Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
916 | -0.007 |
Pir | -0.007 |
Glac | -0.007 |
Token | But |
Token ID | 1537 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
916 | -0.005 |
Pir | -0.005 |
Glac | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
dstg | +0.022 |
arist | +0.022 |
mere | +0.021 |
Roses | +0.021 |
angers | +0.021 |
Neg logit contributions | |
Pag | -0.022 |
olate | -0.022 |
Pir | -0.022 |
916 | -0.022 |
Glac | -0.022 |
Token | extrap |
Token ID | 36804 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | olate |
Token ID | 27976 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Pag | +0.009 |
Glac | +0.006 |
Pir | +0.006 |
916 | +0.004 |
olate | +0.000 |
Neg logit contributions | |
arist | -0.331 |
dstg | -0.328 |
mere | -0.326 |
angers | -0.320 |
Roses | -0.319 |
Token | from |
Token ID | 422 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
olate | +0.344 |
Pag | +0.343 |
Pir | +0.335 |
916 | +0.334 |
Glac | +0.330 |
Neg logit contributions | |
dstg | -0.355 |
arist | -0.354 |
mere | -0.343 |
Roses | -0.335 |
angers | -0.334 |
Token | that |
Token ID | 326 |
Feature activation | -9.72e-03 |
Pos logit contributions | |
Pag | +0.006 |
olate | +0.006 |
Pir | +0.006 |
916 | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | sentiment |
Token ID | 15598 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.006 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.034 |
mere | +0.033 |
Roses | +0.033 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.034 |
Pag | -0.034 |
Pir | -0.033 |
916 | -0.033 |
Glac | -0.033 |
Token | apply |
Token ID | 4174 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | 34 |
Token ID | 4974 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
dstg | +0.060 |
arist | +0.059 |
mere | +0.058 |
Roses | +0.057 |
angers | +0.056 |
Neg logit contributions | |
olate | -0.060 |
Pag | -0.060 |
916 | -0.059 |
Pir | -0.058 |
Glac | -0.058 |
Token | MW |
Token ID | 29961 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.046 |
916 | +0.045 |
Pir | +0.045 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.048 |
arist | -0.048 |
mere | -0.047 |
Roses | -0.046 |
angers | -0.045 |
Token | at |
Token ID | 379 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
dstg | +0.011 |
arist | +0.011 |
mere | +0.011 |
Roses | +0.011 |
angers | +0.011 |
Neg logit contributions | |
olate | -0.013 |
Pag | -0.012 |
916 | -0.012 |
Pir | -0.012 |
Glac | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
olate | +0.035 |
Pag | +0.035 |
916 | +0.034 |
Pir | +0.034 |
Glac | +0.033 |
Neg logit contributions | |
dstg | -0.035 |
arist | -0.035 |
mere | -0.034 |
Roses | -0.033 |
angers | -0.033 |
Token | prope |
Token ID | 44408 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | llers |
Token ID | 13802 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
olate | +0.029 |
Pag | +0.029 |
916 | +0.027 |
Pir | +0.026 |
Glac | +0.026 |
Neg logit contributions | |
dstg | -0.177 |
arist | -0.177 |
mere | -0.174 |
Roses | -0.171 |
angers | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
olate | +0.324 |
Pag | +0.323 |
Pir | +0.316 |
916 | +0.315 |
Glac | +0.312 |
Neg logit contributions | |
dstg | -0.333 |
arist | -0.332 |
mere | -0.322 |
Roses | -0.317 |
angers | -0.314 |
Token | Lenin |
Token ID | 22899 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
dstg | +0.022 |
arist | +0.022 |
mere | +0.021 |
Roses | +0.021 |
angers | +0.021 |
Neg logit contributions | |
olate | -0.021 |
Pag | -0.021 |
916 | -0.020 |
Pir | -0.020 |
Glac | -0.020 |
Token | retired |
Token ID | 9880 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
olate | +0.022 |
Pag | +0.022 |
916 | +0.022 |
Pir | +0.022 |
Glac | +0.022 |
Neg logit contributions | |
dstg | -0.022 |
arist | -0.022 |
mere | -0.021 |
Roses | -0.021 |
angers | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
dstg | +0.063 |
arist | +0.063 |
mere | +0.061 |
Roses | +0.060 |
angers | +0.059 |
Neg logit contributions | |
olate | -0.062 |
Pag | -0.062 |
Pir | -0.060 |
916 | -0.060 |
Glac | -0.060 |
Token | 54 |
Token ID | 7175 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
dstg | +0.062 |
arist | +0.061 |
mere | +0.060 |
Roses | +0.059 |
angers | +0.059 |
Neg logit contributions | |
olate | -0.055 |
Pag | -0.054 |
916 | -0.053 |
Pir | -0.053 |
Glac | -0.052 |
Token | MW |
Token ID | 29961 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
916 | +0.026 |
Pir | +0.026 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.026 |
arist | -0.026 |
mere | -0.025 |
Roses | -0.025 |
angers | -0.025 |
Token | at |
Token ID | 379 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
dstg | +0.013 |
arist | +0.013 |
mere | +0.013 |
Roses | +0.012 |
angers | +0.012 |
Neg logit contributions | |
olate | -0.012 |
Pag | -0.011 |
916 | -0.011 |
Pir | -0.011 |
Glac | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
olate | +0.030 |
Pag | +0.030 |
916 | +0.029 |
Pir | +0.029 |
Glac | +0.029 |
