson | -0.032 |
prolifer | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
fell | +0.014 |
ihad | +0.012 |
iaries | +0.012 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.011 |
synchronized | -0.011 |
Larson | -0.011 |
prolifer | -0.011 |
Token | U |
Token ID | 471 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
fell | +0.037 |
ihad | +0.031 |
iaries | +0.031 |
inges | +0.031 |
ATES | +0.031 |
Neg logit contributions | |
rade | -0.030 |
Braun | -0.029 |
synchronized | -0.028 |
Larson | -0.028 |
lear | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
rade | +0.052 |
Braun | +0.049 |
synchronized | +0.048 |
Larson | +0.047 |
prolifer | +0.047 |
Neg logit contributions | |
fell | -0.073 |
ihad | -0.063 |
iaries | -0.063 |
inges | -0.062 |
ATES | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
prolifer | +0.016 |
oulder | +0.016 |
Neg logit contributions | |
fell | -0.017 |
ihad | -0.015 |
iaries | -0.014 |
inges | -0.014 |
ATES | -0.014 |
Token | wave |
Token ID | 19204 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
fell | +0.004 |
ihad | +0.003 |
iaries | +0.003 |
inges | +0.003 |
ATES | +0.003 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.004 |
synchronized | -0.004 |
prolifer | -0.004 |
Larson | -0.004 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
rade | +0.041 |
Braun | +0.037 |
oulder | +0.037 |
hiro | +0.037 |
lear | +0.037 |
Neg logit contributions | |
fell | -0.056 |
inges | -0.048 |
ihad | -0.048 |
iaries | -0.047 |
define | -0.047 |
Token | ( |
Token ID | 357 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rade | +0.044 |
Braun | +0.041 |
synchronized | +0.040 |
lear | +0.039 |
Larson | +0.039 |
Neg logit contributions | |
fell | -0.068 |
ihad | -0.059 |
iaries | -0.059 |
inges | -0.058 |
ATES | -0.058 |
Token | L |
Token ID | 43 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
rade | +0.072 |
Braun | +0.069 |
synchronized | +0.068 |
Larson | +0.067 |
prolifer | +0.067 |
Neg logit contributions | |
fell | -0.071 |
ihad | -0.060 |
iaries | -0.060 |
inges | -0.058 |
ATES | -0.058 |
Token | IG |
Token ID | 3528 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
fell | +0.020 |
iaries | +0.013 |
ihad | +0.012 |
ATES | +0.012 |
inges | +0.012 |
Neg logit contributions | |
rade | -0.070 |
Braun | -0.068 |
synchronized | -0.067 |
oulder | -0.067 |
Larson | -0.066 |
Token | O |
Token ID | 46 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
fell | +0.350 |
iaries | +0.302 |
ihad | +0.299 |
inges | +0.293 |
ATES | +0.289 |
Neg logit contributions | |
rade | -0.321 |
Braun | -0.308 |
synchronized | -0.299 |
oulder | -0.298 |
Larson | -0.297 |
Token | ) |
Token ID | 8 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
fell | +0.046 |
ihad | +0.039 |
iaries | +0.039 |
ATES | +0.038 |
inges | +0.038 |
Neg logit contributions | |
rade | -0.043 |
Braun | -0.041 |
synchronized | -0.041 |
Larson | -0.040 |
prolifer | -0.040 |
Token | — |
Token ID | 851 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
inges | +0.007 |
ATES | +0.007 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.005 |
lear | -0.005 |
Larson | -0.005 |
Token | comprising |
Token ID | 27918 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rade | +0.022 |
Braun | +0.021 |
synchronized | +0.021 |
Larson | +0.020 |
prolifer | +0.020 |
Neg logit contributions | |
fell | -0.028 |
ihad | -0.024 |
iaries | -0.024 |
ATES | -0.024 |
inges | -0.024 |
Token | sites |
Token ID | 5043 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
fell | +0.094 |
ihad | +0.081 |
iaries | +0.081 |
inges | +0.079 |
ATES | +0.079 |
Neg logit contributions | |
rade | -0.079 |
Braun | -0.075 |
synchronized | -0.074 |
Larson | -0.073 |
prolifer | -0.073 |
Token | fake |
Token ID | 8390 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.018 |
iaries | +0.018 |
inges | +0.017 |
ATES | +0.017 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
synchronized | -0.015 |
Larson | -0.014 |
lear | -0.014 |
Token | positive |
Token ID | 3967 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
rade | +0.068 |
Braun | +0.065 |
synchronized | +0.063 |
Larson | +0.063 |
prolifer | +0.062 |
Neg logit contributions | |
fell | -0.082 |
ihad | -0.071 |
iaries | -0.071 |
inges | -0.069 |
ATES | -0.069 |
Token | signals |
Token ID | 10425 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
lear | +0.003 |
oulder | +0.003 |
Neg logit contributions | |
fell | -0.005 |
iaries | -0.004 |
ihad | -0.004 |
inges | -0.004 |
ATES | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.011 |
lear | +0.011 |
synchronized | +0.011 |
oulder | +0.011 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.017 |
iaries | -0.017 |
inges | -0.017 |
ATES | -0.017 |
Token | L |
Token ID | 406 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rade | +0.089 |
Braun | +0.085 |
synchronized | +0.082 |
lear | +0.082 |
oulder | +0.082 |
Neg logit contributions | |
fell | -0.111 |
ihad | -0.096 |
iaries | -0.095 |
inges | -0.094 |
ATES | -0.093 |
Token | IG |
Token ID | 3528 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
fell | +0.031 |
ihad | +0.019 |
iaries | +0.019 |
inges | +0.017 |
ATES | +0.017 |
Neg logit contributions | |
rade | -0.126 |
Braun | -0.122 |
synchronized | -0.121 |
Larson | -0.120 |
prolifer | -0.120 |
Token | O |
Token ID | 46 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
fell | +0.327 |
ihad | +0.274 |
iaries | +0.272 |
ATES | +0.268 |
inges | +0.265 |
Neg logit contributions | |
rade | -0.345 |
Braun | -0.331 |
synchronized | -0.325 |
prolifer | -0.323 |
Larson | -0.322 |
Token | data |
Token ID | 1366 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
fell | +0.044 |
iaries | +0.038 |
ihad | +0.038 |
inges | +0.037 |
ATES | +0.037 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.032 |
synchronized | -0.031 |
Larson | -0.031 |
prolifer | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
fell | +0.016 |
iaries | +0.013 |
ihad | +0.013 |
ATES | +0.013 |
inges | +0.013 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.011 |
synchronized | -0.011 |
lear | -0.011 |
Larson | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
prolifer | +0.002 |
lear | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
ATES | -0.002 |
inges | -0.002 |
Token | aim |
Token ID | 4031 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
fell | +0.049 |
ihad | +0.042 |
iaries | +0.042 |
inges | +0.041 |
ATES | +0.041 |
Neg logit contributions | |
rade | -0.039 |
Braun | -0.037 |
synchronized | -0.035 |
lear | -0.035 |
oulder | -0.035 |
Token | s |
Token ID | 82 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
rade | +0.000 |
Braun | +0.000 |
synchronized | +0.000 |
Larson | +0.000 |
prolifer | +0.000 |
Neg logit contributions | |
fell | -0.000 |
ihad | -0.000 |
iaries | -0.000 |
inges | -0.000 |
ATES | -0.000 |
Token | protests |
Token ID | 8536 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
fell | +0.029 |
ihad | +0.024 |
iaries | +0.024 |
inges | +0.024 |
ATES | +0.024 |
Neg logit contributions | |
rade | -0.031 |
Braun | -0.030 |
synchronized | -0.029 |
Larson | -0.029 |
lear | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
fell | +0.117 |
ihad | +0.101 |
iaries | +0.101 |
inges | +0.099 |
ATES | +0.099 |
Neg logit contributions | |
rade | -0.082 |
Braun | -0.078 |
synchronized | -0.076 |
Larson | -0.075 |
lear | -0.075 |
Token | relative |
Token ID | 3585 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
rade | +0.024 |
Braun | +0.023 |
synchronized | +0.023 |
Larson | +0.023 |
lear | +0.022 |
Neg logit contributions | |
fell | -0.027 |
ihad | -0.023 |
iaries | -0.022 |
inges | -0.022 |
ATES | -0.022 |
Token | len |
Token ID | 18896 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
fell | +0.018 |
ihad | +0.016 |
iaries | +0.016 |
inges | +0.015 |
ATES | +0.015 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.015 |
synchronized | -0.014 |
Larson | -0.014 |
lear | -0.014 |
Token | iency |
Token ID | 6160 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.000 |
iaries | +0.000 |
ATES | +0.000 |
inges | +0.000 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
lear | -0.002 |
prolifer | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
fell | +0.380 |
ihad | +0.327 |
iaries | +0.322 |
inges | +0.319 |
ATES | +0.318 |
Neg logit contributions | |
rade | -0.289 |
Braun | -0.273 |
synchronized | -0.268 |
lear | -0.267 |
Larson | -0.266 |
Token | Although |
Token ID | 4900 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
fell | +0.023 |
ihad | +0.020 |
iaries | +0.020 |
inges | +0.019 |
ATES | +0.019 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.020 |
synchronized | -0.020 |
Larson | -0.020 |
prolifer | -0.020 |
Token | tear |
Token ID | 11626 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
Larson | +0.016 |
prolifer | +0.016 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.016 |
iaries | -0.016 |
inges | -0.016 |
ATES | -0.016 |
Token | gas |
Token ID | 3623 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
fell | +0.138 |
iaries | +0.122 |
ihad | +0.122 |
inges | +0.121 |
ATES | +0.119 |
Neg logit contributions | |
rade | -0.055 |
Braun | -0.053 |
Larson | -0.050 |
synchronized | -0.049 |
lear | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
rade | +0.187 |
Braun | +0.177 |
synchronized | +0.173 |
oulder | +0.172 |
Larson | +0.172 |
Neg logit contributions | |
fell | -0.227 |
iaries | -0.194 |
ihad | -0.193 |
inges | -0.190 |
ATES | -0.189 |
Token | the |
Token ID | 262 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.006 |
synchronized | +0.006 |
lear | +0.006 |
Larson | +0.006 |
Neg logit contributions | |
fell | -0.008 |
ihad | -0.007 |
iaries | -0.007 |
ATES | -0.007 |
inges | -0.007 |
Token | people |
Token ID | 661 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
inges | +0.013 |
ATES | +0.013 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.013 |
synchronized | -0.012 |
Larson | -0.012 |
lear | -0.012 |
Token | scoring |
Token ID | 9689 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
fell | +0.065 |
ihad | +0.056 |
iaries | +0.056 |
inges | +0.054 |
ATES | +0.054 |
Neg logit contributions | |
rade | -0.052 |
Braun | -0.050 |
synchronized | -0.049 |
Larson | -0.048 |
oulder | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
fell | +0.109 |
ihad | +0.093 |
iaries | +0.093 |
ATES | +0.091 |
inges | +0.091 |
Neg logit contributions | |
rade | -0.090 |
Braun | -0.086 |
synchronized | -0.084 |
Larson | -0.083 |
prolifer | -0.083 |
Token | carc |
Token ID | 36756 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
fell | +0.006 |
ihad | +0.005 |
iaries | +0.005 |
inges | +0.005 |
ATES | +0.005 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
synchronized | -0.005 |
Larson | -0.005 |
prolifer | -0.004 |
Token | asses |
Token ID | 13978 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
rade | +0.152 |
Braun | +0.148 |
synchronized | +0.147 |
Larson | +0.146 |
prolifer | +0.146 |
Neg logit contributions | |
fell | -0.047 |
ihad | -0.032 |
iaries | -0.032 |
inges | -0.030 |
ATES | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
fell | +0.370 |
iaries | +0.318 |
ihad | +0.317 |
inges | +0.310 |
ATES | +0.309 |
Neg logit contributions | |
rade | -0.281 |
Braun | -0.267 |
Larson | -0.259 |
synchronized | -0.259 |
oulder | -0.257 |
Token | employees |
Token ID | 4409 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
rade | +0.027 |
Braun | +0.026 |
synchronized | +0.025 |
Larson | +0.025 |
prolifer | +0.025 |
Neg logit contributions | |
fell | -0.036 |
ihad | -0.031 |
iaries | -0.031 |
ATES | -0.031 |
inges | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
fell | +0.017 |
ihad | +0.015 |
iaries | +0.014 |
inges | +0.014 |
ATES | +0.014 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.013 |
Larson | -0.013 |
lear | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
fell | +0.021 |
ihad | +0.018 |
iaries | +0.018 |
inges | +0.018 |
ATES | +0.018 |
Neg logit contributions | |
rade | -0.018 |
Braun | -0.017 |
synchronized | -0.017 |
Larson | -0.017 |
prolifer | -0.016 |
Token | processors |
Token ID | 20399 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
lear | +0.001 |
Neg logit contributions | |
fell | -0.001 |
ihad | -0.001 |
iaries | -0.001 |
inges | -0.001 |
ATES | -0.001 |
Token | upgrade |
Token ID | 8515 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
fell | +0.005 |
ihad | +0.004 |
iaries | +0.004 |
inges | +0.004 |
ATES | +0.004 |
Neg logit contributions | |
rade | -0.004 |
Braun | -0.004 |
synchronized | -0.003 |
Larson | -0.003 |
lear | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
rade | +0.085 |
Braun | +0.081 |
synchronized | +0.079 |
Larson | +0.078 |
lear | +0.078 |
Neg logit contributions | |
fell | -0.113 |
ihad | -0.098 |
iaries | -0.098 |
ATES | -0.096 |
inges | -0.096 |
Token | called |
Token ID | 1444 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
ATES | +0.007 |
inges | +0.007 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.006 |
prolifer | -0.006 |
Token | Advanced |
Token ID | 13435 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
fell | +0.144 |
ihad | +0.123 |
iaries | +0.122 |
inges | +0.120 |
ATES | +0.120 |
Neg logit contributions | |
rade | -0.125 |
Braun | -0.119 |
synchronized | -0.116 |
Larson | -0.115 |
prolifer | -0.115 |
Token | L |
Token ID | 406 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
fell | +0.023 |
ihad | +0.020 |
iaries | +0.020 |
inges | +0.019 |
ATES | +0.019 |
Neg logit contributions | |
rade | -0.020 |
Braun | -0.019 |
synchronized | -0.018 |
Larson | -0.018 |
prolifer | -0.018 |
Token | IG |
Token ID | 3528 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
fell | +0.033 |
ihad | +0.022 |
iaries | +0.021 |
inges | +0.020 |
ATES | +0.020 |
Neg logit contributions | |
rade | -0.115 |
Braun | -0.112 |
synchronized | -0.110 |
prolifer | -0.109 |
Larson | -0.109 |
Token | O |
Token ID | 46 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
fell | +0.313 |
ihad | +0.264 |
iaries | +0.262 |
ATES | +0.257 |
inges | +0.256 |
Neg logit contributions | |
rade | -0.330 |
Braun | -0.317 |
synchronized | -0.311 |
Larson | -0.308 |
prolifer | -0.308 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
fell | +0.042 |
ihad | +0.036 |
iaries | +0.036 |
inges | +0.035 |
ATES | +0.035 |
Neg logit contributions | |
rade | -0.033 |
Braun | -0.031 |
synchronized | -0.031 |
Larson | -0.030 |
prolifer | -0.030 |
Token | is |
Token ID | 318 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
fell | +0.019 |
ihad | +0.017 |
iaries | +0.017 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.010 |
synchronized | -0.009 |
Larson | -0.009 |
lear | -0.009 |
Token | complete |
Token ID | 1844 |
Feature activation | -5.17e-04 |
Pos logit contributions | |
rade | +0.053 |
Braun | +0.050 |
synchronized | +0.049 |
Larson | +0.049 |
lear | +0.048 |
Neg logit contributions | |
fell | -0.080 |
ihad | -0.069 |
iaries | -0.069 |
ATES | -0.068 |
inges | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
rade | +0.000 |
Braun | +0.000 |
synchronized | +0.000 |
Larson | +0.000 |
lear | +0.000 |
Neg logit contributions | |
fell | -0.000 |
ihad | -0.000 |
iaries | -0.000 |
inges | -0.000 |
ATES | -0.000 |
Token | Click |
Token ID | 6914 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
fell | +0.120 |
ihad | +0.103 |
iaries | +0.102 |
ATES | +0.100 |
inges | +0.100 |
Neg logit contributions | |
rade | -0.108 |
Braun | -0.103 |
synchronized | -0.101 |
Larson | -0.100 |
prolifer | -0.100 |
Token | here |
Token ID | 994 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
fell | +0.043 |
ihad | +0.038 |
iaries | +0.038 |
inges | +0.037 |
ATES | +0.037 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.031 |
synchronized | -0.030 |
Larson | -0.030 |
prolifer | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
rade | +0.008 |
Braun | +0.007 |
synchronized | +0.007 |
lear | +0.007 |
Larson | +0.007 |
Neg logit contributions | |
fell | -0.009 |
ihad | -0.008 |
iaries | -0.008 |
ATES | -0.008 |
inges | -0.008 |
Token | help |
Token ID | 1037 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
fell | +0.040 |
ihad | +0.035 |
iaries | +0.035 |
ATES | +0.034 |
inges | +0.034 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.024 |
synchronized | -0.023 |
Larson | -0.023 |
oulder | -0.023 |
Token | prevent |
Token ID | 2948 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rade | +0.034 |
Braun | +0.032 |
synchronized | +0.032 |
Larson | +0.031 |
lear | +0.031 |
Neg logit contributions | |
fell | -0.043 |
ihad | -0.037 |
iaries | -0.037 |
ATES | -0.036 |
inges | -0.036 |
Token | disenfranch |
Token ID | 41307 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
fell | +0.080 |
ihad | +0.068 |
iaries | +0.068 |
ATES | +0.067 |
inges | +0.066 |
Neg logit contributions | |
rade | -0.070 |
Braun | -0.067 |
synchronized | -0.065 |
lear | -0.065 |
Larson | -0.065 |
Token | is |
Token ID | 271 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
fell | +0.434 |
ihad | +0.382 |
iaries | +0.382 |
inges | +0.376 |
ATES | +0.373 |
Neg logit contributions | |
rade | -0.210 |
Braun | -0.197 |
synchronized | -0.191 |
prolifer | -0.189 |
Larson | -0.189 |
Token | ment |
Token ID | 434 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
rade | +0.098 |
Braun | +0.093 |
synchronized | +0.092 |
Larson | +0.092 |
prolifer | +0.091 |
Neg logit contributions | |
fell | -0.106 |
ihad | -0.090 |
iaries | -0.090 |
inges | -0.088 |
ATES | -0.087 |
Token | in |
Token ID | 287 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
rade | +0.066 |
Braun | +0.062 |
synchronized | +0.061 |
Larson | +0.060 |
lear | +0.060 |
Neg logit contributions | |
fell | -0.087 |
ihad | -0.075 |
iaries | -0.074 |
ATES | -0.073 |
inges | -0.073 |
Token | this |
Token ID | 428 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
fell | +0.003 |
ihad | +0.002 |
iaries | +0.002 |
ATES | +0.002 |
inges | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
lear | -0.002 |
Token | year |
Token ID | 614 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
rade | +0.004 |
Braun | +0.004 |
synchronized | +0.004 |
Larson | +0.004 |
lear | +0.004 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.004 |
iaries | -0.004 |
ATES | -0.004 |
inges | -0.004 |
Token | pp |
Token ID | 381 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
rade | +0.079 |
Braun | +0.076 |
synchronized | +0.074 |
Larson | +0.073 |
prolifer | +0.073 |
Neg logit contributions | |
fell | -0.100 |
ihad | -0.086 |
iaries | -0.086 |
inges | -0.084 |
ATES | -0.084 |
Token | ling |
Token ID | 1359 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
fell | +0.086 |
ihad | +0.075 |
iaries | +0.075 |
inges | +0.073 |
ATES | +0.073 |
Neg logit contributions | |
rade | -0.056 |
Braun | -0.053 |
synchronized | -0.052 |
Larson | -0.051 |
prolifer | -0.051 |
Token | hook |
Token ID | 8011 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
rade | +0.036 |
Braun | +0.034 |
synchronized | +0.033 |
Larson | +0.033 |
prolifer | +0.033 |
Neg logit contributions | |
fell | -0.043 |
ihad | -0.037 |
iaries | -0.037 |
inges | -0.036 |