Neg logit contributions | |
dstg | -0.032 |
arist | -0.032 |
mere | -0.031 |
Roses | -0.031 |
angers | -0.031 |
Token | prope |
Token ID | 44408 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | llers |
Token ID | 13802 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
olate | +0.013 |
Pag | +0.013 |
Pir | +0.011 |
Glac | +0.011 |
916 | +0.010 |
Neg logit contributions | |
dstg | -0.188 |
arist | -0.187 |
mere | -0.185 |
angers | -0.183 |
Roses | -0.182 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
olate | +0.323 |
Pag | +0.321 |
Pir | +0.314 |
916 | +0.314 |
Glac | +0.311 |
Neg logit contributions | |
dstg | -0.330 |
arist | -0.329 |
mere | -0.319 |
Roses | -0.313 |
angers | -0.311 |
Token | are |
Token ID | 389 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
916 | -0.007 |
Pir | -0.007 |
Glac | -0.007 |
Token | used |
Token ID | 973 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
dstg | +0.017 |
arist | +0.017 |
mere | +0.016 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.017 |
Pag | -0.017 |
Pir | -0.016 |
916 | -0.016 |
Glac | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | deep |
Token ID | 2769 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
olate | +0.033 |
Pag | +0.033 |
916 | +0.032 |
Pir | +0.032 |
Glac | +0.032 |
Neg logit contributions | |
dstg | -0.033 |
arist | -0.033 |
mere | -0.032 |
Roses | -0.031 |
angers | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
dstg | +0.021 |
arist | +0.021 |
mere | +0.020 |
Roses | +0.020 |
angers | +0.020 |
Neg logit contributions | |
olate | -0.020 |
Pag | -0.020 |
916 | -0.020 |
Pir | -0.020 |
Glac | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
dstg | +0.011 |
arist | +0.011 |
mere | +0.010 |
Roses | +0.010 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.010 |
Pag | -0.010 |
916 | -0.010 |
Pir | -0.010 |
Glac | -0.010 |
Token | V |
Token ID | 53 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
olate | +0.009 |
Pag | +0.009 |
916 | +0.009 |
Pir | +0.009 |
Glac | +0.009 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.009 |
Roses | -0.009 |
angers | -0.009 |
Token | ik |
Token ID | 1134 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
dstg | +0.024 |
arist | +0.024 |
mere | +0.024 |
Roses | +0.023 |
angers | +0.023 |
Neg logit contributions | |
olate | -0.025 |
Pag | -0.025 |
916 | -0.024 |
Pir | -0.024 |
Glac | -0.024 |
Token | ram |
Token ID | 859 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
arist | +0.006 |
dstg | +0.006 |
mere | +0.006 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
916 | -0.006 |
Pir | -0.006 |
Glac | -0.005 |
Token | Bak |
Token ID | 17466 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
Pag | +0.303 |
olate | +0.303 |
Pir | +0.297 |
916 | +0.295 |
Glac | +0.293 |
Neg logit contributions | |
dstg | -0.294 |
arist | -0.292 |
mere | -0.283 |
Roses | -0.278 |
angers | -0.276 |
Token | shi |
Token ID | 44019 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
olate | +0.068 |
Pag | +0.067 |
Pir | +0.066 |
916 | +0.066 |
Glac | +0.066 |
Neg logit contributions | |
dstg | -0.039 |
arist | -0.038 |
mere | -0.037 |
Roses | -0.036 |
angers | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.034 |
mere | +0.033 |
Roses | +0.032 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.032 |
Pag | -0.032 |
Pir | -0.032 |
916 | -0.032 |
Glac | -0.031 |
Token | managing |
Token ID | 11149 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | director |
Token ID | 3437 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Pag | +0.043 |
olate | +0.043 |
Pir | +0.042 |
916 | +0.042 |
Glac | +0.041 |
Neg logit contributions | |
dstg | -0.069 |
arist | -0.068 |
mere | -0.067 |
Roses | -0.065 |
angers | -0.065 |
Token | below |
Token ID | 2174 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
olate | +0.138 |
Pag | +0.138 |
Pir | +0.134 |
916 | +0.134 |
Glac | +0.132 |
Neg logit contributions | |
dstg | -0.144 |
arist | -0.143 |
mere | -0.138 |
Roses | -0.136 |
angers | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | -9.38e-03 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
Pag | -0.003 |
olate | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | uniform |
Token ID | 8187 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.007 |
916 | -0.007 |
Glac | -0.007 |
Token | mill |
Token ID | 3939 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
olate | +0.022 |
Pag | +0.022 |
Pir | +0.022 |
916 | +0.022 |
Glac | +0.021 |
Neg logit contributions | |
dstg | -0.024 |
arist | -0.024 |
mere | -0.023 |
Roses | -0.023 |
angers | -0.023 |
Token | ig |
Token ID | 328 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
olate | +0.103 |
Pag | +0.101 |
Pir | +0.100 |
916 | +0.099 |
Glac | +0.098 |
Neg logit contributions | |
dstg | -0.092 |
arist | -0.090 |
mere | -0.087 |
Roses | -0.086 |
angers | -0.085 |
Token | ram |
Token ID | 859 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
arist | +0.071 |
dstg | +0.070 |
mere | +0.069 |
angers | +0.068 |
Roses | +0.068 |
Neg logit contributions | |
Pag | -0.008 |
olate | -0.008 |
916 | -0.007 |
Pir | -0.007 |
Glac | -0.007 |
Token | limit |
Token ID | 4179 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
olate | +0.293 |
Pag | +0.292 |
Pir | +0.285 |
916 | +0.284 |
Glac | +0.280 |
Neg logit contributions | |
dstg | -0.303 |
arist | -0.300 |
mere | -0.292 |
Roses | -0.287 |
angers | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
dstg | +0.058 |
arist | +0.058 |
mere | +0.056 |
Roses | +0.055 |
angers | +0.055 |
Neg logit contributions | |
olate | -0.055 |
Pag | -0.055 |
916 | -0.053 |
Pir | -0.053 |
Glac | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | E |
Token ID | 36 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
olate | +0.009 |
Pag | +0.009 |
916 | +0.009 |
Pir | +0.009 |
Glac | +0.009 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.009 |
Roses | -0.009 |
angers | -0.009 |
Token | along |
Token ID | 1863 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
dstg | +0.020 |
arist | +0.020 |
mere | +0.019 |
Roses | +0.019 |
angers | +0.019 |
Neg logit contributions | |
olate | -0.020 |
Pag | -0.020 |
916 | -0.020 |
Pir | -0.020 |
Glac | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | int |
Token ID | 493 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
dstg | +0.029 |
arist | +0.029 |
mere | +0.029 |
Roses | +0.028 |
angers | +0.028 |
Neg logit contributions | |
olate | -0.025 |
Pag | -0.024 |
916 | -0.024 |
Glac | -0.024 |
Pir | -0.024 |
Token | ram |
Token ID | 859 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
dstg | +0.012 |
arist | +0.012 |
mere | +0.012 |
Roses | +0.012 |
angers | +0.012 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | ural |
Token ID | 1523 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
olate | +0.326 |
Pag | +0.325 |
916 | +0.318 |
Pir | +0.318 |
Glac | +0.316 |
Neg logit contributions | |
dstg | -0.268 |
arist | -0.266 |
mere | -0.258 |
Roses | -0.251 |
angers | -0.250 |
Token | activities |
Token ID | 4568 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.034 |
mere | +0.033 |
Roses | +0.033 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.018 |
Pag | -0.017 |
916 | -0.017 |
Pir | -0.017 |
Glac | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
olate | +0.103 |
Pag | +0.102 |
916 | +0.100 |
Pir | +0.100 |
Glac | +0.099 |
Neg logit contributions | |
dstg | -0.101 |
arist | -0.100 |
mere | -0.097 |
Roses | -0.095 |
angers | -0.095 |
Token | including |
Token ID | 1390 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | cheer |
Token ID | 14042 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
dstg | +0.051 |
arist | +0.051 |
mere | +0.050 |
Roses | +0.049 |
angers | +0.049 |
Neg logit contributions | |
olate | -0.042 |
Pag | -0.041 |
916 | -0.040 |
Pir | -0.040 |
Glac | -0.040 |
Token | our |
Token ID | 674 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
dstg | +0.086 |
arist | +0.085 |
mere | +0.083 |
angers | +0.081 |
Roses | +0.080 |
Neg logit contributions | |
Pag | -0.083 |
olate | -0.083 |
Pir | -0.081 |
916 | -0.081 |
Glac | -0.080 |
Token | interview |
Token ID | 2720 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
dstg | +0.024 |
arist | +0.024 |
mere | +0.023 |
Roses | +0.022 |
angers | +0.022 |
Neg logit contributions | |
olate | -0.022 |
Pag | -0.022 |
Pir | -0.022 |
916 | -0.021 |
Glac | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +4.06e-04 |
Pos logit contributions | |
olate | +0.017 |
Pag | +0.017 |
916 | +0.017 |
Pir | +0.017 |
Glac | +0.017 |
Neg logit contributions | |
dstg | -0.018 |
arist | -0.018 |
mere | -0.017 |
Roses | -0.017 |
angers | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | ref |
Token ID | 1006 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | ram |
Token ID | 859 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
dstg | +0.045 |
arist | +0.045 |
mere | +0.042 |
Roses | +0.041 |
angers | +0.040 |
Neg logit contributions | |
olate | -0.111 |
Pag | -0.110 |
916 | -0.109 |
Pir | -0.109 |
Glac | -0.108 |
Token | ed |
Token ID | 276 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
olate | +0.255 |
Pag | +0.251 |
916 | +0.250 |
Pir | +0.250 |
Glac | +0.243 |
Neg logit contributions | |
dstg | -0.329 |
arist | -0.325 |
mere | -0.317 |
Roses | -0.316 |
angers | -0.313 |
Token | the |
Token ID | 262 |
Feature activation | +8.51e-05 |
Pos logit contributions | |
olate | +0.046 |
Pag | +0.046 |
Pir | +0.045 |
916 | +0.045 |
Glac | +0.044 |
Neg logit contributions | |
dstg | -0.047 |
arist | -0.046 |
mere | -0.045 |
Roses | -0.044 |
angers | -0.044 |
Token | question |
Token ID | 1808 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
olate | +0.082 |
Pag | +0.081 |
Pir | +0.079 |
916 | +0.079 |
Glac | +0.079 |
Neg logit contributions | |
dstg | -0.081 |
arist | -0.081 |
mere | -0.079 |
Roses | -0.077 |
angers | -0.076 |
Token | � |
Token ID | 564 |