ATES | -0.036 |
Token | X |
Token ID | 1395 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
fell | +0.053 |
ihad | +0.046 |
iaries | +0.046 |
inges | +0.045 |
ATES | +0.045 |
Neg logit contributions | |
rade | -0.041 |
Braun | -0.039 |
synchronized | -0.039 |
Larson | -0.038 |
prolifer | -0.038 |
Token | BL |
Token ID | 9148 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
fell | +0.098 |
ihad | +0.082 |
iaries | +0.081 |
ATES | +0.079 |
inges | +0.079 |
Neg logit contributions | |
rade | -0.107 |
Braun | -0.103 |
synchronized | -0.101 |
Larson | -0.100 |
prolifer | -0.100 |
Token | IG |
Token ID | 3528 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
fell | +0.025 |
ihad | +0.017 |
iaries | +0.017 |
inges | +0.016 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.069 |
Braun | -0.067 |
synchronized | -0.066 |
Larson | -0.066 |
prolifer | -0.066 |
Token | except |
Token ID | 2845 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
fell | +0.347 |
ihad | +0.297 |
iaries | +0.296 |
ATES | +0.290 |
inges | +0.290 |
Neg logit contributions | |
rade | -0.293 |
Braun | -0.279 |
synchronized | -0.273 |
Larson | -0.271 |
prolifer | -0.270 |
Token | you |
Token ID | 345 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
rade | +0.083 |
Braun | +0.079 |
synchronized | +0.077 |
Larson | +0.076 |
prolifer | +0.076 |
Neg logit contributions | |
fell | -0.111 |
ihad | -0.096 |
iaries | -0.096 |
ATES | -0.094 |
inges | -0.094 |
Token | 're |
Token ID | 821 |
Feature activation | -7.93e-03 |
Pos logit contributions | |
fell | +0.045 |
ihad | +0.038 |
iaries | +0.038 |
inges | +0.038 |
ATES | +0.038 |
Neg logit contributions | |
rade | -0.038 |
Braun | -0.036 |
synchronized | -0.035 |
Larson | -0.035 |
prolifer | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.004 |
synchronized | +0.004 |
Larson | +0.004 |
prolifer | +0.004 |
Neg logit contributions | |
fell | -0.006 |
ihad | -0.005 |
iaries | -0.005 |
inges | -0.005 |
ATES | -0.005 |
Token | lizard |
Token ID | 42406 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | who |
Token ID | 508 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
rade | +0.055 |
Braun | +0.052 |
synchronized | +0.051 |
Larson | +0.051 |
lear | +0.050 |
Neg logit contributions | |
fell | -0.076 |
ihad | -0.065 |
iaries | -0.065 |
inges | -0.064 |
ATES | -0.064 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
fell | +0.039 |
ihad | +0.033 |
iaries | +0.033 |
inges | +0.033 |
ATES | +0.033 |
Neg logit contributions | |
rade | -0.028 |
Braun | -0.027 |
synchronized | -0.026 |
Larson | -0.026 |
oulder | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
fell | +0.080 |
ihad | +0.069 |
iaries | +0.069 |
inges | +0.067 |
ATES | +0.067 |
Neg logit contributions | |
rade | -0.069 |
Braun | -0.066 |
synchronized | -0.065 |
Larson | -0.064 |
prolifer | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
fell | +0.021 |
ihad | +0.018 |
iaries | +0.018 |
inges | +0.018 |
ATES | +0.018 |
Neg logit contributions | |
rade | -0.020 |
Braun | -0.019 |
synchronized | -0.019 |
Larson | -0.019 |
lear | -0.019 |
Token | fr |
Token ID | 1216 |
Feature activation | +5.33e-04 |
Pos logit contributions | |
fell | +0.051 |
ihad | +0.044 |
iaries | +0.044 |
inges | +0.043 |
ATES | +0.043 |
Neg logit contributions | |
rade | -0.045 |
Braun | -0.043 |
synchronized | -0.042 |
Larson | -0.042 |
lear | -0.042 |
Token | inges |
Token ID | 26792 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
fell | +0.000 |
ihad | +0.000 |
iaries | +0.000 |
ATES | +0.000 |
inges | +0.000 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
prolifer | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
fell | +0.346 |
ihad | +0.297 |
iaries | +0.294 |
inges | +0.290 |
ATES | +0.288 |
Neg logit contributions | |
rade | -0.288 |
Braun | -0.275 |
synchronized | -0.268 |
Larson | -0.266 |
lear | -0.266 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
fell | +0.045 |
ihad | +0.038 |
iaries | +0.038 |
inges | +0.037 |
ATES | +0.037 |
Neg logit contributions | |
rade | -0.042 |
Braun | -0.040 |
synchronized | -0.039 |
Larson | -0.039 |
lear | -0.039 |
Token | right |
Token ID | 826 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
fell | +0.035 |
ihad | +0.030 |
iaries | +0.030 |
inges | +0.029 |
ATES | +0.029 |
Neg logit contributions | |
rade | -0.030 |
Braun | -0.029 |
synchronized | -0.028 |
Larson | -0.028 |
prolifer | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
rade | +0.065 |
Braun | +0.062 |
synchronized | +0.061 |
Larson | +0.060 |
prolifer | +0.060 |
Neg logit contributions | |
fell | -0.082 |
ihad | -0.070 |
iaries | -0.070 |
inges | -0.069 |
ATES | -0.068 |
Token | How |
Token ID | 1374 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
fell | +0.042 |
ihad | +0.036 |
iaries | +0.036 |
ATES | +0.035 |
inges | +0.035 |
Neg logit contributions | |
rade | -0.036 |
Braun | -0.035 |
synchronized | -0.034 |
prolifer | -0.034 |
lear | -0.034 |
Token | � |
Token ID | 247 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
prolifer | +0.028 |
Neg logit contributions | |
fell | -0.034 |
ihad | -0.029 |
iaries | -0.029 |
inges | -0.029 |
ATES | -0.029 |
Token | t |
Token ID | 83 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
prolifer | +0.028 |
Neg logit contributions | |
fell | -0.027 |
ihad | -0.023 |
iaries | -0.023 |
inges | -0.022 |
ATES | -0.022 |
Token | really |
Token ID | 1107 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
fell | +0.005 |
ihad | +0.004 |
iaries | +0.004 |
ATES | +0.004 |
inges | +0.004 |
Neg logit contributions | |
rade | -0.003 |
Braun | -0.003 |
synchronized | -0.003 |
Larson | -0.003 |
oulder | -0.003 |
Token | have |
Token ID | 423 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.006 |
synchronized | +0.006 |
Larson | +0.006 |
oulder | +0.006 |
Neg logit contributions | |
fell | -0.009 |
iaries | -0.008 |
ihad | -0.008 |
inges | -0.008 |
ATES | -0.008 |
Token | any |
Token ID | 597 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
fell | +0.035 |
ihad | +0.030 |
iaries | +0.030 |
ATES | +0.029 |
inges | +0.029 |
Neg logit contributions | |
rade | -0.030 |
Braun | -0.029 |
synchronized | -0.028 |
Larson | -0.028 |
prolifer | -0.028 |
Token | vested |
Token ID | 32789 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
rade | +0.024 |
Braun | +0.023 |
synchronized | +0.022 |
Larson | +0.022 |
prolifer | +0.022 |
Neg logit contributions | |
fell | -0.030 |
ihad | -0.026 |
iaries | -0.025 |
ATES | -0.025 |
inges | -0.025 |
Token | interest |
Token ID | 1393 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
fell | +0.376 |
ihad | +0.327 |
iaries | +0.326 |
ATES | +0.320 |
inges | +0.320 |
Neg logit contributions | |
rade | -0.254 |
Braun | -0.241 |
synchronized | -0.235 |
Larson | -0.233 |
prolifer | -0.232 |
Token | in |
Token ID | 287 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
rade | +0.071 |
Braun | +0.067 |
synchronized | +0.066 |
Larson | +0.065 |
prolifer | +0.065 |
Neg logit contributions | |
fell | -0.095 |
ihad | -0.082 |
iaries | -0.082 |
inges | -0.080 |
ATES | -0.080 |
Token | doing |
Token ID | 1804 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.016 |
synchronized | +0.015 |
Larson | +0.015 |
lear | +0.015 |
Neg logit contributions | |
fell | -0.022 |
ihad | -0.019 |
iaries | -0.019 |
ATES | -0.019 |
inges | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
rade | +0.016 |
Braun | +0.015 |
synchronized | +0.015 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.020 |
ihad | -0.017 |
iaries | -0.017 |
ATES | -0.017 |
inges | -0.017 |
Token | sort |
Token ID | 3297 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
rade | +0.023 |
Braun | +0.022 |
synchronized | +0.021 |
Larson | +0.021 |
prolifer | +0.021 |
Neg logit contributions | |
fell | -0.024 |
ihad | -0.020 |
iaries | -0.020 |
inges | -0.020 |
ATES | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
inges | +0.001 |
ATES | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
prolifer | -0.001 |
Token | THE |
Token ID | 10970 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
fell | +0.007 |
ihad | +0.006 |
iaries | +0.006 |
ATES | +0.005 |
inges | +0.005 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.006 |
synchronized | -0.006 |
prolifer | -0.006 |
Larson | -0.006 |
Token | PUR |
Token ID | 33079 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
fell | +0.103 |
ihad | +0.086 |
iaries | +0.086 |
ATES | +0.084 |
inges | +0.084 |
Neg logit contributions | |
rade | -0.109 |
Braun | -0.104 |
synchronized | -0.102 |
Larson | -0.101 |
prolifer | -0.101 |
Token | GE |
Token ID | 8264 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
fell | +0.067 |
ihad | +0.058 |
ATES | +0.058 |
iaries | +0.057 |
inges | +0.057 |
Neg logit contributions | |
rade | -0.042 |
Braun | -0.040 |
synchronized | -0.039 |
Larson | -0.039 |
prolifer | -0.039 |
Token | D |
Token ID | 360 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
rade | +0.082 |
Braun | +0.078 |
synchronized | +0.077 |
lear | +0.076 |
Larson | +0.076 |
Neg logit contributions | |
fell | -0.084 |
ihad | -0.071 |
iaries | -0.071 |
ATES | -0.070 |
inges | -0.069 |
Token | ATES |
Token ID | 29462 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
fell | +0.007 |
ihad | +0.006 |
iaries | +0.006 |
inges | +0.005 |
ATES | +0.005 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.009 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | * |
Token ID | 9 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
fell | +0.315 |
ihad | +0.266 |
iaries | +0.264 |
ATES | +0.261 |
inges | +0.258 |
Neg logit contributions | |
rade | -0.311 |
Braun | -0.295 |
synchronized | -0.290 |
lear | -0.287 |
Larson | -0.287 |
Token | Spread |
Token ID | 31843 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
fell | +0.027 |
ihad | +0.023 |
iaries | +0.023 |
ATES | +0.022 |
inges | +0.022 |
Neg logit contributions | |
rade | -0.024 |
Braun | -0.023 |
synchronized | -0.023 |
Larson | -0.022 |
prolifer | -0.022 |
Token | This |
Token ID | 770 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
rade | +0.135 |
Braun | +0.128 |
synchronized | +0.126 |
Larson | +0.125 |
prolifer | +0.124 |
Neg logit contributions | |
fell | -0.157 |
ihad | -0.134 |
iaries | -0.134 |
ATES | -0.131 |
inges | -0.131 |
Token | around |
Token ID | 1088 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
lear | +0.003 |
Neg logit contributions | |
fell | -0.003 |
ihad | -0.003 |
iaries | -0.003 |
ATES | -0.003 |
inges | -0.003 |
Token | if |
Token ID | 611 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
rade | +0.067 |
Braun | +0.064 |
synchronized | +0.063 |
Larson | +0.062 |
prolifer | +0.062 |
Neg logit contributions | |
fell | -0.080 |
ihad | -0.068 |
iaries | -0.068 |
ATES | -0.067 |
inges | -0.067 |
Token | Red |
Token ID | 2297 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
fell | +0.053 |
ihad | +0.045 |
iaries | +0.045 |
ATES | +0.044 |
inges | +0.044 |
Neg logit contributions | |
rade | -0.048 |
Braun | -0.046 |
synchronized | -0.045 |
Larson | -0.045 |
prolifer | -0.045 |
Token | Tro |
Token ID | 8498 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
fell | +0.036 |
ihad | +0.029 |
iaries | +0.029 |
inges | +0.029 |
ATES | +0.028 |
Neg logit contributions | |
rade | -0.046 |
Braun | -0.045 |
synchronized | -0.044 |
Larson | -0.044 |
prolifer | -0.043 |
Token | ops |
Token ID | 2840 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
fell | +0.034 |
ihad | +0.029 |
iaries | +0.029 |
ATES | +0.028 |
inges | +0.028 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.030 |
synchronized | -0.030 |
Larson | -0.029 |
prolifer | -0.029 |
Token | against |
Token ID | 1028 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
fell | +0.093 |
ihad | +0.080 |
iaries | +0.079 |
ATES | +0.078 |
inges | +0.078 |
Neg logit contributions | |
rade | -0.074 |
Braun | -0.071 |
synchronized | -0.069 |
Larson | -0.069 |
lear | -0.068 |
Token | Kul |
Token ID | 50024 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
fell | +0.105 |
ihad | +0.089 |
iaries | +0.089 |
ATES | +0.087 |
inges | +0.087 |
Neg logit contributions | |
rade | -0.096 |
Braun | -0.091 |
synchronized | -0.090 |
Larson | -0.089 |
lear | -0.089 |
Token | ik |
Token ID | 1134 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
fell | +0.021 |
iaries | +0.018 |
ihad | +0.018 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.025 |
Braun | -0.024 |
synchronized | -0.023 |
Larson | -0.023 |
prolifer | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
fell | +0.366 |
ihad | +0.316 |
iaries | +0.315 |
inges | +0.309 |
ATES | +0.309 |
Neg logit contributions | |
rade | -0.256 |
Braun | -0.245 |
synchronized | -0.239 |
Larson | -0.237 |
prolifer | -0.234 |
Token | widely |
Token ID | 6768 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
fell | +0.073 |
ihad | +0.063 |
iaries | +0.063 |
inges | +0.061 |
ATES | +0.061 |
Neg logit contributions | |
rade | -0.052 |
Braun | -0.049 |
Larson | -0.047 |
synchronized | -0.047 |
oulder | -0.047 |
Token | propag |
Token ID | 8928 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.016 |
Larson | +0.015 |
oulder | +0.015 |
synchronized | +0.015 |
Neg logit contributions | |
fell | -0.030 |
iaries | -0.026 |
ihad | -0.026 |
inges | -0.026 |
ATES | -0.026 |
Token | and |
Token ID | 392 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
rade | +0.170 |
Braun | +0.165 |
synchronized | +0.163 |
Larson | +0.162 |
prolifer | +0.161 |
Neg logit contributions | |
fell | -0.066 |
ihad | -0.048 |
iaries | -0.047 |
inges | -0.045 |
ATES | -0.045 |
Token | ized |
Token ID | 1143 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
fell | +0.110 |
iaries | +0.085 |
ihad | +0.085 |
ATES | +0.081 |
inges | +0.081 |
Neg logit contributions | |
rade | -0.211 |
Braun | -0.206 |
synchronized | -0.202 |
Larson | -0.202 |
prolifer | -0.200 |
Token | to |
Token ID | 284 |
Feature activation | -5.19e-03 |
Pos logit contributions | |
fell | +0.091 |
ihad | +0.078 |
iaries | +0.078 |
inges | +0.076 |
ATES | +0.076 |
Neg logit contributions | |
rade | -0.078 |
Braun | -0.074 |
synchronized | -0.073 |
Larson | -0.072 |
prolifer | -0.072 |
Token | Havana |
Token ID | 40274 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
prolifer | +0.003 |
Neg logit contributions | |
fell | -0.004 |
ihad | -0.003 |
iaries | -0.003 |
inges | -0.003 |
ATES | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
fell | +0.079 |
ihad | +0.068 |
iaries | +0.068 |
inges | +0.067 |
ATES | +0.067 |
Neg logit contributions | |
rade | -0.056 |
Braun | -0.054 |
synchronized | -0.052 |
Larson | -0.052 |
prolifer | -0.052 |
Token | Trinidad |
Token ID | 48269 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.012 |
synchronized | +0.011 |
Larson | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.011 |
iaries | -0.011 |
inges | -0.011 |
ATES | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
ATES | +0.012 |
inges | +0.012 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
prolifer | -0.009 |
Token | walks |
Token ID | 11114 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.010 |
synchronized | +0.010 |
Larson | +0.010 |
prolifer | +0.010 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
ATES | -0.012 |
inges | -0.012 |
Token | through |
Token ID | 832 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
fell | +0.356 |
ihad | +0.308 |
iaries | +0.307 |
inges | +0.301 |
ATES | +0.301 |
Neg logit contributions | |
rade | -0.266 |
Braun | -0.253 |
synchronized | -0.247 |
Larson | -0.245 |
prolifer | -0.244 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
fell | +0.118 |
ihad | +0.101 |
iaries | +0.100 |
ATES | +0.098 |
inges | +0.098 |
Neg logit contributions | |
rade | -0.105 |
Braun | -0.101 |
synchronized | -0.099 |
Larson | -0.098 |
prolifer | -0.097 |
Token | countryside |
Token ID | 25708 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.009 |
iaries | +0.009 |
inges | +0.009 |
ATES | +0.009 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.009 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.01e-04 |
Pos logit contributions | |
rade | +0.031 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
prolifer | +0.028 |
Neg logit contributions | |
fell | -0.043 |
ihad | -0.037 |
iaries | -0.037 |
ATES | -0.036 |
inges | -0.036 |
Token | sn |
Token ID | 3013 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
fell | +0.000 |
ihad | +0.000 |
iaries | +0.000 |
inges | +0.000 |
ATES | +0.000 |
Neg logit contributions | |
rade | -0.000 |
Braun | -0.000 |
synchronized | -0.000 |
Larson | -0.000 |
prolifer | -0.000 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
rade | +0.036 |
Braun | +0.034 |
synchronized | +0.033 |
Larson | +0.033 |
lear | +0.033 |
Neg logit contributions | |
fell | -0.047 |
ihad | -0.040 |
iaries | -0.040 |
ATES | -0.040 |
inges | -0.039 |
Token | through |
Token ID | 832 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.011 |
iaries | +0.011 |
ATES | +0.011 |
inges | +0.011 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.011 |
synchronized | -0.011 |
Larson | -0.011 |
lear | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
fell | +0.119 |
ihad | +0.102 |
iaries | +0.102 |
ATES | +0.100 |
inges | +0.100 |
Neg logit contributions | |
rade | -0.096 |
Braun | -0.091 |
synchronized | -0.089 |
lear | -0.088 |
Larson | -0.088 |
Token | gates |
Token ID | 17435 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
lear | +0.016 |
Larson | +0.016 |
Neg logit contributions | |
fell | -0.018 |
iaries | -0.015 |
ihad | -0.015 |
inges | -0.015 |
ATES | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
lear | -0.010 |
Token | Said |
Token ID | 23885 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
rade | +0.013 |
Braun | +0.012 |
synchronized | +0.012 |
Larson | +0.012 |
prolifer | +0.012 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
inges | -0.012 |
ATES | -0.012 |
Token | John |
Token ID | 1757 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
fell | +0.303 |
ihad | +0.254 |
iaries | +0.253 |
ATES | +0.247 |
inges | +0.247 |
Neg logit contributions | |
rade | -0.320 |
Braun | -0.306 |
synchronized | -0.301 |
Larson | -0.298 |
lear | -0.297 |
Token | Murd |
Token ID | 20305 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
fell | +0.050 |
ihad | +0.043 |
iaries | +0.043 |
ATES | +0.042 |
inges | +0.042 |
Neg logit contributions | |
rade | -0.042 |
Braun | -0.039 |
synchronized | -0.039 |
prolifer | -0.038 |
lear | -0.038 |
Token | y |
Token ID | 88 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
fell | +0.089 |
ihad | +0.078 |
iaries | +0.078 |
inges | +0.076 |
ATES | +0.076 |
Neg logit contributions | |
rade | -0.059 |
Braun | -0.056 |
synchronized | -0.054 |
Larson | -0.054 |
prolifer | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
rade | +0.145 |
Braun | +0.138 |
synchronized | +0.135 |
Larson | +0.134 |
prolifer | +0.133 |
Neg logit contributions | |
fell | -0.192 |
ihad | -0.165 |
iaries | -0.165 |
inges | -0.162 |
ATES | -0.162 |
Token | Halloween |
Token ID | 16032 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
prolifer | +0.003 |
Neg logit contributions | |
fell | -0.004 |
ihad | -0.003 |
iaries | -0.003 |
inges | -0.003 |
ATES | -0.003 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
fell | +0.126 |
ihad | +0.107 |
iaries | +0.107 |
inges | +0.105 |
ATES | +0.105 |
Neg logit contributions | |
rade | -0.105 |
Braun | -0.099 |
synchronized | -0.097 |
Larson | -0.096 |
prolifer | -0.096 |
Token | � |
Token ID | 447 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
fell | +0.014 |
ihad | +0.012 |
iaries | +0.012 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
prolifer | -0.010 |
Token | � |
Token ID | 247 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
fell | +0.016 |
ihad | +0.014 |
iaries | +0.014 |
inges | +0.014 |
ATES | +0.014 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | s |
Token ID | 82 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
prolifer | +0.003 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | Von |
Token ID | 26985 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
fell | +0.029 |
ihad | +0.024 |
iaries | +0.024 |
inges | +0.024 |
ATES | +0.024 |
Neg logit contributions | |
rade | -0.027 |
Braun | -0.026 |
synchronized | -0.025 |
Larson | -0.025 |
prolifer | -0.025 |
Token | Braun |
Token ID | 34492 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
rade | +0.065 |
Braun | +0.062 |
synchronized | +0.060 |
Larson | +0.060 |
prolifer | +0.060 |
Neg logit contributions | |
fell | -0.088 |
ihad | -0.076 |
iaries | -0.076 |
ATES | -0.074 |
inges | -0.074 |
Token | or |
Token ID | 393 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
rade | +0.346 |
Braun | +0.331 |
synchronized | +0.323 |
Larson | +0.321 |
prolifer | +0.319 |
Neg logit contributions | |
fell | -0.398 |
ihad | -0.341 |
iaries | -0.340 |
ATES | -0.333 |
inges | -0.332 |
Token | , |
Token ID | 11 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
ATES | +0.007 |
inges | +0.007 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | before |
Token ID | 878 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
fell | +0.113 |
iaries | +0.098 |
ihad | +0.098 |
ATES | +0.096 |
inges | +0.096 |
Neg logit contributions | |
rade | -0.084 |
Braun | -0.080 |
synchronized | -0.078 |
Larson | -0.077 |
prolifer | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
rade | +0.019 |
Braun | +0.018 |
synchronized | +0.018 |
Larson | +0.018 |
prolifer | +0.018 |
Neg logit contributions | |
fell | -0.025 |
iaries | -0.022 |
ihad | -0.022 |
ATES | -0.021 |
inges | -0.021 |
Token | � |
Token ID | 251 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
ATES | +0.001 |
inges | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.000 |
Larson | -0.000 |
prolifer | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
rade | +0.020 |
Braun | +0.019 |
synchronized | +0.018 |
Larson | +0.018 |
prolifer | +0.018 |
Neg logit contributions | |
fell | -0.022 |
ihad | -0.019 |
iaries | -0.019 |
inges | -0.018 |
ATES | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
lear | +0.002 |
Neg logit contributions | |
fell | -0.002 |
iaries | -0.002 |
ihad | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | — |
Token ID | 960 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
prolifer | +0.003 |
Larson | +0.003 |
Neg logit contributions | |
fell | -0.003 |
ihad | -0.002 |
iaries | -0.002 |
ATES | -0.002 |
inges | -0.002 |
Token | Aaron |
Token ID | 34451 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
rade | +0.094 |
Braun | +0.090 |
synchronized | +0.088 |
Larson | +0.088 |
prolifer | +0.087 |
Neg logit contributions | |
fell | -0.100 |
ihad | -0.085 |
iaries | -0.085 |
inges | -0.083 |
ATES | -0.082 |
Token | Larson |
Token ID | 42630 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
rade | +0.112 |
Braun | +0.106 |
synchronized | +0.104 |
prolifer | +0.103 |
Larson | +0.102 |
Neg logit contributions | |
fell | -0.145 |
ihad | -0.125 |
iaries | -0.124 |
inges | -0.122 |
ATES | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | -7.86e-03 |
Pos logit contributions | |
rade | +0.294 |
Braun | +0.277 |
synchronized | +0.272 |
prolifer | +0.268 |
lear | +0.268 |
Neg logit contributions | |
fell | -0.418 |
iaries | -0.360 |
ihad | -0.360 |
inges | -0.353 |
ATES | -0.353 |
Token | associate |
Token ID | 11602 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
synchronized | +0.005 |
Larson | +0.005 |
prolifer | +0.005 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.005 |
iaries | -0.005 |
inges | -0.005 |
ATES | -0.005 |
Token | editor |
Token ID | 5464 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
fell | +0.043 |
ihad | +0.036 |
iaries | +0.036 |
ATES | +0.035 |
inges | +0.035 |
Neg logit contributions | |
rade | -0.044 |
Braun | -0.042 |
synchronized | -0.041 |
Larson | -0.041 |
prolifer | -0.041 |
Token | (@ |
Token ID | 4275 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
rade | +0.036 |
Braun | +0.034 |
synchronized | +0.034 |
prolifer | +0.033 |
Larson | +0.033 |
Neg logit contributions | |
fell | -0.045 |
ihad | -0.039 |
iaries | -0.038 |
ATES | -0.038 |
inges | -0.038 |
Token | Aaron |
Token ID | 34451 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
fell | +0.053 |
ihad | +0.045 |
iaries | +0.045 |
inges | +0.044 |
ATES | +0.044 |
Neg logit contributions | |
rade | -0.045 |
Braun | -0.043 |
synchronized | -0.043 |
Larson | -0.042 |
prolifer | -0.042 |
Token | too |
Token ID | 1165 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
lear | +0.005 |
synchronized | +0.005 |
oulder | +0.005 |
Neg logit contributions | |
fell | -0.008 |
ihad | -0.007 |
iaries | -0.007 |
ATES | -0.007 |
inges | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
rade | +0.085 |
Braun | +0.081 |
synchronized | +0.079 |
Larson | +0.078 |
lear | +0.078 |
Neg logit contributions | |
fell | -0.114 |
ihad | -0.099 |
iaries | -0.098 |
inges | -0.097 |
ATES | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.028 |
synchronized | +0.028 |
prolifer | +0.028 |
oulder | +0.028 |
Neg logit contributions | |
fell | -0.035 |
ihad | -0.029 |
iaries | -0.029 |
ATES | -0.029 |
inges | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.013 |
synchronized | +0.013 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.016 |
ihad | -0.013 |
iaries | -0.013 |
inges | -0.013 |
ATES | -0.013 |
Token | F |
Token ID | 37 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.009 |
prolifer | +0.009 |
Larson | +0.009 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
ATES | -0.009 |
inges | -0.009 |
Token | owler |
Token ID | 30014 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
fell | +0.132 |
ihad | +0.121 |
iaries | +0.121 |
inges | +0.120 |
ATES | +0.120 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.010 |
synchronized | -0.009 |
prolifer | -0.009 |
Larson | -0.009 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
rade | +0.302 |
Braun | +0.286 |
synchronized | +0.280 |
Larson | +0.277 |
lear | +0.276 |
Neg logit contributions | |
fell | -0.405 |
ihad | -0.350 |
iaries | -0.348 |
inges | -0.342 |
ATES | -0.342 |
Token | music |
Token ID | 2647 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.009 |
lear | +0.009 |
Larson | +0.009 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.010 |
iaries | -0.010 |
inges | -0.010 |
ATES | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
ATES | +0.001 |
inges | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
lear | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-03 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
lear | +0.002 |
synchronized | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | team |
Token ID | 1074 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
inges | +0.002 |
ATES | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
lear | -0.002 |
Larson | -0.002 |
oulder | -0.002 |
Token | OR |
Token ID | 1581 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
rade | +0.023 |
Braun | +0.022 |
synchronized | +0.022 |
prolifer | +0.022 |
lear | +0.022 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.016 |
iaries | -0.016 |
ATES | -0.016 |
inges | -0.015 |
Token | ATH |
Token ID | 12599 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.005 |
synchronized | +0.005 |
Larson | +0.005 |
prolifer | +0.005 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.010 |
iaries | -0.010 |
ATES | -0.010 |
inges | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
fell | +0.110 |
ihad | +0.094 |
iaries | +0.093 |
inges | +0.091 |
ATES | +0.091 |
Neg logit contributions | |
rade | -0.100 |
Braun | -0.096 |
synchronized | -0.094 |
Larson | -0.093 |
prolifer | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
fell | +0.009 |
ihad | +0.008 |
iaries | +0.008 |
inges | +0.008 |
ATES | +0.008 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.007 |
Larson | -0.007 |
prolifer | -0.007 |
Token | B |
Token ID | 33 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
fell | +0.022 |
ihad | +0.019 |
iaries | +0.019 |
ATES | +0.018 |
inges | +0.018 |
Neg logit contributions | |
rade | -0.022 |
Braun | -0.022 |
synchronized | -0.021 |
Larson | -0.021 |
prolifer | -0.021 |
Token | oulder |
Token ID | 17601 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
fell | +0.061 |
ihad | +0.051 |
iaries | +0.051 |
ATES | +0.050 |
inges | +0.050 |
Neg logit contributions | |
rade | -0.060 |
Braun | -0.058 |
synchronized | -0.057 |
Larson | -0.056 |
prolifer | -0.056 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
rade | +0.312 |
Braun | +0.297 |
synchronized | +0.291 |
prolifer | +0.287 |
lear | +0.287 |
Neg logit contributions | |
fell | -0.393 |
ihad | -0.336 |
iaries | -0.335 |
ATES | -0.329 |
inges | -0.329 |
Token | " |
Token ID | 1 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
rade | +0.087 |
Braun | +0.083 |
synchronized | +0.082 |
Larson | +0.081 |
prolifer | +0.081 |
Neg logit contributions | |
fell | -0.085 |
ihad | -0.071 |
iaries | -0.071 |
ATES | -0.069 |
inges | -0.069 |
Token | What |
Token ID | 2061 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
rade | +0.072 |
Braun | +0.069 |
synchronized | +0.067 |
Larson | +0.067 |
prolifer | +0.067 |
Neg logit contributions | |
fell | -0.070 |
ihad | -0.059 |
iaries | -0.059 |
inges | -0.058 |
ATES | -0.058 |
Token | .. |
Token ID | 492 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
lear | +0.002 |
Neg logit contributions | |
fell | -0.003 |
ihad | -0.002 |
iaries | -0.002 |
ATES | -0.002 |
inges | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
fell | +0.079 |
ihad | +0.067 |
iaries | +0.067 |
inges | +0.066 |
ATES | +0.066 |
Neg logit contributions | |
rade | -0.068 |
Braun | -0.065 |
synchronized | -0.063 |
Larson | -0.063 |
prolifer | -0.063 |
Token | signals |
Token ID | 10425 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
fell | +0.161 |
ihad | +0.138 |
iaries | +0.137 |
inges | +0.135 |
ATES | +0.134 |
Neg logit contributions | |
rade | -0.132 |
Braun | -0.126 |
synchronized | -0.123 |
Larson | -0.122 |
lear | -0.122 |
Token | from |
Token ID | 422 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
rade | +0.061 |
Braun | +0.058 |
synchronized | +0.056 |
Larson | +0.056 |
lear | +0.056 |
Neg logit contributions | |
fell | -0.078 |
ihad | -0.067 |
iaries | -0.067 |
inges | -0.066 |
ATES | -0.065 |
Token | them |
Token ID | 606 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.001 |
ihad | -0.001 |
iaries | -0.001 |
inges | -0.001 |
ATES | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
rade | +0.040 |
Braun | +0.038 |
synchronized | +0.037 |
Larson | +0.037 |
lear | +0.037 |
Neg logit contributions | |
fell | -0.054 |
ihad | -0.047 |
iaries | -0.047 |
inges | -0.046 |
ATES | -0.046 |
Token | Astron |
Token ID | 25398 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rade | +0.050 |
Braun | +0.048 |
synchronized | +0.047 |
Larson | +0.046 |
prolifer | +0.046 |
Neg logit contributions | |
fell | -0.057 |
ihad | -0.049 |
iaries | -0.049 |
ATES | -0.047 |
inges | -0.047 |
Token | omers |
Token ID | 21499 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
rade | +0.045 |
Braun | +0.042 |
synchronized | +0.040 |
Larson | +0.040 |
prolifer | +0.040 |
Neg logit contributions | |
fell | -0.094 |
ihad | -0.083 |
iaries | -0.083 |
inges | -0.082 |
ATES | -0.082 |
Token | have |
Token ID | 423 |
Feature activation | +9.13e-03 |
Pos logit contributions | |
rade | +0.305 |
Braun | +0.288 |
synchronized | +0.281 |
Larson | +0.279 |
oulder | +0.278 |
Neg logit contributions | |
fell | -0.396 |
ihad | -0.342 |
iaries | -0.340 |
inges | -0.333 |
ATES | -0.333 |
Token | long |
Token ID | 890 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
inges | +0.007 |
ATES | +0.007 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
oulder | -0.004 |
Larson | -0.004 |
synchronized | -0.004 |
Token | relied |
Token ID | 17498 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
rade | +0.092 |
Braun | +0.086 |
Larson | +0.084 |
synchronized | +0.084 |
oulder | +0.083 |
Neg logit contributions | |
fell | -0.135 |
ihad | -0.117 |
iaries | -0.116 |
inges | -0.114 |
ATES | -0.114 |
Token | on |
Token ID | 319 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
fell | +0.066 |
ihad | +0.057 |
iaries | +0.057 |
ATES | +0.055 |
inges | +0.055 |
Neg logit contributions | |
rade | -0.057 |
Braun | -0.055 |
synchronized | -0.054 |
Larson | -0.053 |
prolifer | -0.053 |
Token | simulated |
Token ID | 28590 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
rade | +0.018 |
Braun | +0.017 |
synchronized | +0.017 |
Larson | +0.016 |
prolifer | +0.016 |
Neg logit contributions | |
fell | -0.022 |
ihad | -0.019 |
iaries | -0.019 |
inges | -0.019 |
ATES | -0.019 |
Token | � |
Token ID | 447 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
fell | +0.017 |
ihad | +0.014 |
iaries | +0.014 |
ATES | +0.014 |
inges | +0.014 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
prolifer | -0.014 |
lear | -0.014 |
Token | � |
Token ID | 251 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
rade | +0.024 |
Braun | +0.023 |
synchronized | +0.022 |
prolifer | +0.022 |
lear | +0.022 |
Neg logit contributions | |
fell | -0.027 |
ihad | -0.023 |
iaries | -0.023 |
ATES | -0.022 |
inges | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
fell | +0.019 |
ihad | +0.017 |
iaries | +0.017 |
inges | +0.016 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.017 |
Braun | -0.016 |
synchronized | -0.016 |
Larson | -0.016 |
prolifer | -0.016 |
Token | F |
Token ID | 37 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
fell | +0.025 |
ihad | +0.021 |
iaries | +0.021 |
ATES | +0.020 |
inges | +0.020 |
Neg logit contributions | |
rade | -0.023 |
Braun | -0.022 |
synchronized | -0.022 |
prolifer | -0.022 |
Larson | -0.022 |
Token | owler |
Token ID | 30014 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
fell | +0.133 |
ihad | +0.122 |
iaries | +0.122 |
inges | +0.121 |
ATES | +0.120 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.010 |
synchronized | -0.009 |
prolifer | -0.009 |
Larson | -0.009 |
Token | � |
Token ID | 447 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
rade | +0.293 |
Braun | +0.277 |
synchronized | +0.270 |
Larson | +0.269 |
oulder | +0.267 |
Neg logit contributions | |
fell | -0.393 |
ihad | -0.339 |
iaries | -0.337 |
inges | -0.331 |
ATES | -0.331 |
Token | � |
Token ID | 247 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.002 |
Larson | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.004 |
iaries | -0.004 |
ATES | -0.004 |
inges | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
Larson | +0.016 |
prolifer | +0.016 |
Neg logit contributions | |
fell | -0.016 |
ihad | -0.013 |
iaries | -0.013 |
inges | -0.013 |
ATES | -0.013 |
Token | � |
Token ID | 564 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
fell | +0.078 |
ihad | +0.067 |
iaries | +0.067 |
ATES | +0.065 |
inges | +0.065 |
Neg logit contributions | |
rade | -0.063 |
Braun | -0.060 |
synchronized | -0.058 |
Larson | -0.058 |
oulder | -0.058 |
Token | � |
Token ID | 250 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
fell | +0.037 |
ihad | +0.033 |
iaries | +0.032 |
inges | +0.032 |
ATES | +0.032 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
Larson | -0.024 |
prolifer | -0.024 |
Token | oked |
Token ID | 6545 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
rade | +0.145 |
Braun | +0.141 |
synchronized | +0.139 |
lear | +0.138 |
oulder | +0.138 |
Neg logit contributions | |
fell | -0.049 |
iaries | -0.034 |
ihad | -0.034 |
ATES | -0.031 |
inges | -0.031 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
fell | +0.200 |
ihad | +0.169 |
iaries | +0.169 |
ATES | +0.165 |
inges | +0.165 |
Neg logit contributions | |
rade | -0.189 |
Braun | -0.180 |
synchronized | -0.177 |
Larson | -0.175 |
prolifer | -0.175 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
rade | +0.041 |
Braun | +0.038 |
synchronized | +0.038 |
Larson | +0.037 |
prolifer | +0.037 |
Neg logit contributions | |
fell | -0.060 |
ihad | -0.052 |
iaries | -0.052 |
ATES | -0.051 |
inges | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
rade | +0.036 |
Braun | +0.034 |
synchronized | +0.033 |
Larson | +0.033 |
prolifer | +0.033 |
Neg logit contributions | |
fell | -0.058 |
ihad | -0.050 |
iaries | -0.050 |
inges | -0.049 |
ATES | -0.049 |
Token | Deborah |
Token ID | 36976 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.013 |
synchronized | +0.013 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.015 |
ihad | -0.013 |
iaries | -0.013 |
inges | -0.013 |
ATES | -0.013 |
Token | Wasserman |
Token ID | 38997 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
rade | +0.026 |
Braun | +0.023 |
synchronized | +0.022 |
lear | +0.021 |
prolifer | +0.021 |
Neg logit contributions | |
fell | -0.133 |
ihad | -0.121 |
iaries | -0.121 |
ATES | -0.119 |
inges | -0.119 |
Token | Schultz |
Token ID | 26530 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
rade | +0.217 |
Braun | +0.201 |
synchronized | +0.196 |
Larson | +0.193 |
lear | +0.192 |
Neg logit contributions | |
fell | -0.468 |
ihad | -0.413 |
iaries | -0.413 |
inges | -0.406 |
ATES | -0.406 |
Token | will |
Token ID | 481 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
rade | +0.080 |
Braun | +0.076 |
synchronized | +0.074 |
Larson | +0.073 |
prolifer | +0.073 |
Neg logit contributions | |
fell | -0.115 |
ihad | -0.099 |
iaries | -0.099 |
ATES | -0.097 |
inges | -0.097 |
Token | not |
Token ID | 407 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
fell | +0.060 |
ihad | +0.052 |
iaries | +0.051 |
inges | +0.051 |
ATES | +0.051 |
Neg logit contributions | |
rade | -0.047 |
Braun | -0.044 |
synchronized | -0.043 |
prolifer | -0.043 |
Larson | -0.043 |
Token | allow |
Token ID | 1249 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
fell | +0.025 |
iaries | +0.022 |
ihad | +0.022 |
inges | +0.021 |
ATES | +0.021 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
Larson | -0.018 |
lear | -0.017 |
Token | Bernie |
Token ID | 10477 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
rade | +0.038 |
Braun | +0.036 |
synchronized | +0.035 |
Larson | +0.035 |
prolifer | +0.035 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.033 |
iaries | -0.033 |