Feature activation | -9.08e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | HHS |
Token ID | 45497 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
Pir | -0.004 |
916 | -0.004 |
Glac | -0.004 |
Token | seeks |
Token ID | 12932 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
dstg | +0.122 |
arist | +0.122 |
mere | +0.118 |
Roses | +0.116 |
angers | +0.115 |
Neg logit contributions | |
olate | -0.125 |
Pag | -0.124 |
916 | -0.121 |
Pir | -0.121 |
Glac | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -7.75e-04 |
Pos logit contributions | |
dstg | +0.081 |
arist | +0.081 |
mere | +0.078 |
Roses | +0.077 |
angers | +0.076 |
Neg logit contributions | |
olate | -0.085 |
Pag | -0.084 |
916 | -0.083 |
Pir | -0.083 |
Glac | -0.082 |
Token | " |
Token ID | 366 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | d |
Token ID | 67 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
dstg | +0.028 |
arist | +0.027 |
mere | +0.027 |
Roses | +0.026 |
angers | +0.026 |
Neg logit contributions | |
olate | -0.025 |
Pag | -0.025 |
916 | -0.024 |
Pir | -0.024 |
Glac | -0.024 |
Token | ram |
Token ID | 859 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
olate | +0.038 |
Pag | +0.037 |
916 | +0.037 |
Pir | +0.037 |
Glac | +0.036 |
Neg logit contributions | |
dstg | -0.020 |
arist | -0.020 |
mere | -0.019 |
Roses | -0.018 |
angers | -0.018 |
Token | atically |
Token ID | 4142 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
olate | +0.321 |
Pag | +0.317 |
916 | +0.311 |
Pir | +0.311 |
Glac | +0.308 |
Neg logit contributions | |
dstg | -0.269 |
arist | -0.264 |
mere | -0.256 |
Roses | -0.253 |
angers | -0.249 |
Token | " |
Token ID | 1 |
Feature activation | -8.33e-04 |
Pos logit contributions | |
dstg | +0.023 |
arist | +0.023 |
mere | +0.022 |
Roses | +0.021 |
angers | +0.021 |
Neg logit contributions | |
olate | -0.028 |
Pag | -0.027 |
916 | -0.027 |
Pir | -0.027 |
Glac | -0.027 |
Token | shorten |
Token ID | 45381 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
dstg | +0.099 |
arist | +0.098 |
mere | +0.095 |
Roses | +0.093 |
angers | +0.093 |
Neg logit contributions | |
olate | -0.097 |
Pag | -0.097 |
Pir | -0.095 |
916 | -0.095 |
Glac | -0.094 |
Token | 2018 |
Token ID | 2864 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
Pag | +0.001 |
olate | +0.001 |
Pir | +0.001 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
angers | -0.001 |
Roses | -0.001 |
Token | we |
Token ID | 356 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | now |
Token ID | 783 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
dstg | +0.022 |
arist | +0.022 |
mere | +0.021 |
Roses | +0.021 |
angers | +0.021 |
Neg logit contributions | |
olate | -0.022 |
Pag | -0.022 |
916 | -0.021 |
Pir | -0.021 |
Glac | -0.021 |
Token | know |
Token ID | 760 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
dstg | +0.036 |
arist | +0.036 |
mere | +0.035 |
Roses | +0.034 |
angers | +0.034 |
Neg logit contributions | |
olate | -0.033 |
Pag | -0.033 |
916 | -0.032 |
Pir | -0.032 |
Glac | -0.032 |
Token | existed |
Token ID | 11196 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
olate | +0.041 |
Pag | +0.040 |
Pir | +0.040 |
916 | +0.039 |
Glac | +0.039 |
Neg logit contributions | |
dstg | -0.040 |
arist | -0.040 |
mere | -0.039 |
Roses | -0.038 |
angers | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
dstg | +0.146 |
arist | +0.145 |
mere | +0.141 |
Roses | +0.138 |
angers | +0.137 |
Neg logit contributions | |
olate | -0.146 |
Pag | -0.146 |
Pir | -0.143 |
916 | -0.142 |
Glac | -0.141 |
Token | Hispan |
Token ID | 13600 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
olate | +0.016 |
Pag | +0.016 |
Pir | +0.015 |
916 | +0.015 |
Glac | +0.015 |
Neg logit contributions | |
dstg | -0.016 |
arist | -0.016 |
mere | -0.016 |
Roses | -0.015 |
angers | -0.015 |
Token | iola |
Token ID | 30292 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Pag | +0.255 |
olate | +0.255 |
Pir | +0.247 |
916 | +0.244 |
Glac | +0.244 |
Neg logit contributions | |
dstg | -0.333 |
arist | -0.326 |
mere | -0.321 |
Roses | -0.314 |
angers | -0.312 |
Token | relatively |
Token ID | 5365 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
olate | +0.073 |
Pag | +0.073 |
Pir | +0.071 |
916 | +0.071 |
Glac | +0.071 |
Neg logit contributions | |
dstg | -0.074 |
arist | -0.073 |
mere | -0.071 |
Roses | -0.070 |
angers | -0.069 |
Token | unchanged |
Token ID | 21588 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
olate | +0.021 |
Pag | +0.021 |
916 | +0.021 |
Pir | +0.021 |
Glac | +0.021 |
Neg logit contributions | |
dstg | -0.021 |
arist | -0.021 |
mere | -0.020 |
Roses | -0.020 |
angers | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | +3.38e-03 |
Pos logit contributions | |
olate | +0.020 |
Pag | +0.020 |
916 | +0.019 |
Pir | +0.019 |
Glac | +0.019 |
Neg logit contributions | |
dstg | -0.019 |
arist | -0.019 |
mere | -0.019 |
Roses | -0.018 |
angers | -0.018 |
Token | over |
Token ID | 625 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | Life |