inges | -0.032 |
ATES | -0.032 |
Token | birth |
Token ID | 4082 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.017 |
iaries | +0.017 |
inges | +0.016 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.018 |
Braun | -0.017 |
synchronized | -0.016 |
Larson | -0.016 |
prolifer | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
rade | +0.025 |
Braun | +0.023 |
synchronized | +0.023 |
Larson | +0.023 |
prolifer | +0.023 |
Neg logit contributions | |
fell | -0.036 |
ihad | -0.031 |
iaries | -0.031 |
ATES | -0.030 |
inges | -0.030 |
Token | death |
Token ID | 1918 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
inges | +0.006 |
ATES | +0.006 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.006 |
prolifer | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
rade | +0.110 |
Braun | +0.104 |
synchronized | +0.102 |
Larson | +0.101 |
prolifer | +0.100 |
Neg logit contributions | |
fell | -0.154 |
ihad | -0.134 |
iaries | -0.133 |
inges | -0.131 |
ATES | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.010 |
iaries | +0.010 |
inges | +0.010 |
ATES | +0.010 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.008 |
Token | Resurrection |
Token ID | 30688 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
rade | +0.008 |
Braun | +0.008 |
synchronized | +0.007 |
Larson | +0.007 |
prolifer | +0.007 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.008 |
ATES | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
rade | +0.282 |
Braun | +0.266 |
synchronized | +0.260 |
Larson | +0.258 |
lear | +0.257 |
Neg logit contributions | |
fell | -0.388 |
ihad | -0.336 |
iaries | -0.334 |
ATES | -0.329 |
inges | -0.328 |
Token | The |
Token ID | 383 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.011 |
iaries | +0.011 |
inges | +0.011 |
ATES | +0.011 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.011 |
synchronized | -0.011 |
Larson | -0.011 |
prolifer | -0.011 |
Token | paintings |
Token ID | 21641 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
fell | +0.030 |
ihad | +0.025 |
iaries | +0.025 |
inges | +0.025 |
ATES | +0.025 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.024 |
synchronized | -0.024 |
Larson | -0.024 |
lear | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
rade | +0.121 |
Braun | +0.115 |
synchronized | +0.112 |
Larson | +0.112 |
lear | +0.112 |
Neg logit contributions | |
fell | -0.144 |
ihad | -0.123 |
iaries | -0.122 |
inges | -0.119 |
ATES | -0.119 |
Token | expensive |
Token ID | 5789 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
fell | +0.106 |
ihad | +0.092 |
iaries | +0.092 |
inges | +0.090 |
ATES | +0.090 |
Neg logit contributions | |
rade | -0.072 |
Braun | -0.068 |
synchronized | -0.066 |
Larson | -0.066 |
lear | -0.066 |
Token | over |
Token ID | 625 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.005 |
synchronized | +0.005 |
Larson | +0.005 |
prolifer | +0.005 |
Neg logit contributions | |
fell | -0.007 |
ihad | -0.006 |
iaries | -0.006 |
inges | -0.006 |
ATES | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
rade | +0.091 |
Braun | +0.088 |
synchronized | +0.086 |
prolifer | +0.085 |
Larson | +0.085 |
Neg logit contributions | |
fell | -0.082 |
ihad | -0.069 |
iaries | -0.069 |
ATES | -0.067 |
inges | -0.067 |
Token | the |
Token ID | 1169 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
fell | +0.005 |
iaries | +0.004 |
ihad | +0.004 |
ATES | +0.004 |
inges | +0.004 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.007 |
synchronized | -0.007 |
Larson | -0.007 |
prolifer | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
fell | +0.021 |
ihad | +0.018 |
iaries | +0.018 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.020 |
Braun | -0.019 |
synchronized | -0.019 |
Larson | -0.018 |
prolifer | -0.018 |
Token | sh |
Token ID | 1477 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
rade | +0.013 |
Braun | +0.012 |
synchronized | +0.012 |
Larson | +0.012 |
prolifer | +0.012 |
Neg logit contributions | |
fell | -0.020 |
ihad | -0.017 |
iaries | -0.017 |
inges | -0.017 |
ATES | -0.017 |
Token | oulder |
Token ID | 17601 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
fell | +0.280 |
ihad | +0.257 |
iaries | +0.256 |
inges | +0.255 |
ATES | +0.253 |
Neg logit contributions | |
rade | -0.017 |
Braun | -0.013 |
synchronized | -0.011 |
Larson | -0.010 |
prolifer | -0.009 |
Token | camera |
Token ID | 4676 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
rade | +0.273 |
Braun | +0.259 |
synchronized | +0.254 |
Larson | +0.250 |
prolifer | +0.250 |
Neg logit contributions | |
fell | -0.394 |
ihad | -0.343 |
iaries | -0.342 |
inges | -0.336 |
ATES | -0.335 |
Token | or |
Token ID | 393 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
fell | +0.110 |
ihad | +0.095 |
iaries | +0.095 |
ATES | +0.093 |
inges | +0.093 |
Neg logit contributions | |
rade | -0.081 |
Braun | -0.077 |
synchronized | -0.075 |
Larson | -0.074 |
prolifer | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.012 |
synchronized | +0.012 |
Larson | +0.012 |
prolifer | +0.012 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.011 |
iaries | -0.011 |
ATES | -0.011 |
inges | -0.011 |
Token | default |
Token ID | 4277 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
ATES | +0.002 |
inges | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token | action |
Token ID | 2223 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
fell | +0.142 |
ihad | +0.121 |
iaries | +0.121 |
inges | +0.118 |
ATES | +0.118 |
Neg logit contributions | |
rade | -0.119 |
Braun | -0.113 |
synchronized | -0.111 |
Larson | -0.110 |
prolifer | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
fell | +0.049 |
ihad | +0.042 |
iaries | +0.042 |
inges | +0.041 |
ATES | +0.041 |
Neg logit contributions | |
rade | -0.039 |
Braun | -0.038 |
synchronized | -0.037 |
Larson | -0.036 |
prolifer | -0.036 |
Token | purpose |
Token ID | 4007 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
rade | +0.021 |
Braun | +0.020 |
synchronized | +0.019 |
Larson | +0.019 |
prolifer | +0.019 |
Neg logit contributions | |
fell | -0.022 |
ihad | -0.019 |
iaries | -0.019 |
inges | -0.018 |
ATES | -0.018 |
Token | ful |
Token ID | 913 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
fell | +0.038 |
iaries | +0.034 |
ihad | +0.034 |
inges | +0.033 |
ATES | +0.033 |
Neg logit contributions | |
rade | -0.023 |
Braun | -0.022 |
synchronized | -0.022 |
Larson | -0.021 |
prolifer | -0.021 |
Token | tactic |
Token ID | 18543 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
rade | +0.058 |
Braun | +0.055 |
synchronized | +0.054 |
Larson | +0.054 |
prolifer | +0.054 |
Neg logit contributions | |
fell | -0.076 |
ihad | -0.065 |
iaries | -0.065 |
inges | -0.064 |
ATES | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
rade | +0.123 |
Braun | +0.117 |
synchronized | +0.114 |
Larson | +0.113 |
prolifer | +0.113 |
Neg logit contributions | |
fell | -0.161 |
ihad | -0.139 |
iaries | -0.139 |
inges | -0.136 |
ATES | -0.136 |
Token | deter |
Token ID | 2206 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
fell | +0.006 |
ihad | +0.005 |
iaries | +0.005 |
inges | +0.005 |
ATES | +0.005 |
Neg logit contributions | |
rade | -0.004 |
Braun | -0.004 |
synchronized | -0.004 |
prolifer | -0.004 |
Larson | -0.004 |
Token | people |
Token ID | 661 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
rade | +0.324 |
Braun | +0.310 |
synchronized | +0.304 |
Larson | +0.301 |
prolifer | +0.301 |
Neg logit contributions | |
fell | -0.337 |
iaries | -0.285 |
ihad | -0.285 |
inges | -0.278 |
ATES | -0.278 |
Token | from |
Token ID | 422 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.018 |
iaries | +0.018 |
inges | +0.017 |
ATES | +0.017 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.016 |
synchronized | -0.015 |
Larson | -0.015 |
prolifer | -0.015 |
Token | finding |
Token ID | 4917 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.017 |
synchronized | +0.016 |
Larson | +0.016 |
lear | +0.016 |
Neg logit contributions | |
fell | -0.024 |
ihad | -0.021 |
iaries | -0.021 |
ATES | -0.020 |
inges | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
rade | +0.047 |
Braun | +0.045 |
synchronized | +0.044 |
Larson | +0.044 |
prolifer | +0.044 |
Neg logit contributions | |
fell | -0.058 |
ihad | -0.050 |
iaries | -0.049 |
ATES | -0.048 |
inges | -0.048 |
Token | protest |
Token ID | 5402 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.016 |
synchronized | +0.016 |
Larson | +0.016 |
prolifer | +0.016 |
Neg logit contributions | |
fell | -0.020 |
ihad | -0.017 |
iaries | -0.017 |
inges | -0.017 |
ATES | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.009 |
Larson | +0.009 |
prolifer | +0.009 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.011 |
iaries | -0.011 |
ATES | -0.011 |
inges | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
fell | +0.009 |
ihad | +0.008 |
iaries | +0.008 |
inges | +0.007 |
ATES | +0.007 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
prolifer | -0.006 |
lear | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.011 |
iaries | +0.011 |
inges | +0.011 |
ATES | +0.011 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.011 |
synchronized | -0.011 |
Larson | -0.010 |
lear | -0.010 |
Token | F |
Token ID | 37 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
fell | +0.016 |
ihad | +0.013 |
iaries | +0.013 |
ATES | +0.013 |
inges | +0.013 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.013 |
prolifer | -0.013 |
Larson | -0.013 |
Token | owler |
Token ID | 30014 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
fell | +0.091 |
ihad | +0.078 |
iaries | +0.078 |
ATES | +0.077 |
inges | +0.077 |
Neg logit contributions | |
rade | -0.074 |
Braun | -0.071 |
synchronized | -0.069 |
prolifer | -0.069 |
Larson | -0.069 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
rade | +0.284 |
Braun | +0.268 |
synchronized | +0.263 |
Larson | +0.261 |
lear | +0.260 |
Neg logit contributions | |
fell | -0.376 |
ihad | -0.324 |
iaries | -0.322 |
inges | -0.316 |
ATES | -0.316 |
Token | a |
Token ID | 257 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
fell | +0.026 |
ihad | +0.023 |
iaries | +0.022 |
inges | +0.022 |
ATES | +0.022 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.020 |
synchronized | -0.019 |
Larson | -0.019 |
prolifer | -0.019 |
Token | player |
Token ID | 2137 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
rade | +0.041 |
Braun | +0.039 |
synchronized | +0.038 |
Larson | +0.038 |
prolifer | +0.038 |
Neg logit contributions | |
fell | -0.047 |
ihad | -0.041 |
iaries | -0.040 |
inges | -0.040 |
ATES | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
fell | +0.155 |
ihad | +0.133 |
iaries | +0.133 |
inges | +0.130 |
ATES | +0.130 |
Neg logit contributions | |
rade | -0.123 |
Braun | -0.117 |
synchronized | -0.114 |
Larson | -0.113 |
prolifer | -0.113 |
Token | Cardinals |
Token ID | 18071 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
rade | +0.020 |
Braun | +0.019 |
synchronized | +0.018 |
Larson | +0.018 |
prolifer | +0.018 |
Neg logit contributions | |
fell | -0.025 |
ihad | -0.022 |
iaries | -0.022 |
inges | -0.021 |
ATES | -0.021 |
Token | constructive |
Token ID | 26938 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
fell | +0.056 |
ihad | +0.047 |
iaries | +0.047 |
inges | +0.046 |
ATES | +0.046 |
Neg logit contributions | |
rade | -0.050 |
Braun | -0.047 |
synchronized | -0.047 |
Larson | -0.046 |
prolifer | -0.046 |
Token | is |
Token ID | 318 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
rade | +0.069 |
Braun | +0.066 |
synchronized | +0.065 |
Larson | +0.064 |
prolifer | +0.064 |
Neg logit contributions | |
fell | -0.074 |
ihad | -0.063 |
iaries | -0.063 |
inges | -0.061 |
ATES | -0.061 |
Token | offered |
Token ID | 4438 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
rade | +0.046 |
Braun | +0.044 |
synchronized | +0.043 |
Larson | +0.042 |
oulder | +0.042 |
Neg logit contributions | |
fell | -0.071 |
ihad | -0.061 |
iaries | -0.061 |
inges | -0.060 |
ATES | -0.060 |
Token | that |
Token ID | 326 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.028 |
synchronized | +0.028 |
lear | +0.028 |
Larson | +0.027 |
Neg logit contributions | |
fell | -0.037 |
ihad | -0.032 |
iaries | -0.032 |
inges | -0.031 |
ATES | -0.031 |
Token | might |
Token ID | 1244 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
fell | +0.036 |
ihad | +0.031 |
iaries | +0.031 |
inges | +0.030 |
ATES | +0.030 |
Neg logit contributions | |
rade | -0.029 |
Braun | -0.028 |
synchronized | -0.027 |
Larson | -0.027 |
prolifer | -0.027 |
Token | deter |
Token ID | 2206 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
inges | +0.001 |
ATES | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
lear | -0.001 |
Token | future |
Token ID | 2003 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
rade | +0.307 |
Braun | +0.293 |
synchronized | +0.287 |
Larson | +0.284 |
prolifer | +0.284 |
Neg logit contributions | |
fell | -0.349 |
ihad | -0.298 |
iaries | -0.297 |
inges | -0.291 |
ATES | -0.291 |
Token | attacks |
Token ID | 3434 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
fell | +0.099 |
ihad | +0.084 |
iaries | +0.084 |
inges | +0.082 |
ATES | +0.082 |
Neg logit contributions | |
rade | -0.093 |
Braun | -0.089 |
synchronized | -0.087 |
Larson | -0.086 |
prolifer | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
rade | +0.022 |
Braun | +0.021 |
synchronized | +0.021 |
Larson | +0.020 |
lear | +0.020 |
Neg logit contributions | |
fell | -0.029 |
ihad | -0.025 |
iaries | -0.025 |
inges | -0.024 |
ATES | -0.024 |
Token | Indeed |
Token ID | 9676 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
rade | +0.010 |
Braun | +0.010 |
synchronized | +0.010 |
Larson | +0.010 |
prolifer | +0.010 |
Neg logit contributions | |
fell | -0.012 |
ihad | -0.010 |
iaries | -0.010 |
ATES | -0.010 |
inges | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
rade | +0.132 |
Braun | +0.126 |
synchronized | +0.123 |
Larson | +0.122 |
prolifer | +0.121 |
Neg logit contributions | |
fell | -0.177 |
ihad | -0.153 |
iaries | -0.153 |
inges | -0.149 |
ATES | -0.149 |
Token | from |
Token ID | 422 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
fell | +0.050 |
ihad | +0.043 |
iaries | +0.043 |
inges | +0.042 |
ATES | +0.042 |
Neg logit contributions | |
rade | -0.040 |
Braun | -0.038 |
synchronized | -0.037 |
Larson | -0.037 |
prolifer | -0.036 |
Token | Mitch |
Token ID | 20472 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
fell | +0.010 |
ihad | +0.009 |
iaries | +0.009 |
ATES | +0.008 |
inges | +0.008 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | McConnell |
Token ID | 18184 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
fell | +0.106 |
ihad | +0.094 |
iaries | +0.093 |
inges | +0.092 |
ATES | +0.092 |
Neg logit contributions | |
rade | -0.046 |
Braun | -0.043 |
synchronized | -0.042 |
lear | -0.042 |
prolifer | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
rade | +0.091 |
Braun | +0.086 |
synchronized | +0.085 |
Larson | +0.084 |
prolifer | +0.083 |
Neg logit contributions | |
fell | -0.127 |
ihad | -0.110 |
iaries | -0.109 |
inges | -0.107 |
ATES | -0.107 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
rade | +0.016 |
Braun | +0.016 |
synchronized | +0.015 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.018 |
ihad | -0.015 |
iaries | -0.015 |
inges | -0.015 |
ATES | -0.015 |
Token | Grassley |
Token ID | 44050 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
ATES | +0.013 |
inges | +0.013 |
Neg logit contributions | |
rade | -0.004 |
Braun | -0.004 |
synchronized | -0.004 |
prolifer | -0.004 |
oulder | -0.004 |
Token | would |
Token ID | 561 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rade | +0.269 |
Braun | +0.255 |
synchronized | +0.249 |
Larson | +0.246 |
prolifer | +0.246 |
Neg logit contributions | |
fell | -0.380 |
ihad | -0.330 |
iaries | -0.329 |
inges | -0.323 |
ATES | -0.322 |
Token | be |
Token ID | 307 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
rade | +0.084 |
Braun | +0.080 |
synchronized | +0.078 |
Larson | +0.077 |
prolifer | +0.077 |
Neg logit contributions | |
fell | -0.112 |
ihad | -0.097 |
iaries | -0.097 |
ATES | -0.095 |
inges | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
rade | +0.008 |
Braun | +0.008 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.009 |
ihad | -0.008 |
iaries | -0.008 |
ATES | -0.008 |
inges | -0.008 |
Token | end |
Token ID | 886 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
fell | +0.019 |
ihad | +0.016 |
iaries | +0.016 |
inges | +0.016 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
synchronized | -0.015 |
Larson | -0.015 |
prolifer | -0.015 |
Token | result |
Token ID | 1255 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
rade | +0.007 |
Braun | +0.007 |
synchronized | +0.007 |
Larson | +0.007 |
prolifer | +0.007 |
Neg logit contributions | |
fell | -0.008 |
ihad | -0.007 |
iaries | -0.007 |
inges | -0.006 |
ATES | -0.006 |
Token | network |
Token ID | 3127 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
fell | +0.007 |
ihad | +0.006 |
iaries | +0.006 |
inges | +0.006 |
ATES | +0.006 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.005 |
synchronized | -0.005 |
Larson | -0.005 |
prolifer | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.010 |
iaries | +0.010 |
ATES | +0.010 |
inges | +0.010 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.007 |
Larson | -0.007 |
prolifer | -0.007 |
Token | mitigation |
Token ID | 33585 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
rade | +0.031 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
lear | +0.028 |
Neg logit contributions | |
fell | -0.038 |
iaries | -0.032 |
ihad | -0.032 |
ATES | -0.032 |
inges | -0.032 |
Token | are |
Token ID | 389 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
fell | +0.085 |
ihad | +0.074 |
iaries | +0.074 |
ATES | +0.072 |
inges | +0.072 |
Neg logit contributions | |
rade | -0.062 |
Braun | -0.059 |
synchronized | -0.057 |
Larson | -0.057 |
lear | -0.057 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.028 |
synchronized | +0.028 |
Larson | +0.027 |
prolifer | +0.027 |
Neg logit contributions | |
fell | -0.040 |
ihad | -0.035 |
iaries | -0.035 |
inges | -0.034 |
ATES | -0.034 |
Token | synchronized |
Token ID | 47192 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
fell | +0.055 |
ihad | +0.048 |
iaries | +0.048 |
ATES | +0.047 |
inges | +0.047 |
Neg logit contributions | |
rade | -0.029 |
Braun | -0.028 |
synchronized | -0.027 |
Larson | -0.027 |
lear | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
rade | +0.266 |
Braun | +0.252 |
synchronized | +0.244 |
Larson | +0.244 |
lear | +0.243 |
Neg logit contributions | |
fell | -0.378 |
ihad | -0.328 |
iaries | -0.326 |
ATES | -0.321 |
inges | -0.321 |
Token |
|
Token ID | 198 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.011 |
synchronized | +0.010 |
Larson | +0.010 |
lear | +0.010 |
Neg logit contributions | |
fell | -0.013 |
iaries | -0.011 |
ihad | -0.011 |
inges | -0.011 |
ATES | -0.011 |
Token | At |
Token ID | 2953 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
rade | +0.004 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
lear | +0.003 |
Neg logit contributions | |
fell | -0.003 |
iaries | -0.003 |
ihad | -0.003 |
inges | -0.003 |
ATES | -0.003 |
Token | this |
Token ID | 428 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.010 |
iaries | +0.010 |
inges | +0.010 |
ATES | +0.010 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.010 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | point |
Token ID | 966 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
ATES | +0.002 |
inges | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
fell | +0.026 |
ihad | +0.022 |
iaries | +0.022 |
inges | +0.022 |
ATES | +0.022 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
Larson | -0.018 |
prolifer | -0.017 |
Token | My |
Token ID | 2011 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
rade | +0.045 |
Braun | +0.043 |
synchronized | +0.042 |
Larson | +0.042 |
prolifer | +0.042 |
Neg logit contributions | |
fell | -0.050 |
ihad | -0.043 |
iaries | -0.043 |
inges | -0.042 |
ATES | -0.042 |
Token | findings |
Token ID | 6373 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
rade | +0.036 |
Braun | +0.034 |
synchronized | +0.034 |
Larson | +0.033 |
prolifer | +0.033 |
Neg logit contributions | |
fell | -0.041 |
ihad | -0.035 |
iaries | -0.035 |
inges | -0.034 |
ATES | -0.034 |
Token | are |
Token ID | 389 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
rade | +0.144 |
Braun | +0.137 |
synchronized | +0.133 |
Larson | +0.132 |
lear | +0.132 |
Neg logit contributions | |
fell | -0.186 |
ihad | -0.160 |
iaries | -0.159 |
inges | -0.156 |
ATES | -0.156 |
Token | incon |
Token ID | 15861 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
rade | +0.059 |
Braun | +0.056 |
synchronized | +0.055 |
Larson | +0.055 |
prolifer | +0.054 |
Neg logit contributions | |
fell | -0.076 |
ihad | -0.065 |
iaries | -0.065 |
inges | -0.064 |
ATES | -0.064 |
Token | clusive |
Token ID | 5731 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
fell | +0.162 |
ihad | +0.144 |
iaries | +0.143 |
inges | +0.142 |
ATES | +0.140 |
Neg logit contributions | |
rade | -0.053 |
Braun | -0.050 |
synchronized | -0.049 |
Larson | -0.048 |
prolifer | -0.047 |
Token | if |
Token ID | 611 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
rade | +0.270 |
Braun | +0.256 |
synchronized | +0.250 |
lear | +0.247 |
Larson | +0.247 |
Neg logit contributions | |
fell | -0.372 |
ihad | -0.322 |
iaries | -0.320 |
ATES | -0.315 |
inges | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | -9.92e-03 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.009 |
iaries | -0.009 |
ATES | -0.009 |
inges | -0.009 |
Token | place |
Token ID | 1295 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
rade | +0.007 |
Braun | +0.006 |
synchronized | +0.006 |
Larson | +0.006 |
prolifer | +0.006 |
Neg logit contributions | |
fell | -0.007 |
ihad | -0.006 |
iaries | -0.006 |
inges | -0.006 |
ATES | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
rade | +0.016 |
Braun | +0.016 |
synchronized | +0.015 |
Larson | +0.015 |
oulder | +0.015 |
Neg logit contributions | |
fell | -0.022 |
ihad | -0.018 |
iaries | -0.018 |
inges | -0.018 |
ATES | -0.018 |
Token | haunted |
Token ID | 26688 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
rade | +0.066 |
Braun | +0.063 |
synchronized | +0.061 |
Larson | +0.061 |
prolifer | +0.061 |
Neg logit contributions | |
fell | -0.081 |
ihad | -0.070 |
iaries | -0.069 |
ATES | -0.068 |
inges | -0.068 |
Token | good |
Token ID | 922 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
rade | +0.039 |
Braun | +0.037 |
synchronized | +0.036 |
Larson | +0.036 |
prolifer | +0.035 |
Neg logit contributions | |
fell | -0.048 |
ihad | -0.041 |
iaries | -0.041 |
ATES | -0.040 |
inges | -0.040 |
Token | on |
Token ID | 319 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
rade | +0.035 |
Braun | +0.033 |
synchronized | +0.033 |
Larson | +0.032 |
prolifer | +0.032 |
Neg logit contributions | |
fell | -0.046 |
ihad | -0.040 |
iaries | -0.040 |
ATES | -0.039 |
inges | -0.039 |
Token | its |
Token ID | 663 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
fell | +0.027 |
ihad | +0.023 |
iaries | +0.023 |
inges | +0.023 |
ATES | +0.023 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
lear | -0.018 |
prolifer | -0.018 |
Token | potential |
Token ID | 2785 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rade | +0.070 |
Braun | +0.067 |
synchronized | +0.065 |
Larson | +0.065 |
lear | +0.064 |
Neg logit contributions | |
fell | -0.086 |
ihad | -0.074 |
iaries | -0.073 |
inges | -0.072 |
ATES | -0.072 |
Token | caric |
Token ID | 33674 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
rade | +0.084 |
Braun | +0.079 |
synchronized | +0.078 |
Larson | +0.077 |
lear | +0.077 |
Neg logit contributions | |
fell | -0.112 |
ihad | -0.096 |
iaries | -0.096 |
inges | -0.094 |
ATES | -0.094 |
Token | atures |
Token ID | 6691 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
rade | +0.027 |
Braun | +0.025 |
synchronized | +0.024 |
Larson | +0.024 |
prolifer | +0.024 |
Neg logit contributions | |
fell | -0.064 |
ihad | -0.057 |
iaries | -0.056 |
inges | -0.056 |
ATES | -0.056 |
Token | through |
Token ID | 832 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
rade | +0.283 |
Braun | +0.268 |
synchronized | +0.263 |
lear | +0.260 |
Larson | +0.260 |
Neg logit contributions | |
fell | -0.359 |
ihad | -0.309 |
iaries | -0.306 |
inges | -0.302 |
ATES | -0.301 |
Token | Allen |
Token ID | 9659 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
fell | +0.113 |
ihad | +0.098 |
iaries | +0.097 |
inges | +0.095 |
ATES | +0.095 |
Neg logit contributions | |
rade | -0.089 |
Braun | -0.084 |
synchronized | -0.083 |
Larson | -0.082 |
prolifer | -0.082 |
Token | � |
Token ID | 447 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
fell | +0.073 |
ihad | +0.063 |
iaries | +0.063 |
inges | +0.062 |
ATES | +0.062 |
Neg logit contributions | |
rade | -0.055 |
Braun | -0.052 |
synchronized | -0.051 |
Larson | -0.050 |
lear | -0.050 |
Token | � |
Token ID | 247 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.016 |
synchronized | +0.015 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.031 |
ihad | -0.027 |
iaries | -0.027 |
ATES | -0.027 |
inges | -0.027 |
Token | s |
Token ID | 82 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
rade | +0.029 |
Braun | +0.028 |
synchronized | +0.028 |
Larson | +0.027 |
prolifer | +0.027 |
Neg logit contributions | |
fell | -0.025 |
ihad | -0.020 |
iaries | -0.020 |
inges | -0.020 |
ATES | -0.020 |
Token | terror |
Token ID | 3246 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
fell | +0.025 |
iaries | +0.021 |
ihad | +0.021 |
inges | +0.021 |
ATES | +0.021 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.020 |
synchronized | -0.020 |
Larson | -0.020 |
prolifer | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.013 |
synchronized | +0.013 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.018 |
ihad | -0.016 |
iaries | -0.016 |
inges | -0.016 |
ATES | -0.016 |
Token | Israel |
Token ID | 2692 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
fell | +0.016 |
ihad | +0.014 |
iaries | +0.014 |
inges | +0.014 |
ATES | +0.014 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.013 |
synchronized | -0.013 |
Larson | -0.013 |
prolifer | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.029 |
synchronized | +0.028 |
Larson | +0.028 |
prolifer | +0.028 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.034 |
iaries | -0.034 |
inges | -0.033 |
ATES | -0.033 |
Token | be |
Token ID | 307 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
fell | +0.033 |
ihad | +0.028 |
iaries | +0.028 |
inges | +0.028 |
ATES | +0.028 |
Neg logit contributions | |
rade | -0.024 |
Braun | -0.023 |
synchronized | -0.023 |
Larson | -0.022 |
lear | -0.022 |
Token | deter |
Token ID | 2206 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
synchronized | +0.004 |
Larson | +0.004 |
prolifer | +0.004 |
Neg logit contributions | |
fell | -0.006 |
ihad | -0.006 |
iaries | -0.006 |
inges | -0.005 |
ATES | -0.005 |
Token | red |
Token ID | 445 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rade | +0.239 |
Braun | +0.227 |
synchronized | +0.220 |
Larson | +0.219 |
lear | +0.216 |
Neg logit contributions | |
fell | -0.399 |
ihad | -0.349 |
iaries | -0.346 |
inges | -0.339 |
ATES | -0.337 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
rade | +0.062 |
Braun | +0.059 |
synchronized | +0.058 |
Larson | +0.057 |
lear | +0.057 |
Neg logit contributions | |
fell | -0.082 |
ihad | -0.071 |
iaries | -0.070 |
inges | -0.069 |
ATES | -0.069 |
Token | The |
Token ID | 383 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
rade | +0.004 |
Braun | +0.004 |
synchronized | +0.003 |
prolifer | +0.003 |
Larson | +0.003 |
Neg logit contributions | |
fell | -0.004 |
ihad | -0.004 |
iaries | -0.004 |
ATES | -0.004 |
inges | -0.004 |
Token | government |
Token ID | 1230 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.041 |
iaries | +0.041 |
inges | +0.040 |
ATES | +0.040 |
Neg logit contributions | |
rade | -0.041 |
Braun | -0.039 |
synchronized | -0.038 |
Larson | -0.037 |
lear | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
fell | +0.098 |
ihad | +0.084 |
iaries | +0.084 |
ATES | +0.082 |
inges | +0.082 |
Neg logit contributions | |
rade | -0.076 |
Braun | -0.072 |
synchronized | -0.070 |
Larson | -0.070 |
lear | -0.070 |
Token | presidential |
Token ID | 4787 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
fell | +0.021 |
ihad | +0.018 |
iaries | +0.018 |
inges | +0.017 |
ATES | +0.017 |
Neg logit contributions | |
rade | -0.020 |
Braun | -0.019 |
synchronized | -0.019 |
Larson | -0.019 |
prolifer | -0.019 |
Token | race |
Token ID | 3234 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
rade | +0.071 |
Braun | +0.068 |
synchronized | +0.066 |
Larson | +0.066 |
lear | +0.065 |
Neg logit contributions | |
fell | -0.074 |
iaries | -0.063 |
ihad | -0.063 |
inges | -0.062 |
ATES | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
rade | +0.078 |
Braun | +0.075 |
synchronized | +0.073 |
Larson | +0.072 |
lear | +0.072 |
Neg logit contributions | |
fell | -0.092 |
ihad | -0.079 |
iaries | -0.079 |
inges | -0.077 |
ATES | -0.077 |
Token | lame |
Token ID | 30248 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
fell | +0.016 |
ihad | +0.014 |
iaries | +0.014 |
inges | +0.014 |
ATES | +0.014 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.013 |
Larson | -0.013 |
prolifer | -0.013 |
Token | caric |
Token ID | 33674 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
fell | +0.036 |
ihad | +0.030 |
iaries | +0.030 |
inges | +0.030 |
ATES | +0.030 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.033 |
synchronized | -0.032 |
Larson | -0.032 |
lear | -0.032 |
Token | atures |
Token ID | 6691 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
rade | +0.017 |
Braun | +0.015 |
synchronized | +0.014 |
Larson | +0.014 |
prolifer | +0.014 |
Neg logit contributions | |
fell | -0.059 |
ihad | -0.054 |
iaries | -0.053 |
inges | -0.053 |
ATES | -0.053 |
Token | of |
Token ID | 286 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
rade | +0.302 |
Braun | +0.286 |
synchronized | +0.278 |
lear | +0.278 |
Larson | +0.277 |
Neg logit contributions | |
fell | -0.337 |
ihad | -0.286 |
iaries | -0.283 |
inges | -0.279 |
ATES | -0.277 |
Token | Asians |
Token ID | 30852 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
rade | +0.044 |
Braun | +0.042 |
synchronized | +0.041 |
Larson | +0.041 |
prolifer | +0.041 |
Neg logit contributions | |
fell | -0.044 |
ihad | -0.037 |
iaries | -0.037 |
inges | -0.037 |
ATES | -0.037 |
Token | mas |
Token ID | 12422 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
rade | +0.052 |
Braun | +0.049 |
synchronized | +0.047 |
Larson | +0.047 |
lear | +0.047 |
Neg logit contributions | |
fell | -0.072 |
ihad | -0.062 |
iaries | -0.061 |
inges | -0.060 |
ATES | -0.060 |
Token | quer |
Token ID | 10819 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
inges | +0.012 |
ATES | +0.012 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.014 |
oulder | -0.014 |
Token | ading |
Token ID | 4980 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
fell | +0.038 |
ihad | +0.033 |
iaries | +0.033 |
inges | +0.032 |
ATES | +0.032 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
Larson | -0.024 |
prolifer | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
Larson | +0.005 |
synchronized | +0.005 |
prolifer | +0.005 |
Neg logit contributions | |
fell | -0.006 |
ihad | -0.005 |
iaries | -0.005 |
inges | -0.005 |
ATES | -0.005 |
Token | wrest |
Token ID | 10419 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
rade | +0.008 |
Braun | +0.007 |
synchronized | +0.007 |
Larson | +0.007 |
oulder | +0.007 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.008 |
ATES | -0.008 |
Token | led |
Token ID | 992 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
fell | +0.024 |
ihad | +0.020 |
iaries | +0.020 |
inges | +0.019 |
ATES | +0.019 |
Neg logit contributions | |
rade | -0.029 |
Braun | -0.028 |
synchronized | -0.027 |
Larson | -0.027 |
prolifer | -0.027 |
Token | immortal |
Token ID | 26156 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.006 |
synchronized | +0.006 |
Larson | +0.005 |
prolifer | +0.005 |
Neg logit contributions | |
fell | -0.008 |
ihad | -0.007 |
iaries | -0.007 |
inges | -0.007 |
ATES | -0.007 |
Token | eld |
Token ID | 18441 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
rade | +0.235 |
Braun | +0.226 |
synchronized | +0.221 |
prolifer | +0.219 |
Larson | +0.218 |
Neg logit contributions | |
fell | -0.233 |
ihad | -0.198 |
iaries | -0.196 |
inges | -0.193 |
ATES | -0.191 |
Token | ritch |
Token ID | 46510 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
fell | +0.051 |
ihad | +0.046 |
iaries | +0.046 |
ATES | +0.045 |
inges | +0.045 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
synchronized | -0.014 |
Larson | -0.014 |
prolifer | -0.014 |
Token | mon |
Token ID | 937 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
rade | +0.303 |
Braun | +0.290 |
synchronized | +0.285 |
prolifer | +0.283 |
Larson | +0.281 |
Neg logit contributions | |
fell | -0.330 |
ihad | -0.282 |
iaries | -0.280 |
inges | -0.275 |
ATES | -0.275 |
Token | stros |
Token ID | 48288 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
rade | +0.023 |
Braun | +0.022 |
synchronized | +0.022 |
Larson | +0.021 |
lear | +0.021 |
Neg logit contributions | |
fell | -0.029 |
ihad | -0.025 |
iaries | -0.025 |
ATES | -0.024 |
inges | -0.024 |
Token | ities |
Token ID | 871 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
rade | +0.185 |
Braun | +0.177 |
synchronized | +0.173 |
Larson | +0.172 |
prolifer | +0.171 |
Neg logit contributions | |
fell | -0.194 |
ihad | -0.165 |
iaries | -0.165 |
ATES | -0.161 |
inges | -0.161 |
Token | year |
Token ID | 614 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
rade | +0.038 |
Braun | +0.036 |
synchronized | +0.035 |
Larson | +0.035 |
prolifer | +0.035 |
Neg logit contributions | |
fell | -0.050 |
ihad | -0.043 |
iaries | -0.043 |
inges | -0.042 |
ATES | -0.042 |
Token | after |
Token ID | 706 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
rade | +0.086 |
Braun | +0.081 |
synchronized | +0.080 |
Larson | +0.079 |
prolifer | +0.079 |
Neg logit contributions | |
fell | -0.111 |
ihad | -0.096 |
iaries | -0.096 |
ATES | -0.094 |
inges | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
rade | +0.086 |
Braun | +0.082 |
synchronized | +0.080 |
Larson | +0.079 |
prolifer | +0.079 |
Neg logit contributions | |
fell | -0.101 |
ihad | -0.086 |
iaries | -0.086 |
inges | -0.084 |
ATES | -0.084 |
Token | Turtles |
Token ID | 44356 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
rade | +0.019 |
Braun | +0.018 |
synchronized | +0.017 |
Larson | +0.017 |
prolifer | +0.017 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.016 |
iaries | -0.016 |
ATES | -0.016 |
inges | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
fell | +0.074 |
ihad | +0.064 |
iaries | +0.063 |
inges | +0.063 |
ATES | +0.062 |
Neg logit contributions | |
rade | -0.055 |
Braun | -0.052 |
synchronized | -0.050 |
Larson | -0.050 |
lear | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
rade | +0.029 |
Braun | +0.027 |
synchronized | +0.027 |
Larson | +0.027 |
prolifer | +0.027 |
Neg logit contributions | |
fell | -0.033 |
ihad | -0.028 |
iaries | -0.028 |
inges | -0.027 |
ATES | -0.027 |
Token | nin |
Token ID | 13462 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.001 |
iaries | -0.001 |
ATES | -0.001 |
inges | -0.001 |
Token | jas |
Token ID | 28121 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
fell | +0.036 |
ihad | +0.032 |
iaries | +0.032 |
inges | +0.032 |
ATES | +0.032 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.007 |
prolifer | -0.007 |
Token | erupt |
Token ID | 17866 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
rade | +0.295 |
Braun | +0.281 |
synchronized | +0.275 |
Larson | +0.273 |
lear | +0.272 |
Neg logit contributions | |
fell | -0.339 |
ihad | -0.290 |
iaries | -0.288 |
inges | -0.283 |
ATES | -0.283 |
Token | s |
Token ID | 82 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
rade | +0.043 |
Braun | +0.041 |
synchronized | +0.040 |
Larson | +0.040 |
prolifer | +0.040 |
Neg logit contributions | |
fell | -0.035 |
ihad | -0.029 |
iaries | -0.029 |
inges | -0.029 |
ATES | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.017 |
iaries | +0.017 |
inges | +0.017 |
ATES | +0.017 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.014 |
lear | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.002 |
Larson | +0.002 |
prolifer | +0.002 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | turtles |
Token ID | 36288 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.017 |
iaries | +0.017 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.021 |
Braun | -0.021 |
synchronized | -0.020 |
Larson | -0.020 |
prolifer | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
fell | +0.039 |
ihad | +0.034 |
iaries | +0.033 |
inges | +0.033 |
ATES | +0.033 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.031 |
synchronized | -0.030 |
prolifer | -0.030 |
Larson | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
fell | +0.024 |
ihad | +0.021 |
iaries | +0.020 |
ATES | +0.020 |
inges | +0.020 |
Neg logit contributions | |
rade | -0.022 |
Braun | -0.021 |
synchronized | -0.020 |
prolifer | -0.020 |
Larson | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
inges | +0.006 |
ATES | +0.006 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.007 |
synchronized | -0.006 |
Larson | -0.006 |
prolifer | -0.006 |
Token | H |
Token ID | 39 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.010 |
iaries | +0.010 |
ATES | +0.010 |
inges | +0.010 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.012 |
synchronized | -0.012 |
prolifer | -0.012 |
Larson | -0.012 |
Token | att |
Token ID | 1078 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
rade | +0.047 |
Braun | +0.045 |
synchronized | +0.044 |
Larson | +0.044 |