Token ID | 5155 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
dstg | +0.015 |
arist | +0.015 |
mere | +0.014 |
Roses | +0.014 |
angers | +0.014 |
Neg logit contributions | |
olate | -0.015 |
Pag | -0.015 |
Pir | -0.015 |
916 | -0.015 |
Glac | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
dstg | +0.030 |
arist | +0.030 |
mere | +0.029 |
Roses | +0.028 |
angers | +0.028 |
Neg logit contributions | |
olate | -0.030 |
Pag | -0.029 |
Pir | -0.029 |
916 | -0.029 |
Glac | -0.028 |
Token | Christ |
Token ID | 1951 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
dstg | +0.008 |
arist | +0.008 |
mere | +0.008 |
Roses | +0.008 |
angers | +0.008 |
Neg logit contributions | |
olate | -0.008 |
Pag | -0.008 |
Pir | -0.008 |
916 | -0.008 |
Glac | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
dstg | +0.015 |
arist | +0.015 |
mere | +0.014 |
Roses | +0.014 |
angers | +0.014 |
Neg logit contributions | |
olate | -0.015 |
Pag | -0.015 |
Pir | -0.014 |
916 | -0.014 |
Glac | -0.014 |
Token | Sac |
Token ID | 9295 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
Pag | -0.005 |
olate | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | ram |
Token ID | 859 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
dstg | +0.182 |
arist | +0.181 |
mere | +0.178 |
Roses | +0.176 |
angers | +0.175 |
Neg logit contributions | |
olate | -0.036 |
Pag | -0.036 |
Pir | -0.033 |
916 | -0.033 |
Glac | -0.032 |
Token | ents |
Token ID | 658 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
olate | +0.299 |
Pag | +0.297 |
Pir | +0.291 |
916 | +0.289 |
Glac | +0.287 |
Neg logit contributions | |
dstg | -0.287 |
arist | -0.281 |
mere | -0.275 |
Roses | -0.271 |
angers | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
olate | +0.024 |
Pag | +0.024 |
Pir | +0.023 |
916 | +0.023 |
Glac | +0.023 |
Neg logit contributions | |
dstg | -0.024 |
arist | -0.024 |
mere | -0.023 |
Roses | -0.023 |
angers | -0.023 |
Token | Bapt |
Token ID | 18226 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | ism |
Token ID | 1042 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
olate | +0.045 |
Pag | +0.045 |
Pir | +0.043 |
916 | +0.043 |
Glac | +0.043 |
Neg logit contributions | |
dstg | -0.059 |
arist | -0.058 |
mere | -0.057 |
Roses | -0.056 |
angers | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +9.56e-04 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.047 |
916 | +0.046 |
Pir | +0.046 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.047 |
arist | -0.046 |
mere | -0.045 |
Roses | -0.044 |
angers | -0.044 |
Token | 's |
Token ID | 338 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
dstg | +0.072 |
arist | +0.072 |
mere | +0.070 |
Roses | +0.068 |
angers | +0.068 |
Neg logit contributions | |
olate | -0.071 |
Pag | -0.071 |
Pir | -0.069 |
916 | -0.069 |
Glac | -0.069 |
Token | chief |
Token ID | 4039 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | executive |
Token ID | 4640 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
dstg | +0.045 |
arist | +0.045 |
mere | +0.044 |
Roses | +0.043 |
angers | +0.043 |
Neg logit contributions | |
olate | -0.033 |
Pag | -0.033 |
916 | -0.032 |
Pir | -0.032 |
Glac | -0.032 |
Token | Stella |
Token ID | 45856 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
olate | +0.059 |
Pag | +0.059 |
916 | +0.058 |
Pir | +0.057 |
Glac | +0.057 |
Neg logit contributions | |
dstg | -0.060 |
arist | -0.060 |
mere | -0.058 |
Roses | -0.057 |
angers | -0.057 |
Token | Av |
Token ID | 5184 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
dstg | +0.080 |
arist | +0.080 |
mere | +0.078 |
Roses | +0.077 |
angers | +0.076 |
Neg logit contributions | |
olate | -0.071 |
Pag | -0.071 |
916 | -0.069 |
Pir | -0.069 |
Glac | -0.068 |
Token | ram |
Token ID | 859 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
dstg | +0.062 |
arist | +0.062 |
mere | +0.060 |
Roses | +0.059 |
angers | +0.059 |
Neg logit contributions | |
olate | -0.056 |
Pag | -0.056 |
916 | -0.055 |
Pir | -0.055 |
Glac | -0.054 |
Token | opoulos |
Token ID | 20338 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
olate | +0.298 |
Pag | +0.297 |
Pir | +0.291 |
916 | +0.289 |
Glac | +0.287 |
Neg logit contributions | |
dstg | -0.287 |
arist | -0.281 |
mere | -0.273 |
Roses | -0.269 |
angers | -0.266 |
Token | said |
Token ID | 531 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
dstg | +0.105 |
arist | +0.104 |
mere | +0.102 |
Roses | +0.099 |
angers | +0.099 |
Neg logit contributions | |
olate | -0.111 |
Pag | -0.110 |
916 | -0.108 |
Pir | -0.108 |
Glac | -0.107 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
dstg | +0.014 |
arist | +0.014 |
mere | +0.013 |
Roses | +0.013 |
angers | +0.013 |
Neg logit contributions | |
olate | -0.014 |
Pag | -0.014 |
Pir | -0.013 |
916 | -0.013 |
Glac | -0.013 |
Token | face |
Token ID | 1986 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
dstg | +0.009 |
arist | +0.009 |
mere | +0.009 |
Roses | +0.008 |