prolifer | +0.044 |
Neg logit contributions | |
fell | -0.052 |
ihad | -0.045 |
iaries | -0.044 |
inges | -0.044 |
ATES | -0.043 |
Token | if |
Token ID | 361 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
rade | +0.052 |
Braun | +0.050 |
synchronized | +0.049 |
Larson | +0.048 |
prolifer | +0.048 |
Neg logit contributions | |
fell | -0.054 |
ihad | -0.046 |
iaries | -0.045 |
inges | -0.044 |
ATES | -0.044 |
Token | att |
Token ID | 1078 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
fell | +0.272 |
ihad | +0.233 |
iaries | +0.231 |
inges | +0.226 |
ATES | +0.225 |
Neg logit contributions | |
rade | -0.238 |
Braun | -0.228 |
synchronized | -0.224 |
prolifer | -0.222 |
Larson | -0.221 |
Token | eners |
Token ID | 36014 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
rade | +0.038 |
Braun | +0.036 |
synchronized | +0.035 |
Larson | +0.035 |
prolifer | +0.035 |
Neg logit contributions | |
fell | -0.039 |
ihad | -0.033 |
iaries | -0.033 |
ATES | -0.032 |
inges | -0.032 |
Token | [ |
Token ID | 58 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
rade | +0.053 |
Braun | +0.050 |
synchronized | +0.049 |
Larson | +0.048 |
prolifer | +0.048 |
Neg logit contributions | |
fell | -0.070 |
ihad | -0.060 |
iaries | -0.060 |
inges | -0.059 |
ATES | -0.059 |
Token | 28 |
Token ID | 2078 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
rade | +0.079 |
Braun | +0.076 |
synchronized | +0.074 |
Larson | +0.074 |
prolifer | +0.074 |
Neg logit contributions | |
fell | -0.073 |
ihad | -0.061 |
iaries | -0.061 |
inges | -0.060 |
ATES | -0.060 |
Token | ] |
Token ID | 60 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.041 |
iaries | +0.041 |
inges | +0.040 |
ATES | +0.040 |
Neg logit contributions | |
rade | -0.035 |
Braun | -0.033 |
synchronized | -0.032 |
Larson | -0.032 |
prolifer | -0.032 |
Token | lose |
Token ID | 4425 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.014 |
synchronized | +0.013 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.016 |
ihad | -0.014 |
iaries | -0.014 |
ATES | -0.014 |
inges | -0.014 |
Token | out |
Token ID | 503 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
fell | +0.190 |
iaries | +0.166 |
ihad | +0.166 |
inges | +0.162 |
ATES | +0.162 |
Neg logit contributions | |
rade | -0.131 |
Braun | -0.124 |
synchronized | -0.121 |
Larson | -0.120 |
prolifer | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.009 |
iaries | +0.009 |
ATES | +0.009 |
inges | +0.009 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.007 |
prolifer | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
ATES | +0.013 |
inges | +0.013 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.013 |
synchronized | -0.012 |
Larson | -0.012 |
prolifer | -0.012 |
Token | oret |
Token ID | 9997 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.041 |
iaries | +0.041 |
inges | +0.040 |
ATES | +0.040 |
Neg logit contributions | |
rade | -0.040 |
Braun | -0.038 |
synchronized | -0.037 |
Larson | -0.037 |
prolifer | -0.037 |
Token | ically |
Token ID | 1146 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
rade | +0.175 |
Braun | +0.169 |
synchronized | +0.167 |
Larson | +0.166 |
prolifer | +0.166 |
Neg logit contributions | |
fell | -0.065 |
ihad | -0.046 |
iaries | -0.046 |
ATES | -0.044 |
inges | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
fell | +0.299 |
ihad | +0.259 |
iaries | +0.258 |
inges | +0.253 |
ATES | +0.253 |
Neg logit contributions | |
rade | -0.228 |
Braun | -0.217 |
synchronized | -0.212 |
Larson | -0.210 |
prolifer | -0.209 |
Token | But |
Token ID | 887 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
fell | +0.021 |
ihad | +0.018 |
iaries | +0.018 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.018 |
Braun | -0.017 |
synchronized | -0.016 |
Larson | -0.016 |
prolifer | -0.016 |
Token | while |
Token ID | 981 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
fell | +0.015 |
ihad | +0.013 |
iaries | +0.013 |
ATES | +0.012 |
inges | +0.012 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.011 |
synchronized | -0.010 |
lear | -0.010 |
Larson | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
fell | +0.033 |
ihad | +0.028 |
iaries | +0.028 |
inges | +0.027 |
ATES | +0.027 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
Larson | -0.024 |
prolifer | -0.024 |
Token | outcome |
Token ID | 8055 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
fell | +0.032 |
ihad | +0.028 |
iaries | +0.028 |
inges | +0.027 |
ATES | +0.027 |
Neg logit contributions | |
rade | -0.027 |
Braun | -0.026 |
synchronized | -0.026 |
Larson | -0.025 |
prolifer | -0.025 |
Token | interested |
Token ID | 4609 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
fell | +0.006 |
ihad | +0.005 |
iaries | +0.005 |
ATES | +0.005 |
inges | +0.005 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.008 |
oulder | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
fell | +0.003 |
ihad | +0.002 |
iaries | +0.002 |
inges | +0.002 |
ATES | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token | such |
Token ID | 884 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
fell | +0.031 |
ihad | +0.027 |
iaries | +0.027 |
inges | +0.026 |
ATES | +0.026 |
Neg logit contributions | |
rade | -0.025 |
Braun | -0.024 |
synchronized | -0.023 |
Larson | -0.023 |
oulder | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
fell | +0.040 |
ihad | +0.034 |
iaries | +0.034 |
inges | +0.034 |
ATES | +0.034 |
Neg logit contributions | |
rade | -0.033 |
Braun | -0.031 |
synchronized | -0.030 |
Larson | -0.030 |
oulder | -0.030 |
Token | surg |
Token ID | 19797 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
fell | +0.016 |
ihad | +0.014 |
iaries | +0.014 |
ATES | +0.014 |
inges | +0.014 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
oulder | -0.010 |
Token | ically |
Token ID | 1146 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
fell | +0.017 |
ihad | +0.012 |
iaries | +0.012 |
ATES | +0.012 |
inges | +0.012 |
Neg logit contributions | |
rade | -0.049 |
Braun | -0.048 |
synchronized | -0.047 |
Larson | -0.047 |
prolifer | -0.047 |
Token | implanted |
Token ID | 40740 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
fell | +0.279 |
ihad | +0.243 |
iaries | +0.241 |
inges | +0.237 |
ATES | +0.236 |
Neg logit contributions | |
rade | -0.199 |
Braun | -0.187 |
oulder | -0.182 |
Larson | -0.182 |
lear | -0.181 |
Token | device |
Token ID | 3335 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
fell | +0.188 |
ihad | +0.163 |
iaries | +0.163 |
inges | +0.159 |
ATES | +0.159 |
Neg logit contributions | |
rade | -0.132 |
Braun | -0.125 |
synchronized | -0.122 |
Larson | -0.121 |
oulder | -0.120 |
Token | ? |
Token ID | 30 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
rade | +0.038 |
Braun | +0.036 |
synchronized | +0.035 |
Larson | +0.035 |
lear | +0.035 |
Neg logit contributions | |
fell | -0.042 |
ihad | -0.035 |
iaries | -0.035 |
inges | -0.035 |
ATES | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
fell | +0.079 |
ihad | +0.067 |
iaries | +0.067 |
ATES | +0.065 |
inges | +0.065 |
Neg logit contributions | |
rade | -0.070 |
Braun | -0.066 |
synchronized | -0.066 |
prolifer | -0.065 |
lear | -0.065 |
Token | � |
Token ID | 447 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
rade | +0.023 |
Braun | +0.022 |
synchronized | +0.022 |
Larson | +0.021 |
prolifer | +0.021 |
Neg logit contributions | |
fell | -0.032 |
ihad | -0.028 |
iaries | -0.028 |
inges | -0.027 |
ATES | -0.027 |
Token | is |
Token ID | 318 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
fell | +0.201 |
ihad | +0.175 |
iaries | +0.175 |
ATES | +0.172 |
inges | +0.172 |
Neg logit contributions | |
rade | -0.124 |
Braun | -0.117 |
synchronized | -0.115 |
Larson | -0.113 |
prolifer | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
rade | +0.082 |
Braun | +0.078 |
synchronized | +0.076 |
Larson | +0.076 |
prolifer | +0.075 |
Neg logit contributions | |
fell | -0.096 |
ihad | -0.082 |
iaries | -0.082 |
inges | -0.080 |
ATES | -0.080 |
Token | CEO |
Token ID | 6123 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.008 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.009 |
ATES | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
rade | +0.067 |
Braun | +0.064 |
synchronized | +0.063 |
Larson | +0.062 |
prolifer | +0.062 |
Neg logit contributions | |
fell | -0.078 |
ihad | -0.067 |
iaries | -0.067 |
ATES | -0.065 |
inges | -0.065 |
Token | Kol |
Token ID | 25910 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
rade | +0.014 |
Braun | +0.014 |
synchronized | +0.013 |
Larson | +0.013 |
prolifer | +0.013 |
Neg logit contributions | |
fell | -0.016 |
ihad | -0.014 |
iaries | -0.014 |
inges | -0.013 |
ATES | -0.013 |
Token | umb |
Token ID | 2178 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
rade | +0.030 |
Braun | +0.029 |
synchronized | +0.028 |
lear | +0.028 |
oulder | +0.028 |
Neg logit contributions | |
fell | -0.037 |
ihad | -0.032 |
iaries | -0.032 |
ATES | -0.032 |
inges | -0.031 |
Token | ini |
Token ID | 5362 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
fell | +0.273 |
ihad | +0.234 |
iaries | +0.232 |
inges | +0.227 |
ATES | +0.226 |
Neg logit contributions | |
rade | -0.236 |
Braun | -0.226 |
synchronized | -0.222 |
Larson | -0.220 |
prolifer | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
fell | +0.090 |
ihad | +0.076 |
iaries | +0.076 |
inges | +0.074 |
ATES | +0.074 |
Neg logit contributions | |
rade | -0.082 |
Braun | -0.079 |
synchronized | -0.077 |
Larson | -0.076 |
prolifer | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
rade | +0.022 |
Braun | +0.021 |
synchronized | +0.021 |
Larson | +0.021 |
prolifer | +0.021 |
Neg logit contributions | |
fell | -0.029 |
ihad | -0.025 |
iaries | -0.025 |
inges | -0.024 |
ATES | -0.024 |
Token | company |
Token ID | 1664 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.012 |
synchronized | +0.011 |
Larson | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.011 |
iaries | -0.011 |
inges | -0.011 |
ATES | -0.011 |
Token | affiliated |
Token ID | 18552 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
inges | +0.002 |
ATES | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token | It |
Token ID | 632 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
rade | +0.004 |
Braun | +0.004 |
synchronized | +0.004 |
prolifer | +0.004 |
lear | +0.004 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.004 |
iaries | -0.004 |
ATES | -0.004 |
inges | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
rade | +0.026 |
Braun | +0.024 |
synchronized | +0.024 |
Larson | +0.024 |
lear | +0.024 |
Neg logit contributions | |
fell | -0.034 |
ihad | -0.030 |
iaries | -0.029 |
inges | -0.029 |
ATES | -0.029 |
Token | � |
Token ID | 247 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
fell | +0.009 |
ihad | +0.008 |
iaries | +0.008 |
inges | +0.008 |
ATES | +0.008 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
synchronized | -0.004 |
Larson | -0.004 |
prolifer | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
rade | +0.008 |
Braun | +0.008 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.007 |
ihad | -0.006 |
iaries | -0.006 |
ATES | -0.006 |
inges | -0.006 |
Token | tough |
Token ID | 5802 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
fell | +0.036 |
ihad | +0.031 |
iaries | +0.031 |
ATES | +0.031 |
inges | +0.031 |
Neg logit contributions | |
rade | -0.029 |
Braun | -0.028 |
synchronized | -0.027 |
Larson | -0.027 |
lear | -0.027 |
Token | recovering |
Token ID | 20222 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
fell | +0.020 |
ihad | +0.017 |
iaries | +0.017 |
ATES | +0.017 |
inges | +0.017 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
synchronized | -0.015 |
Larson | -0.014 |
prolifer | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
fell | +0.295 |
ihad | +0.253 |
iaries | +0.252 |
inges | +0.247 |
ATES | +0.247 |
Neg logit contributions | |
rade | -0.241 |
Braun | -0.229 |
synchronized | -0.224 |
prolifer | -0.221 |
lear | -0.221 |
Token | holiday |
Token ID | 9912 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
fell | +0.031 |
ihad | +0.026 |
iaries | +0.026 |
inges | +0.026 |
ATES | +0.026 |
Neg logit contributions | |
rade | -0.026 |
Braun | -0.025 |
synchronized | -0.024 |
Larson | -0.024 |
prolifer | -0.024 |
Token | weekends |
Token ID | 21511 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
rade | +0.041 |
Braun | +0.039 |
synchronized | +0.038 |
lear | +0.038 |
Larson | +0.038 |
Neg logit contributions | |
fell | -0.049 |
ihad | -0.042 |
iaries | -0.042 |
inges | -0.041 |
ATES | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
rade | +0.028 |
Braun | +0.027 |
synchronized | +0.026 |
lear | +0.026 |
Larson | +0.026 |
Neg logit contributions | |
fell | -0.037 |
ihad | -0.032 |
iaries | -0.032 |
inges | -0.031 |
ATES | -0.031 |
Token | I |
Token ID | 314 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
synchronized | +0.005 |
prolifer | +0.005 |
lear | +0.005 |
Neg logit contributions | |
fell | -0.006 |
ihad | -0.005 |
iaries | -0.005 |
ATES | -0.005 |
inges | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
fell | +0.122 |
ihad | +0.104 |
iaries | +0.104 |
inges | +0.102 |
ATES | +0.102 |
Neg logit contributions | |
rade | -0.105 |
Braun | -0.100 |
synchronized | -0.098 |
Larson | -0.097 |
prolifer | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
inges | +0.001 |
ATES | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
lear | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -7.47e-05 |
Pos logit contributions | |
fell | +0.022 |
ihad | +0.019 |
iaries | +0.019 |
ATES | +0.019 |
inges | +0.019 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.013 |
synchronized | -0.013 |
lear | -0.013 |
Larson | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
rade | +0.000 |
Braun | +0.000 |
synchronized | +0.000 |
Larson | +0.000 |
prolifer | +0.000 |
Neg logit contributions | |
fell | -0.000 |
ihad | -0.000 |
iaries | -0.000 |
inges | -0.000 |
ATES | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
fell | +0.034 |
ihad | +0.029 |
iaries | +0.029 |
inges | +0.029 |
ATES | +0.029 |
Neg logit contributions | |
rade | -0.028 |
Braun | -0.027 |
synchronized | -0.026 |
Larson | -0.026 |
prolifer | -0.026 |
Token | not |
Token ID | 407 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
fell | +0.046 |
ihad | +0.039 |
iaries | +0.039 |
ATES | +0.038 |
inges | +0.038 |
Neg logit contributions | |
rade | -0.043 |
Braun | -0.041 |
synchronized | -0.040 |
Larson | -0.039 |
lear | -0.039 |
Token | what |
Token ID | 644 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
fell | +0.044 |
ihad | +0.038 |
iaries | +0.038 |
inges | +0.037 |
ATES | +0.037 |
Neg logit contributions | |
rade | -0.040 |
Braun | -0.039 |
synchronized | -0.038 |
Larson | -0.037 |
prolifer | -0.037 |
Token | I |
Token ID | 314 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
fell | +0.033 |
ihad | +0.028 |
iaries | +0.028 |
ATES | +0.028 |
inges | +0.028 |
Neg logit contributions | |
rade | -0.027 |
Braun | -0.026 |
synchronized | -0.026 |
Larson | -0.025 |
prolifer | -0.025 |
Token | want |
Token ID | 765 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.010 |
synchronized | +0.010 |
Larson | +0.010 |
prolifer | +0.010 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
ATES | -0.012 |
inges | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
rade | +0.061 |
Braun | +0.058 |
synchronized | +0.057 |
Larson | +0.056 |
prolifer | +0.056 |
Neg logit contributions | |
fell | -0.075 |
ihad | -0.064 |
iaries | -0.064 |
ATES | -0.063 |
inges | -0.062 |
Token | I |
Token ID | 314 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.011 |
iaries | +0.011 |
inges | +0.011 |
ATES | +0.011 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
prolifer | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.012 |
synchronized | +0.011 |
Larson | +0.011 |
oulder | +0.011 |
Neg logit contributions | |
fell | -0.013 |
iaries | -0.011 |
ihad | -0.011 |
inges | -0.011 |
ATES | -0.011 |
Token | looms |
Token ID | 46234 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
fell | +0.043 |
iaries | +0.037 |
ihad | +0.037 |
inges | +0.036 |
ATES | +0.036 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.032 |
synchronized | -0.031 |
Larson | -0.031 |
lear | -0.031 |
Token | are |
Token ID | 389 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
fell | +0.049 |
ihad | +0.042 |
iaries | +0.042 |
inges | +0.041 |
ATES | +0.041 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.032 |
lear | -0.031 |
synchronized | -0.031 |
oulder | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
fell | +0.008 |
iaries | +0.007 |
ihad | +0.007 |
inges | +0.007 |
ATES | +0.007 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
lear | -0.005 |
Larson | -0.005 |
synchronized | -0.005 |
Token | display |
Token ID | 3359 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
fell | +0.121 |
iaries | +0.107 |
ihad | +0.106 |
inges | +0.105 |
ATES | +0.105 |
Neg logit contributions | |
rade | -0.063 |
Braun | -0.059 |
synchronized | -0.057 |
Larson | -0.056 |
lear | -0.056 |
Token | at |
Token ID | 379 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
rade | +0.039 |
Braun | +0.036 |
lear | +0.035 |
synchronized | +0.035 |
Larson | +0.035 |
Neg logit contributions | |
fell | -0.053 |
ihad | -0.046 |
iaries | -0.046 |
inges | -0.045 |
ATES | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
fell | +0.043 |
ihad | +0.037 |
iaries | +0.037 |
inges | +0.036 |
ATES | +0.036 |
Neg logit contributions | |
rade | -0.036 |
Braun | -0.034 |
synchronized | -0.033 |
Larson | -0.033 |
lear | -0.033 |
Token | Shu |
Token ID | 32344 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
fell | +0.054 |
ihad | +0.046 |
iaries | +0.046 |
inges | +0.045 |
ATES | +0.045 |
Neg logit contributions | |
rade | -0.046 |
Braun | -0.044 |
synchronized | -0.043 |
Larson | -0.043 |
prolifer | -0.043 |
Token | Bro |
Token ID | 2806 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
rade | +0.086 |
Braun | +0.083 |
synchronized | +0.081 |
Larson | +0.080 |
prolifer | +0.080 |
Neg logit contributions | |
fell | -0.076 |
ihad | -0.064 |
iaries | -0.064 |
ATES | -0.062 |
inges | -0.062 |
Token | cade |
Token ID | 46395 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
rade | +0.010 |
Braun | +0.010 |
synchronized | +0.009 |
Larson | +0.009 |
prolifer | +0.009 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.008 |
ATES | -0.008 |
Token | Museum |
Token ID | 9594 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
fell | +0.038 |
iaries | +0.032 |
ihad | +0.032 |
inges | +0.031 |
ATES | +0.031 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.030 |
synchronized | -0.030 |
Larson | -0.029 |
lear | -0.029 |
Token | ING |
Token ID | 2751 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.008 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.008 |
ihad | -0.007 |
iaries | -0.007 |
ATES | -0.007 |
inges | -0.007 |
Token | S |
Token ID | 311 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
fell | +0.009 |
ihad | +0.007 |
iaries | +0.007 |
ATES | +0.007 |