angers | +0.008 |
Neg logit contributions | |
olate | -0.009 |
Pag | -0.009 |
916 | -0.009 |
Pir | -0.009 |
Glac | -0.009 |
Token | Tal |
Token ID | 7193 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | ion |
Token ID | 295 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
olate | +0.109 |
Pag | +0.108 |
Pir | +0.106 |
916 | +0.105 |
Glac | +0.105 |
Neg logit contributions | |
dstg | -0.106 |
arist | -0.104 |
mere | -0.102 |
Roses | -0.099 |
angers | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | or |
Token ID | 393 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
Pir | +0.004 |
916 | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | Rh |
Token ID | 10323 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | ulic |
Token ID | 28575 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
dstg | +0.063 |
arist | +0.062 |
mere | +0.061 |
angers | +0.059 |
Roses | +0.059 |
Neg logit contributions | |
olate | -0.067 |
Pag | -0.067 |
916 | -0.066 |
Pir | -0.065 |
Glac | -0.065 |
Token | soldiers |
Token ID | 5795 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
olate | +0.284 |
Pag | +0.284 |
Pir | +0.277 |
916 | +0.276 |
Glac | +0.274 |
Neg logit contributions | |
dstg | -0.297 |
arist | -0.295 |
mere | -0.287 |
Roses | -0.281 |
angers | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
dstg | +0.022 |
arist | +0.021 |
mere | +0.021 |
Roses | +0.020 |
angers | +0.020 |
Neg logit contributions | |
olate | -0.022 |
Pag | -0.022 |
Pir | -0.022 |
916 | -0.022 |
Glac | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | certainly |
Token ID | 3729 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
Pir | +0.026 |
916 | +0.026 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.030 |
arist | -0.030 |
mere | -0.029 |
Roses | -0.028 |
angers | -0.028 |
Token | born |
Token ID | 4642 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
dstg | +0.071 |
arist | +0.070 |
mere | +0.068 |
Roses | +0.067 |
angers | +0.067 |
Neg logit contributions | |
olate | -0.075 |
Pag | -0.074 |
Pir | -0.073 |
916 | -0.073 |
Glac | -0.072 |
Token | British |
Token ID | 3517 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.047 |
916 | +0.046 |
Pir | +0.046 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.048 |
arist | -0.048 |
mere | -0.047 |
Roses | -0.046 |
angers | -0.046 |
Token | National |
Token ID | 2351 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
olate | +0.090 |
Pag | +0.090 |
Pir | +0.088 |
916 | +0.088 |
Glac | +0.087 |
Neg logit contributions | |
dstg | -0.090 |
arist | -0.089 |
mere | -0.087 |
Roses | -0.085 |
angers | -0.084 |
Token | Kh |
Token ID | 5311 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
dstg | +0.038 |
arist | +0.038 |
mere | +0.037 |
Roses | +0.036 |
angers | +0.036 |
Neg logit contributions | |
olate | -0.038 |
Pag | -0.038 |
916 | -0.037 |
Pir | -0.037 |
Glac | -0.037 |
Token | ur |
Token ID | 333 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
arist | +0.022 |
dstg | +0.021 |
mere | +0.021 |
angers | +0.020 |
Roses | +0.020 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.026 |
916 | -0.026 |
Glac | -0.025 |
Pir | -0.025 |
Token | ram |
Token ID | 859 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
olate | +0.015 |
Pag | +0.015 |
916 | +0.014 |
Pir | +0.014 |
Glac | +0.014 |
Neg logit contributions | |
arist | -0.054 |
dstg | -0.054 |
mere | -0.053 |
Roses | -0.052 |
angers | -0.052 |
Token | She |
Token ID | 1375 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
Pag | +0.291 |
Pir | +0.287 |
olate | +0.286 |
Glac | +0.283 |
916 | +0.279 |
Neg logit contributions | |
dstg | -0.294 |
arist | -0.291 |
mere | -0.278 |
Roses | -0.275 |
angers | -0.274 |
Token | hz |
Token ID | 32179 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | ad |
Token ID | 324 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
dstg | +0.098 |
arist | +0.095 |
mere | +0.092 |
Roses | +0.090 |
angers | +0.087 |
Neg logit contributions | |
olate | -0.165 |
Pag | -0.164 |
Pir | -0.162 |
916 | -0.160 |
Glac | -0.159 |
Token | Butt |
Token ID | 36041 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
dstg | +0.096 |
arist | +0.096 |
mere | +0.093 |
Roses | +0.091 |
angers | +0.091 |
Neg logit contributions | |
olate | -0.095 |
Pag | -0.095 |
Pir | -0.093 |
916 | -0.092 |
Glac | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e-03 |
Pos logit contributions | |
dstg | +0.068 |
arist | +0.067 |
mere | +0.065 |
Roses | +0.064 |
angers | +0.063 |
Neg logit contributions | |
olate | -0.065 |
Pag | -0.065 |
Pir | -0.064 |
916 | -0.063 |
Glac | -0.063 |
Token | Great |
Token ID | 3878 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
olate | +0.011 |
Pag | +0.011 |
916 | +0.011 |
Pir | +0.011 |
Glac | +0.011 |
Neg logit contributions | |
dstg | -0.018 |
arist | -0.018 |
mere | -0.017 |
Roses | -0.017 |
angers | -0.017 |
Token | Again |
Token ID | 6521 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
olate | +0.079 |
Pag | +0.079 |
916 | +0.077 |
Pir | +0.077 |
Glac | +0.076 |
Neg logit contributions | |
dstg | -0.071 |
arist | -0.071 |
mere | -0.069 |
Roses | -0.067 |
angers | -0.067 |
Token | # |
Token ID | 1303 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
dstg | +0.022 |
arist | +0.022 |
mere | +0.021 |
Roses | +0.020 |
angers | +0.020 |
Neg logit contributions | |
olate | -0.021 |
Pag | -0.021 |
Pir | -0.020 |
916 | -0.020 |
Glac | -0.020 |
Token | In |
Token ID | 818 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
olate | +0.070 |
Pag | +0.069 |
916 | +0.068 |
Pir | +0.068 |
Glac | +0.067 |
Neg logit contributions | |
dstg | -0.074 |
arist | -0.074 |
mere | -0.072 |
Roses | -0.070 |
angers | -0.070 |
Token | aug |
Token ID | 7493 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Pag | +0.014 |
olate | +0.014 |
Pir | +0.014 |
916 | +0.014 |
Glac | +0.014 |
Neg logit contributions | |
dstg | -0.014 |
arist | -0.014 |
mere | -0.014 |
Roses | -0.014 |
angers | -0.014 |
Token | uration |
Token ID | 3924 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
olate | +0.025 |
Pag | +0.025 |
916 | +0.024 |
Pir | +0.024 |
Glac | +0.024 |
Neg logit contributions | |
dstg | -0.069 |
arist | -0.069 |
mere | -0.067 |
Roses | -0.066 |
angers | -0.066 |
Token | 2017 |
Token ID | 5539 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
olate | +0.296 |
Pag | +0.295 |
916 | +0.288 |
Pir | +0.288 |
Glac | +0.285 |
Neg logit contributions | |
dstg | -0.283 |
arist | -0.282 |
mere | -0.274 |
Roses | -0.267 |
angers | -0.266 |
Token | � |
Token ID | 6184 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
olate | +0.048 |
Pag | +0.048 |
916 | +0.047 |
Pir | +0.047 |
Glac | +0.046 |
Neg logit contributions | |
dstg | -0.050 |
arist | -0.050 |
mere | -0.048 |
Roses | -0.047 |
angers | -0.047 |
Token | � |
Token ID | 95 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | � |
Token ID | 126 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
dstg | +0.009 |
arist | +0.009 |
mere | +0.009 |
Roses | +0.008 |
angers | +0.008 |
Neg logit contributions | |
olate | -0.009 |
Pag | -0.009 |
916 | -0.008 |
Pir | -0.008 |
Glac | -0.008 |
Token | � |
Token ID | 222 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
dstg | +0.047 |
arist | +0.047 |
mere | +0.046 |
Roses | +0.044 |
angers | +0.044 |
Neg logit contributions | |
olate | -0.073 |
Pag | -0.073 |
916 | -0.072 |
Pir | -0.072 |
Glac | -0.071 |
Token | ill |
Token ID | 359 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
olate | +0.030 |
Pag | +0.030 |
916 | +0.029 |
Pir | +0.029 |
Glac | +0.029 |
Neg logit contributions | |
dstg | -0.027 |
arist | -0.027 |
mere | -0.026 |
Roses | -0.026 |
angers | -0.025 |
Token | oth |
Token ID | 849 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
dstg | +0.020 |
arist | +0.020 |
mere | +0.020 |
Roses | +0.019 |
angers | +0.019 |
Neg logit contributions | |
olate | -0.023 |
Pag | -0.023 |
916 | -0.022 |
Pir | -0.022 |
Glac | -0.022 |
Token | rix |
Token ID | 8609 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
dstg | +0.024 |
arist | +0.023 |
mere | +0.023 |
Roses | +0.022 |
angers | +0.022 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.026 |
Pir | -0.025 |
916 | -0.025 |
Glac | -0.025 |
Token | existed |
Token ID | 11196 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
olate | +0.044 |
Pag | +0.044 |
916 | +0.043 |
Pir | +0.043 |
Glac | +0.042 |
Neg logit contributions | |
arist | -0.044 |
dstg | -0.044 |
mere | -0.043 |
Roses | -0.042 |
angers | -0.042 |
Token | on |
Token ID | 319 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
dstg | +0.156 |
arist | +0.155 |
mere | +0.151 |
Roses | +0.148 |
angers | +0.147 |
Neg logit contributions | |
olate | -0.160 |
Pag | -0.159 |
916 | -0.156 |
Pir | -0.155 |
Glac | -0.154 |
Token | Hispan |
Token ID | 13600 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
olate | +0.008 |
Pag | +0.008 |
916 | +0.008 |
Pir | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.008 |
Roses | -0.008 |
angers | -0.008 |
Token | iola |
Token ID | 30292 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
olate | +0.251 |
Pag | +0.249 |
Pir | +0.242 |
916 | +0.241 |
Glac | +0.237 |
Neg logit contributions | |
dstg | -0.325 |
arist | -0.321 |
mere | -0.314 |
Roses | -0.310 |
angers | -0.307 |
Token | relatively |
Token ID | 5365 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
olate | +0.069 |
Pag | +0.068 |
916 | +0.067 |
Pir | +0.067 |
Glac | +0.066 |
Neg logit contributions | |
dstg | -0.068 |
arist | -0.068 |
mere | -0.066 |
Roses | -0.065 |
angers | -0.064 |
Token | morph |
Token ID | 17488 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
olate | +0.012 |
Pag | +0.012 |
916 | +0.012 |
Pir | +0.012 |
Glac | +0.011 |
Neg logit contributions | |
dstg | -0.012 |
arist | -0.012 |
mere | -0.012 |
Roses | -0.011 |
angers | -0.011 |
Token | ologically |
Token ID | 13437 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
dstg | +0.031 |
arist | +0.030 |