inges | +0.007 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | AV |
Token ID | 10116 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
rade | +0.016 |
Braun | +0.015 |
synchronized | +0.015 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.013 |
ihad | -0.010 |
iaries | -0.010 |
inges | -0.010 |
ATES | -0.010 |
Token | V |
Token ID | 53 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
fell | +0.031 |
ihad | +0.025 |
iaries | +0.025 |
ATES | +0.025 |
inges | +0.025 |
Neg logit contributions | |
rade | -0.043 |
Braun | -0.041 |
synchronized | -0.041 |
Larson | -0.040 |
prolifer | -0.040 |
Token | Y |
Token ID | 56 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.009 |
iaries | +0.009 |
inges | +0.009 |
ATES | +0.009 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.013 |
synchronized | -0.012 |
Larson | -0.012 |
lear | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
rade | +0.054 |
Braun | +0.051 |
synchronized | +0.050 |
Larson | +0.050 |
prolifer | +0.050 |
Neg logit contributions | |
fell | -0.054 |
ihad | -0.046 |
iaries | -0.046 |
ATES | -0.045 |
inges | -0.045 |
Token | Hamilton |
Token ID | 45405 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
fell | +0.077 |
ihad | +0.065 |
iaries | +0.065 |
ATES | +0.063 |
inges | +0.063 |
Neg logit contributions | |
rade | -0.075 |
Braun | -0.072 |
synchronized | -0.071 |
prolifer | -0.070 |
Larson | -0.070 |
Token | had |
Token ID | 550 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.041 |
iaries | +0.041 |
inges | +0.040 |
ATES | +0.040 |
Neg logit contributions | |
rade | -0.036 |
Braun | -0.034 |
synchronized | -0.033 |
oulder | -0.033 |
Larson | -0.033 |
Token | speed |
Token ID | 2866 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
rade | +0.038 |
Braun | +0.036 |
synchronized | +0.035 |
Larson | +0.035 |
oulder | +0.035 |
Neg logit contributions | |
fell | -0.045 |
ihad | -0.038 |
iaries | -0.038 |
inges | -0.037 |
ATES | -0.037 |
Token | but |
Token ID | 475 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
fell | +0.080 |
ihad | +0.069 |
iaries | +0.069 |
inges | +0.068 |
ATES | +0.067 |
Neg logit contributions | |
rade | -0.062 |
Braun | -0.058 |
synchronized | -0.057 |
Larson | -0.057 |
oulder | -0.056 |
Token | it |
Token ID | 340 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
rade | +0.048 |
Braun | +0.046 |
synchronized | +0.045 |
Larson | +0.044 |
prolifer | +0.044 |
Neg logit contributions | |
fell | -0.063 |
ihad | -0.055 |
iaries | -0.055 |
inges | -0.053 |
ATES | -0.053 |
Token | promises |
Token ID | 10497 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
fell | +0.141 |
ihad | +0.121 |
iaries | +0.120 |
inges | +0.118 |
ATES | +0.118 |
Neg logit contributions | |
rade | -0.116 |
Braun | -0.111 |
synchronized | -0.108 |
Larson | -0.107 |
prolifer | -0.107 |
Token | from |
Token ID | 422 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
rade | +0.033 |
Braun | +0.031 |
synchronized | +0.030 |
Larson | +0.030 |
prolifer | +0.030 |
Neg logit contributions | |
fell | -0.042 |
ihad | -0.036 |
iaries | -0.036 |
ATES | -0.035 |
inges | -0.035 |
Token | all |
Token ID | 477 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
fell | +0.041 |
iaries | +0.035 |
ihad | +0.035 |
inges | +0.034 |
ATES | +0.034 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.032 |
synchronized | -0.032 |
Larson | -0.031 |
prolifer | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
fell | +0.027 |
iaries | +0.023 |
ihad | +0.023 |
inges | +0.023 |
ATES | +0.023 |
Neg logit contributions | |
rade | -0.024 |
Braun | -0.023 |
synchronized | -0.023 |
Larson | -0.023 |
prolifer | -0.023 |
Token | Muslims |
Token ID | 7045 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
fell | +0.005 |
ihad | +0.004 |
iaries | +0.004 |
inges | +0.004 |
ATES | +0.004 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.005 |
prolifer | -0.005 |
Token | present |
Token ID | 1944 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
rade | +0.033 |
Braun | +0.031 |
synchronized | +0.031 |
Larson | +0.030 |
prolifer | +0.030 |
Neg logit contributions | |
fell | -0.044 |
ihad | -0.038 |
iaries | -0.038 |
inges | -0.037 |
ATES | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
fell | +0.135 |
ihad | +0.117 |
iaries | +0.117 |
ATES | +0.114 |
inges | +0.114 |
Neg logit contributions | |
rade | -0.103 |
Braun | -0.097 |
synchronized | -0.095 |
Larson | -0.094 |
lear | -0.094 |
Token | they |
Token ID | 484 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
fell | +0.019 |
ihad | +0.017 |
iaries | +0.017 |
inges | +0.017 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.013 |
Larson | -0.013 |
prolifer | -0.013 |
Token | would |
Token ID | 561 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
rade | +0.024 |
Braun | +0.023 |
synchronized | +0.022 |
Larson | +0.022 |
prolifer | +0.022 |
Neg logit contributions | |
fell | -0.041 |
ihad | -0.036 |
iaries | -0.036 |
ATES | -0.035 |
inges | -0.035 |
Token | indeed |
Token ID | 5600 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
rade | +0.074 |
Braun | +0.071 |
synchronized | +0.069 |
prolifer | +0.069 |
Larson | +0.069 |
Neg logit contributions | |
fell | -0.092 |
ihad | -0.079 |
iaries | -0.079 |
inges | -0.077 |
ATES | -0.077 |
Token | abide |
Token ID | 27851 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
fell | +0.024 |
ihad | +0.020 |
iaries | +0.020 |
inges | +0.020 |
ATES | +0.020 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
Larson | -0.018 |
prolifer | -0.018 |
Token | took |
Token ID | 1718 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rade | +0.007 |
Braun | +0.007 |
synchronized | +0.007 |
lear | +0.006 |
oulder | +0.006 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
ATES | -0.009 |
inges | -0.009 |
Token | photographs |
Token ID | 12566 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
fell | +0.088 |
ihad | +0.076 |
iaries | +0.076 |
inges | +0.074 |
ATES | +0.074 |
Neg logit contributions | |
rade | -0.069 |
Braun | -0.066 |
synchronized | -0.064 |
Larson | -0.064 |
prolifer | -0.063 |
Token | for |
Token ID | 329 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
rade | +0.043 |
Braun | +0.041 |
lear | +0.040 |
synchronized | +0.040 |
Larson | +0.039 |
Neg logit contributions | |
fell | -0.053 |
ihad | -0.045 |
iaries | -0.045 |
ATES | -0.044 |
inges | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.011 |
synchronized | +0.011 |
lear | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
ATES | -0.011 |
inges | -0.011 |
Token | project |
Token ID | 1628 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.010 |
iaries | +0.010 |
ATES | +0.009 |
inges | +0.009 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.009 |
lear | -0.009 |
Larson | -0.009 |
Token | - |
Token ID | 532 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
rade | +0.045 |
Braun | +0.043 |
synchronized | +0.042 |
Larson | +0.041 |
lear | +0.041 |
Neg logit contributions | |
fell | -0.061 |
ihad | -0.052 |
iaries | -0.052 |
ATES | -0.051 |
inges | -0.051 |
Token | thank |
Token ID | 5875 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
fell | +0.043 |
ihad | +0.037 |
iaries | +0.037 |
ATES | +0.036 |
inges | +0.036 |
Neg logit contributions | |
rade | -0.031 |
Braun | -0.029 |
synchronized | -0.028 |
Larson | -0.028 |
prolifer | -0.028 |
Token | you |
Token ID | 345 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
rade | +0.127 |
Braun | +0.122 |
synchronized | +0.119 |
Larson | +0.118 |
prolifer | +0.117 |
Neg logit contributions | |
fell | -0.130 |
ihad | -0.111 |
iaries | -0.111 |
inges | -0.108 |
ATES | -0.108 |
Token | ! |
Token ID | 0 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
inges | +0.002 |
ATES | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token | P |
Token ID | 350 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
fell | +0.063 |
ihad | +0.054 |
iaries | +0.054 |
ATES | +0.053 |
inges | +0.053 |
Neg logit contributions | |
rade | -0.056 |
Braun | -0.053 |
synchronized | -0.052 |
Larson | -0.052 |
prolifer | -0.051 |
Token | sh |
Token ID | 1477 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
rade | +0.048 |
Braun | +0.046 |
synchronized | +0.045 |
Larson | +0.045 |
lear | +0.044 |
Neg logit contributions | |
fell | -0.047 |
ihad | -0.039 |
iaries | -0.039 |
inges | -0.038 |
ATES | -0.038 |
Token | � |
Token ID | 447 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
fell | +0.005 |
ihad | +0.004 |
iaries | +0.004 |
inges | +0.004 |
ATES | +0.004 |
Neg logit contributions | |
rade | -0.004 |
Braun | -0.003 |
synchronized | -0.003 |
Larson | -0.003 |
lear | -0.003 |
Token | � |
Token ID | 247 |
Feature activation | -2.60e-03 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
prolifer | +0.003 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.005 |
iaries | -0.005 |
inges | -0.005 |
ATES | -0.005 |
Token | d |
Token ID | 67 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
rade | +0.002 |
Braun | +0.002 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.002 |
ihad | -0.002 |
iaries | -0.002 |
inges | -0.002 |
ATES | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.010 |
iaries | +0.010 |
inges | +0.010 |
ATES | +0.010 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.009 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
rade | +0.003 |
Braun | +0.003 |
synchronized | +0.003 |
Larson | +0.003 |
prolifer | +0.003 |
Neg logit contributions | |
fell | -0.004 |
iaries | -0.003 |
ihad | -0.003 |
inges | -0.003 |
ATES | -0.003 |
Token | if |
Token ID | 611 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
rade | +0.001 |
Braun | +0.001 |
synchronized | +0.001 |
Larson | +0.001 |
prolifer | +0.001 |
Neg logit contributions | |
fell | -0.001 |
ihad | -0.001 |
iaries | -0.001 |
ATES | -0.001 |
inges | -0.001 |
Token | right |
Token ID | 826 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
fell | +0.008 |
iaries | +0.007 |
ihad | +0.007 |
ATES | +0.007 |
inges | +0.007 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.007 |
synchronized | -0.007 |
Larson | -0.007 |
prolifer | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
rade | +0.099 |
Braun | +0.095 |
synchronized | +0.093 |
Larson | +0.092 |
prolifer | +0.092 |
Neg logit contributions | |
fell | -0.109 |
ihad | -0.092 |
iaries | -0.092 |
inges | -0.090 |
ATES | -0.090 |
Token | wing |
Token ID | 5469 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.009 |
iaries | +0.009 |
ATES | +0.009 |
inges | +0.009 |
Neg logit contributions | |
rade | -0.024 |
Braun | -0.024 |
synchronized | -0.023 |
Larson | -0.023 |
prolifer | -0.023 |
Token | ers |
Token ID | 364 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
fell | +0.277 |
ihad | +0.237 |
iaries | +0.236 |
ATES | +0.231 |
inges | +0.231 |
Neg logit contributions | |
rade | -0.238 |
Braun | -0.227 |
synchronized | -0.222 |
Larson | -0.220 |
prolifer | -0.220 |
Token | had |
Token ID | 550 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
rade | +0.101 |
Braun | +0.096 |
synchronized | +0.094 |
Larson | +0.093 |
prolifer | +0.092 |
Neg logit contributions | |
fell | -0.129 |
ihad | -0.111 |
iaries | -0.111 |
inges | -0.109 |
ATES | -0.109 |
Token | have |
Token ID | 423 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
rade | +0.021 |
Braun | +0.020 |
synchronized | +0.020 |
Larson | +0.020 |
prolifer | +0.020 |
Neg logit contributions | |
fell | -0.023 |
ihad | -0.020 |
iaries | -0.020 |
ATES | -0.019 |
inges | -0.019 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
fell | +0.046 |
ihad | +0.040 |
iaries | +0.040 |
ATES | +0.039 |
inges | +0.039 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.030 |
synchronized | -0.029 |
Larson | -0.029 |
lear | -0.029 |
Token | had |
Token ID | 550 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
rade | +0.015 |
Braun | +0.014 |
synchronized | +0.014 |
Larson | +0.014 |
prolifer | +0.014 |
Neg logit contributions | |
fell | -0.023 |
ihad | -0.020 |
iaries | -0.020 |
ATES | -0.019 |
inges | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
rade | +0.015 |
Braun | +0.014 |
synchronized | +0.014 |
Larson | +0.014 |
prolifer | +0.014 |
Neg logit contributions | |
fell | -0.021 |
ihad | -0.018 |
iaries | -0.018 |
inges | -0.018 |
ATES | -0.018 |
Token | � |
Token ID | 447 |
Feature activation | +5.37e-04 |
Pos logit contributions | |
rade | +0.027 |
Braun | +0.026 |
synchronized | +0.025 |
Larson | +0.025 |
prolifer | +0.025 |
Neg logit contributions | |
fell | -0.032 |
ihad | -0.028 |
iaries | -0.027 |
ATES | -0.027 |
inges | -0.027 |
Token | � |
Token ID | 251 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
fell | +0.000 |
ihad | +0.000 |
iaries | +0.000 |
ATES | +0.000 |
inges | +0.000 |
Neg logit contributions | |
rade | -0.000 |
Braun | -0.000 |
synchronized | -0.000 |
Larson | -0.000 |
prolifer | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
rade | +0.026 |
Braun | +0.025 |
synchronized | +0.024 |
Larson | +0.024 |
prolifer | +0.024 |
Neg logit contributions | |
fell | -0.030 |
ihad | -0.026 |
iaries | -0.026 |
ATES | -0.025 |
inges | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
rade | +0.027 |
Braun | +0.026 |
synchronized | +0.025 |
Larson | +0.025 |
prolifer | +0.025 |
Neg logit contributions | |
fell | -0.031 |
ihad | -0.026 |
iaries | -0.026 |
inges | -0.026 |
ATES | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | +3.44e-05 |
Pos logit contributions | |
rade | +0.025 |
Braun | +0.024 |
synchronized | +0.024 |
prolifer | +0.023 |
Larson | +0.023 |
Neg logit contributions | |
fell | -0.027 |
ihad | -0.023 |
iaries | -0.023 |
ATES | -0.023 |
inges | -0.023 |
Token | current |
Token ID | 1459 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
fell | +0.000 |
ihad | +0.000 |
iaries | +0.000 |
inges | +0.000 |
ATES | +0.000 |
Neg logit contributions | |
rade | -0.000 |
Braun | -0.000 |
synchronized | -0.000 |
Larson | -0.000 |
lear | -0.000 |
Token | round |
Token ID | 2835 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
fell | +0.030 |
ihad | +0.025 |
iaries | +0.025 |
inges | +0.025 |
ATES | +0.025 |
Neg logit contributions | |
rade | -0.031 |
Braun | -0.029 |
synchronized | -0.029 |
lear | -0.028 |
Larson | -0.028 |
Token | One |
Token ID | 3198 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
fell | +0.001 |
ihad | +0.001 |
iaries | +0.001 |
inges | +0.001 |
ATES | +0.001 |
Neg logit contributions | |
rade | -0.001 |
Braun | -0.001 |
synchronized | -0.001 |
Larson | -0.001 |
prolifer | -0.001 |
Token | such |
Token ID | 884 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
rade | +0.056 |
Braun | +0.054 |
synchronized | +0.053 |
Larson | +0.053 |
prolifer | +0.052 |
Neg logit contributions | |
fell | -0.065 |
ihad | -0.056 |
iaries | -0.056 |
inges | -0.055 |
ATES | -0.055 |
Token | example |
Token ID | 1672 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
fell | +0.018 |
ihad | +0.015 |
iaries | +0.015 |
inges | +0.015 |
ATES | +0.015 |
Neg logit contributions | |
rade | -0.018 |
Braun | -0.017 |
synchronized | -0.017 |
Larson | -0.017 |
prolifer | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
fell | +0.080 |
ihad | +0.070 |
iaries | +0.069 |
inges | +0.068 |
ATES | +0.068 |
Neg logit contributions | |
rade | -0.060 |
Braun | -0.057 |
synchronized | -0.056 |
Larson | -0.055 |
prolifer | -0.055 |
Token | seen |
Token ID | 1775 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
fell | +0.051 |
ihad | +0.044 |
iaries | +0.044 |
inges | +0.043 |
ATES | +0.043 |
Neg logit contributions | |
rade | -0.043 |
Braun | -0.041 |
synchronized | -0.040 |
Larson | -0.040 |
prolifer | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
rade | +0.058 |
Braun | +0.055 |
synchronized | +0.054 |
Larson | +0.053 |
prolifer | +0.053 |
Neg logit contributions | |
fell | -0.075 |
ihad | -0.064 |
iaries | -0.064 |
inges | -0.063 |
ATES | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
rade | +0.012 |
Braun | +0.011 |
synchronized | +0.011 |
Larson | +0.011 |
prolifer | +0.011 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
ATES | -0.011 |
inges | -0.011 |
Token | prison |
Token ID | 3770 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
rade | +0.015 |
Braun | +0.014 |
synchronized | +0.014 |
Larson | +0.014 |
prolifer | +0.014 |
Neg logit contributions | |
fell | -0.017 |
ihad | -0.015 |
iaries | -0.015 |
inges | -0.015 |
ATES | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
fell | +0.096 |
iaries | +0.082 |
ihad | +0.082 |
inges | +0.080 |
ATES | +0.080 |
Neg logit contributions | |
rade | -0.077 |
Braun | -0.073 |
synchronized | -0.071 |
Larson | -0.071 |
lear | -0.071 |
Token | where |
Token ID | 810 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
rade | +0.006 |
Braun | +0.006 |
synchronized | +0.006 |
Larson | +0.006 |
prolifer | +0.006 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.009 |
ATES | -0.009 |
Token | we |
Token ID | 356 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
rade | +0.076 |
Braun | +0.073 |
synchronized | +0.071 |
Larson | +0.071 |
prolifer | +0.070 |
Neg logit contributions | |
fell | -0.088 |
ihad | -0.076 |
iaries | -0.076 |
inges | -0.074 |
ATES | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
fell | +0.018 |
ihad | +0.015 |
iaries | +0.015 |
inges | +0.015 |
ATES | +0.015 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
Larson | -0.015 |
synchronized | -0.015 |
lear | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
fell | +0.026 |
ihad | +0.023 |
iaries | +0.023 |
inges | +0.022 |
ATES | +0.022 |
Neg logit contributions | |
rade | -0.023 |
Braun | -0.022 |
synchronized | -0.021 |
Larson | -0.021 |
prolifer | -0.021 |
Token | Three |
Token ID | 12510 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
fell | +0.025 |
ihad | +0.021 |
iaries | +0.021 |
inges | +0.021 |
ATES | +0.021 |
Neg logit contributions | |
rade | -0.024 |
Braun | -0.023 |
synchronized | -0.023 |
Larson | -0.023 |
lear | -0.022 |
Token | weeks |
Token ID | 2745 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
fell | +0.064 |
ihad | +0.055 |
iaries | +0.055 |
inges | +0.054 |
ATES | +0.054 |
Neg logit contributions | |
rade | -0.057 |
Braun | -0.055 |
synchronized | -0.054 |
Larson | -0.053 |
prolifer | -0.053 |
Token | after |
Token ID | 706 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
fell | +0.025 |
ihad | +0.022 |
iaries | +0.022 |
inges | +0.021 |
ATES | +0.021 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.018 |
Larson | -0.018 |
prolifer | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
fell | +0.017 |
ihad | +0.014 |
iaries | +0.014 |
inges | +0.014 |
ATES | +0.014 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.014 |
prolifer | -0.014 |
Token | club |
Token ID | 3430 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
fell | +0.030 |
ihad | +0.026 |
iaries | +0.026 |
inges | +0.025 |
ATES | +0.025 |
Neg logit contributions | |
rade | -0.027 |
Braun | -0.026 |
synchronized | -0.025 |
Larson | -0.025 |
prolifer | -0.025 |
Token | fired |
Token ID | 6294 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
fell | +0.098 |
ihad | +0.082 |
iaries | +0.082 |
ATES | +0.080 |
inges | +0.080 |
Neg logit contributions | |
rade | -0.096 |
Braun | -0.092 |
synchronized | -0.090 |
Larson | -0.089 |
prolifer | -0.089 |
Token | Price |
Token ID | 7886 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
fell | +0.081 |
ihad | +0.067 |
iaries | +0.067 |
inges | +0.066 |
ATES | +0.065 |
Neg logit contributions | |
rade | -0.097 |
Braun | -0.094 |
synchronized | -0.092 |
Larson | -0.092 |
prolifer | -0.091 |
Token | in |
Token ID | 287 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
fell | +0.194 |
ihad | +0.168 |
iaries | +0.167 |
inges | +0.164 |
ATES | +0.164 |
Neg logit contributions | |
rade | -0.146 |
Braun | -0.139 |
synchronized | -0.136 |
Larson | -0.135 |
prolifer | -0.134 |
Token | June |
Token ID | 2795 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
fell | +0.012 |
ihad | +0.010 |
iaries | +0.010 |
inges | +0.010 |
ATES | +0.010 |
Neg logit contributions | |
rade | -0.008 |
Braun | -0.008 |
synchronized | -0.008 |
Larson | -0.008 |
prolifer | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
fell | +0.008 |
ihad | +0.007 |
iaries | +0.007 |
ATES | +0.007 |
inges | +0.007 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.006 |
prolifer | -0.006 |
Token | West |
Token ID | 2688 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
fell | +0.010 |
ihad | +0.008 |
iaries | +0.008 |
ATES | +0.008 |
inges | +0.008 |
Neg logit contributions | |
rade | -0.007 |
Braun | -0.007 |
synchronized | -0.007 |
Larson | -0.007 |
prolifer | -0.007 |
Token | Bank |
Token ID | 5018 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
rade | +0.080 |
Braun | +0.076 |
synchronized | +0.074 |
lear | +0.073 |
prolifer | +0.073 |
Neg logit contributions | |
fell | -0.102 |
ihad | -0.088 |
iaries | -0.087 |
inges | -0.086 |
ATES | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
rade | +0.011 |
Braun | +0.011 |
synchronized | +0.011 |
Larson | +0.010 |
lear | +0.010 |
Neg logit contributions | |
fell | -0.019 |
ihad | -0.016 |
iaries | -0.016 |
inges | -0.016 |
ATES | -0.016 |
Token | has |
Token ID | 468 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
rade | +0.018 |
Braun | +0.017 |
synchronized | +0.017 |
Larson | +0.017 |
prolifer | +0.017 |
Neg logit contributions | |
fell | -0.024 |
ihad | -0.021 |
iaries | -0.021 |
inges | -0.021 |
ATES | -0.021 |
Token | effective |
Token ID | 4050 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
fell | +0.056 |
ihad | +0.048 |
iaries | +0.048 |
ATES | +0.047 |
inges | +0.047 |
Neg logit contributions | |
rade | -0.042 |
Braun | -0.040 |
synchronized | -0.039 |
Larson | -0.039 |
lear | -0.038 |
Token | control |
Token ID | 1630 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
rade | +0.089 |
Braun | +0.085 |
synchronized | +0.084 |
prolifer | +0.083 |
Larson | +0.083 |
Neg logit contributions | |
fell | -0.086 |
ihad | -0.073 |
iaries | -0.072 |
inges | -0.071 |
ATES | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
fell | +0.098 |
ihad | +0.085 |
iaries | +0.084 |
ATES | +0.083 |
inges | +0.083 |
Neg logit contributions | |
rade | -0.068 |
Braun | -0.064 |
synchronized | -0.062 |
Larson | -0.062 |
lear | -0.062 |
Token | as |
Token ID | 355 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
fell | +0.017 |
ihad | +0.015 |
iaries | +0.015 |
ATES | +0.015 |
inges | +0.015 |
Neg logit contributions | |
rade | -0.012 |
Braun | -0.011 |
synchronized | -0.011 |
Larson | -0.011 |
lear | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
rade | +0.016 |
Braun | +0.015 |
synchronized | +0.015 |
Larson | +0.015 |
prolifer | +0.015 |
Neg logit contributions | |
fell | -0.020 |
ihad | -0.017 |
iaries | -0.017 |
inges | -0.017 |
ATES | -0.017 |
Token | UN |
Token ID | 4725 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
fell | +0.019 |
ihad | +0.016 |
iaries | +0.016 |
inges | +0.016 |
ATES | +0.016 |
Neg logit contributions | |
rade | -0.016 |
Braun | -0.015 |
synchronized | -0.015 |
Larson | -0.015 |
prolifer | -0.015 |
Token | 50 |
Token ID | 1120 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
fell | +0.032 |
ihad | +0.027 |
iaries | +0.027 |
inges | +0.026 |
ATES | +0.026 |
Neg logit contributions | |
rade | -0.037 |
Braun | -0.035 |
synchronized | -0.035 |
Larson | -0.035 |
prolifer | -0.034 |
Token | - |
Token ID | 532 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
fell | +0.037 |
ihad | +0.032 |
iaries | +0.032 |
inges | +0.031 |
ATES | +0.031 |
Neg logit contributions | |
rade | -0.034 |
Braun | -0.033 |
synchronized | -0.032 |
Larson | -0.032 |
prolifer | -0.032 |
Token | yellow |
Token ID | 7872 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
fell | +0.070 |
ihad | +0.059 |
iaries | +0.059 |
inges | +0.057 |
ATES | +0.057 |
Neg logit contributions | |
rade | -0.068 |
Braun | -0.065 |
synchronized | -0.064 |
Larson | -0.064 |
prolifer | -0.063 |
Token | ( |
Token ID | 357 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
fell | +0.034 |
ihad | +0.030 |
iaries | +0.030 |
inges | +0.029 |
ATES | +0.029 |
Neg logit contributions | |
rade | -0.019 |
Braun | -0.018 |
synchronized | -0.017 |
Larson | -0.017 |
prolifer | -0.017 |
Token | poly |
Token ID | 35428 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
rade | +0.078 |
Braun | +0.073 |
synchronized | +0.072 |
Larson | +0.071 |
prolifer | +0.071 |
Neg logit contributions | |
fell | -0.121 |
ihad | -0.106 |
iaries | -0.105 |
inges | -0.103 |
ATES | -0.103 |
Token | mer |
Token ID | 647 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
rade | +0.072 |
Braun | +0.066 |
synchronized | +0.063 |
Larson | +0.062 |
prolifer | +0.061 |
Neg logit contributions | |
fell | -0.239 |
ihad | -0.215 |
iaries | -0.214 |
inges | -0.211 |
ATES | -0.211 |
Token | , |
Token ID | 11 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
rade | +0.207 |
Braun | +0.197 |
synchronized | +0.193 |
Larson | +0.190 |
prolifer | +0.190 |
Neg logit contributions | |
fell | -0.275 |
ihad | -0.238 |
iaries | -0.237 |
inges | -0.233 |
ATES | -0.232 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
fell | +0.025 |
ihad | +0.022 |
iaries | +0.022 |
inges | +0.021 |
ATES | +0.021 |
Neg logit contributions | |
rade | -0.022 |
Braun | -0.021 |
synchronized | -0.020 |
Larson | -0.020 |
prolifer | -0.020 |
Token | ) |
Token ID | 8 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
fell | +0.002 |
ihad | +0.002 |
iaries | +0.002 |
ATES | +0.002 |
inges | +0.002 |
Neg logit contributions | |
rade | -0.002 |
Braun | -0.002 |
synchronized | -0.002 |
Larson | -0.002 |
prolifer | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.008 |
synchronized | +0.008 |
Larson | +0.008 |
prolifer | +0.008 |
Neg logit contributions | |
fell | -0.011 |
ihad | -0.009 |
iaries | -0.009 |
inges | -0.009 |
ATES | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
fell | +0.004 |
ihad | +0.003 |
iaries | +0.003 |
inges | +0.003 |
ATES | +0.003 |
Neg logit contributions | |
rade | -0.003 |
Braun | -0.003 |
synchronized | -0.003 |
Larson | -0.003 |
prolifer | -0.003 |
Token | ouls |
Token ID | 42033 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
rade | +0.131 |
Braun | +0.126 |
synchronized | +0.124 |
Larson | +0.123 |
prolifer | +0.123 |
Neg logit contributions | |
fell | -0.103 |
ihad | -0.085 |
iaries | -0.085 |
inges | -0.082 |
ATES | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
rade | +0.010 |
Braun | +0.009 |
synchronized | +0.009 |
lear | +0.009 |
Larson | +0.009 |
Neg logit contributions | |
fell | -0.014 |
ihad | -0.012 |
iaries | -0.012 |
ATES | -0.012 |
inges | -0.012 |
Token | ghosts |
Token ID | 25899 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
fell | +0.005 |
iaries | +0.004 |
ihad | +0.004 |
ATES | +0.004 |
inges | +0.004 |
Neg logit contributions | |
rade | -0.004 |
Braun | -0.004 |
oulder | -0.003 |
lear | -0.003 |
synchronized | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
rade | +0.040 |
Braun | +0.038 |
synchronized | +0.037 |
lear | +0.036 |
Larson | +0.036 |
Neg logit contributions | |
fell | -0.057 |
ihad | -0.049 |
iaries | -0.049 |
ATES | -0.048 |
inges | -0.048 |
Token | spect |
Token ID | 5444 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
fell | +0.017 |
iaries | +0.015 |
ihad | +0.014 |
ATES | +0.014 |
inges | +0.014 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.012 |
synchronized | -0.012 |
lear | -0.012 |
Larson | -0.012 |
Token | res |
Token ID | 411 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
fell | +0.098 |
iaries | +0.087 |
ihad | +0.086 |
ATES | +0.085 |
inges | +0.085 |
Neg logit contributions | |
rade | -0.044 |
Braun | -0.041 |
synchronized | -0.040 |
Larson | -0.040 |
prolifer | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
rade | +0.160 |
Braun | +0.151 |
synchronized | +0.147 |
Larson | +0.146 |
lear | +0.146 |
Neg logit contributions | |
fell | -0.232 |
ihad | -0.202 |
iaries | -0.201 |
ATES | -0.197 |
inges | -0.197 |
Token | other |
Token ID | 584 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
fell | +0.013 |
ihad | +0.011 |
iaries | +0.011 |
ATES | +0.011 |
inges | +0.011 |
Neg logit contributions | |
rade | -0.011 |
Braun | -0.010 |
synchronized | -0.010 |
Larson | -0.010 |
lear | -0.010 |
Token | creepy |
Token ID | 23387 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
fell | +0.044 |
ihad | +0.038 |
iaries | +0.038 |
ATES | +0.037 |
inges | +0.037 |
Neg logit contributions | |
rade | -0.040 |
Braun | -0.038 |
synchronized | -0.037 |
Larson | -0.037 |
prolifer | -0.037 |
Token | craw |
Token ID | 27784 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
rade | +0.102 |
Braun | +0.097 |
synchronized | +0.095 |
Larson | +0.095 |
prolifer | +0.094 |
Neg logit contributions | |
fell | -0.103 |
ihad | -0.087 |
iaries | -0.087 |
inges | -0.085 |
ATES | -0.085 |
Token | lers |
Token ID | 8116 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
rade | +0.058 |
Braun | +0.055 |
synchronized | +0.054 |
Larson | +0.054 |
prolifer | +0.053 |
Neg logit contributions | |
fell | -0.063 |
ihad | -0.054 |
iaries | -0.054 |
ATES | -0.053 |
inges | -0.053 |
Token | le |
Token ID | 443 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
rade | +0.148 |
Braun | +0.141 |
synchronized | +0.138 |
Larson | +0.136 |
prolifer | +0.136 |
Neg logit contributions | |
fell | -0.191 |
ihad | -0.165 |
iaries | -0.165 |
inges | -0.161 |
ATES | -0.161 |
Token | l |
Token ID | 75 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
rade | +0.049 |
Braun | +0.047 |
synchronized | +0.046 |
Larson | +0.046 |
prolifer | +0.045 |
Neg logit contributions | |
fell | -0.063 |
ihad | -0.055 |
iaries | -0.054 |
inges | -0.053 |
ATES | -0.053 |
Token | m |
Token ID | 285 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
rade | +0.047 |
Braun | +0.044 |
synchronized | +0.043 |
Larson | +0.043 |
prolifer | +0.042 |
Neg logit contributions | |
fell | -0.085 |
ihad | -0.075 |
iaries | -0.074 |
inges | -0.073 |
ATES | -0.073 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
rade | +0.069 |
Braun | +0.067 |
synchronized | +0.066 |
Larson | +0.065 |
prolifer | +0.065 |
Neg logit contributions | |
fell | -0.061 |
ihad | -0.051 |
iaries | -0.050 |
ATES | -0.049 |
inges | -0.049 |
Token | k |
Token ID | 74 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
rade | +0.034 |
Braun | +0.033 |
synchronized | +0.032 |
Larson | +0.032 |
prolifer | +0.032 |
Neg logit contributions | |
fell | -0.026 |
ihad | -0.021 |
iaries | -0.021 |
inges | -0.020 |
ATES | -0.020 |
Token | [ |
Token ID | 685 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
fell | +0.072 |
ihad | +0.064 |
iaries | +0.064 |
ATES | +0.063 |
inges | +0.063 |
Neg logit contributions | |
rade | -0.032 |
Braun | -0.030 |
synchronized | -0.028 |
Larson | -0.028 |
prolifer | -0.028 |
Token | 10 |
Token ID | 940 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
rade | +0.191 |
Braun | +0.183 |
synchronized | +0.179 |
Larson | +0.178 |
prolifer | +0.177 |
Neg logit contributions | |
fell | -0.200 |
ihad | -0.170 |
iaries | -0.170 |
inges | -0.166 |
ATES | -0.166 |
Token | : |
Token ID | 25 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
rade | +0.055 |
Braun | +0.053 |
synchronized | +0.052 |
Larson | +0.051 |
prolifer | +0.051 |
Neg logit contributions | |
fell | -0.066 |
ihad | -0.057 |
iaries | -0.057 |
inges | -0.056 |
ATES | -0.056 |
Token | 47 |
Token ID | 2857 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
rade | +0.065 |
Braun | +0.063 |
synchronized | +0.062 |
Larson | +0.062 |
prolifer | +0.062 |
Neg logit contributions | |
fell | -0.047 |
ihad | -0.038 |
iaries | -0.038 |
inges | -0.037 |
ATES | -0.037 |
Token | ] |
Token ID | 60 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
fell | +0.014 |
ihad | +0.012 |
iaries | +0.012 |
ATES | +0.011 |
inges | +0.011 |
Neg logit contributions | |
rade | -0.010 |
Braun | -0.010 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | < |
Token ID | 1279 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
rade | +0.108 |
Braun | +0.101 |
synchronized | +0.098 |
Larson | +0.097 |
prolifer | +0.096 |
Neg logit contributions | |
fell | -0.226 |
ihad | -0.200 |
iaries | -0.199 |
inges | -0.196 |
ATES | -0.196 |
Token | services |
Token ID | 2594 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
fell | +0.028 |
ihad | +0.024 |
iaries | +0.024 |
ATES | +0.024 |
inges | +0.024 |
Neg logit contributions | |
rade | -0.022 |
Braun | -0.021 |
synchronized | -0.021 |
Larson | -0.021 |
lear | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
rade | +0.058 |
Braun | +0.055 |
synchronized | +0.054 |
Larson | +0.053 |
lear | +0.053 |
Neg logit contributions | |
fell | -0.075 |
ihad | -0.065 |
iaries | -0.065 |
ATES | -0.063 |
inges | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.004 |
synchronized | +0.004 |
Larson | +0.004 |
prolifer | +0.004 |
Neg logit contributions | |
fell | -0.005 |
ihad | -0.005 |
iaries | -0.005 |
inges | -0.004 |
ATES | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
fell | +0.006 |
iaries | +0.005 |
ihad | +0.005 |
inges | +0.005 |
ATES | +0.005 |
Neg logit contributions | |
rade | -0.005 |
Braun | -0.005 |
synchronized | -0.005 |
Larson | -0.005 |
lear | -0.005 |
Token | D |
Token ID | 35 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
fell | +0.006 |
ihad | +0.005 |
iaries | +0.005 |
inges | +0.005 |
ATES | +0.005 |
Neg logit contributions | |
rade | -0.006 |
Braun | -0.006 |
synchronized | -0.006 |
Larson | -0.006 |
prolifer | -0.006 |
Token | DoS |
Token ID | 46498 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
fell | +0.026 |
ihad | +0.023 |
iaries | +0.023 |
ATES | +0.023 |
inges | +0.023 |
Neg logit contributions | |
rade | -0.013 |
Braun | -0.012 |
synchronized | -0.012 |
Larson | -0.012 |
prolifer | -0.012 |
Token | Attack |
Token ID | 8307 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
rade | +0.180 |
Braun | +0.172 |
synchronized | +0.168 |
Larson | +0.167 |
lear | +0.166 |
Neg logit contributions | |
fell | -0.204 |
ihad | -0.174 |
iaries | -0.174 |
inges | -0.170 |
ATES | -0.170 |
Token | Complex |
Token ID | 19157 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
fell | +0.057 |
iaries | +0.049 |
ihad | +0.049 |
inges | +0.048 |
ATES | +0.048 |
Neg logit contributions | |
rade | -0.047 |
Braun | -0.045 |
synchronized | -0.044 |
lear | -0.043 |
Larson | -0.043 |
Token | ity |
Token ID | 414 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
fell | +0.089 |
ihad | +0.073 |
iaries | +0.073 |
ATES | +0.070 |
inges | +0.070 |
Neg logit contributions | |
rade | -0.120 |
Braun | -0.116 |
synchronized | -0.114 |
Larson | -0.113 |
prolifer | -0.113 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
rade | +0.005 |
Braun | +0.005 |
synchronized | +0.005 |
Larson | +0.005 |
lear | +0.005 |
Neg logit contributions | |
fell | -0.006 |
ihad | -0.005 |
iaries | -0.005 |
ATES | -0.005 |
inges | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
fell | +0.011 |
ihad | +0.009 |
iaries | +0.009 |
inges | +0.009 |
ATES | +0.009 |
Neg logit contributions | |
rade | -0.009 |
Braun | -0.009 |
synchronized | -0.009 |
Larson | -0.009 |
prolifer | -0.009 |
Token | site |
Token ID | 2524 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
fell | +0.034 |
ihad | +0.029 |
iaries | +0.029 |
inges | +0.029 |
ATES | +0.029 |
Neg logit contributions | |
rade | -0.028 |
Braun | -0.026 |
synchronized | -0.026 |
lear | -0.026 |
Larson | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
rade | +0.009 |
Braun | +0.009 |
synchronized | +0.008 |
Larson | +0.008 |
oulder | +0.008 |
Neg logit contributions | |
fell | -0.010 |
ihad | -0.008 |
iaries | -0.008 |
inges | -0.008 |
ATES | -0.008 |
Token | inoc |
Token ID | 49027 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
fell | +0.048 |
ihad | +0.042 |
iaries | +0.042 |
inges | +0.042 |
ATES | +0.041 |
Neg logit contributions | |
rade | -0.030 |
Braun | -0.028 |
synchronized | -0.027 |
oulder | -0.027 |
lear | -0.027 |
Token | ulation |
Token ID | 1741 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
rade | +0.141 |
Braun | +0.137 |
synchronized | +0.135 |
Larson | +0.134 |
prolifer | +0.133 |
Neg logit contributions | |
fell | -0.110 |
ihad | -0.090 |
iaries | -0.090 |
inges | -0.088 |
ATES | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
fell | +0.136 |
ihad | +0.117 |
iaries | +0.116 |
inges | +0.115 |
ATES | +0.115 |
Neg logit contributions | |
rade | -0.099 |
Braun | -0.094 |
lear | -0.091 |
synchronized | -0.091 |
Larson | -0.091 |
Token | lymph |
Token ID | 28837 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
fell | +0.021 |
iaries | +0.018 |
ihad | +0.018 |
inges | +0.018 |
ATES | +0.018 |
Neg logit contributions | |
rade | -0.015 |
Braun | -0.014 |
oulder | -0.013 |
synchronized | -0.013 |
lear | -0.013 |
Token | nodes |
Token ID | 13760 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
rade | +0.178 |
Braun | +0.169 |
synchronized | +0.165 |
Larson | +0.164 |
lear | +0.163 |
Neg logit contributions | |
fell | -0.216 |
ihad | -0.185 |
iaries | -0.185 |
ATES | -0.181 |
inges | -0.181 |
Token | .[ |
Token ID | 3693 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
rade | +0.081 |
Braun | +0.076 |
synchronized | +0.074 |
Larson | +0.074 |
oulder | +0.074 |
Neg logit contributions | |
fell | -0.108 |
ihad | -0.093 |
iaries | -0.093 |
inges | -0.091 |
ATES | -0.091 |
Token | 118 |
Token ID | 16817 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
fell | +0.010 |
ihad | +0.008 |
iaries | +0.008 |
ATES | +0.008 |
inges | +0.008 |
Neg logit contributions | |
rade | -0.014 |
Braun | -0.014 |
synchronized | -0.014 |
Larson | -0.013 |
prolifer | -0.013 |
Token | ] |
Token ID | 60 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
fell | +0.125 |
ihad | +0.108 |
iaries | +0.107 |
ATES | +0.106 |
inges | +0.105 |
Neg logit contributions | |
rade | -0.094 |
Braun | -0.089 |
synchronized | -0.087 |
Larson | -0.086 |
prolifer | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
fell | +0.025 |
iaries | +0.022 |
ihad | +0.022 |
ATES | +0.021 |
inges | +0.021 |
Neg logit contributions | |
rade | -0.022 |
Braun | -0.021 |
synchronized | -0.021 |
lear | -0.021 |
oulder | -0.021 |