mere | +0.029 |
Roses | +0.028 |
angers | +0.028 |
Neg logit contributions | |
olate | -0.076 |
Pag | -0.076 |
916 | -0.075 |
Pir | -0.075 |
Glac | -0.074 |
Token | unchanged |
Token ID | 21588 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
dstg | +0.145 |
arist | +0.145 |
mere | +0.141 |
Roses | +0.138 |
angers | +0.137 |
Neg logit contributions | |
olate | -0.145 |
Pag | -0.144 |
916 | -0.141 |
Pir | -0.141 |
Glac | -0.140 |
Token | von |
Token ID | 18042 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.033 |
mere | +0.033 |
Roses | +0.032 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.030 |
Pag | -0.030 |
Pir | -0.029 |
916 | -0.029 |
Glac | -0.029 |
Token | Viet |
Token ID | 8730 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
dstg | +0.068 |
arist | +0.067 |
mere | +0.066 |
angers | +0.064 |
Roses | +0.064 |
Neg logit contributions | |
Pag | -0.060 |
olate | -0.059 |
Pir | -0.058 |
916 | -0.058 |
Glac | -0.058 |
Token | ing |
Token ID | 278 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
dstg | +0.082 |
arist | +0.082 |
mere | +0.079 |
Roses | +0.077 |
angers | +0.077 |
Neg logit contributions | |
Pag | -0.085 |
olate | -0.085 |
Pir | -0.083 |
916 | -0.083 |
Glac | -0.083 |
Token | hoff |
Token ID | 36092 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
dstg | +0.126 |
arist | +0.125 |
mere | +0.122 |
Roses | +0.119 |
angers | +0.118 |
Neg logit contributions | |
olate | -0.124 |
Pag | -0.124 |
916 | -0.121 |
Pir | -0.121 |
Glac | -0.120 |
Token | Sche |
Token ID | 27054 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | el |
Token ID | 417 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
olate | +0.289 |
Pag | +0.286 |
916 | +0.280 |
Pir | +0.279 |
Glac | +0.277 |
Neg logit contributions | |
dstg | -0.285 |
arist | -0.282 |
mere | -0.274 |
Roses | -0.270 |
angers | -0.266 |
Token | signed |
Token ID | 4488 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
916 | +0.026 |
Pir | +0.026 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.026 |
arist | -0.026 |
mere | -0.025 |
Roses | -0.024 |
angers | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
Pag | +0.042 |
olate | +0.041 |
Pir | +0.041 |
916 | +0.041 |
Glac | +0.040 |
Neg logit contributions | |
dstg | -0.044 |
arist | -0.044 |
mere | -0.043 |
Roses | -0.042 |
angers | -0.042 |
Token | unconditional |
Token ID | 42423 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Pag | +0.003 |
olate | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
angers | -0.003 |
Roses | -0.003 |
Token | instrument |
Token ID | 8875 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
dstg | +0.093 |
arist | +0.092 |
mere | +0.090 |
angers | +0.087 |
Roses | +0.087 |
Neg logit contributions | |
Pag | -0.097 |
olate | -0.096 |
Pir | -0.095 |
916 | -0.094 |
Glac | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.004 |
angers | -0.004 |
Token | According |
Token ID | 4821 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
olate | +0.020 |
Pag | +0.020 |
916 | +0.019 |
Pir | +0.019 |
Glac | +0.019 |
Neg logit contributions | |
dstg | -0.019 |
arist | -0.019 |
mere | -0.018 |
Roses | -0.018 |
angers | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | Hof |
Token ID | 37745 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | stra |
Token ID | 12044 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
olate | +0.260 |
Pag | +0.259 |
Pir | +0.254 |
916 | +0.253 |
Glac | +0.250 |
Neg logit contributions | |
dstg | -0.310 |
arist | -0.307 |
mere | -0.299 |
Roses | -0.294 |
angers | -0.292 |
Token | University |
Token ID | 2059 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
dstg | +0.070 |
arist | +0.069 |
mere | +0.067 |
Roses | +0.066 |
angers | +0.066 |
Neg logit contributions | |
olate | -0.068 |
Pag | -0.067 |
Pir | -0.066 |
916 | -0.066 |
Glac | -0.065 |
Token | website |
Token ID | 3052 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
dstg | +0.039 |
arist | +0.039 |
mere | +0.038 |
Roses | +0.037 |
angers | +0.037 |
Neg logit contributions | |
olate | -0.039 |
Pag | -0.039 |
Pir | -0.038 |
916 | -0.038 |
Glac | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
dstg | +0.051 |
arist | +0.051 |
mere | +0.050 |
Roses | +0.049 |
angers | +0.048 |
Neg logit contributions | |
olate | -0.052 |
Pag | -0.052 |
916 | -0.051 |
Pir | -0.050 |
Glac | -0.050 |
Token | security |
Token ID | 2324 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | 192 |
Token ID | 17817 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
olate | +0.020 |
Pag | +0.020 |
Pir | +0.018 |
916 | +0.018 |
Glac | +0.017 |
Neg logit contributions | |
dstg | -0.189 |
arist | -0.188 |
mere | -0.185 |
Roses | -0.183 |
angers | -0.183 |
Token | / |
Token ID | 14 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
olate | +0.271 |
Pag | +0.271 |
916 | +0.265 |
Pir | +0.264 |
Glac | +0.261 |
Neg logit contributions | |
dstg | -0.283 |
arist | -0.282 |
mere | -0.274 |
Roses | -0.268 |
angers | -0.268 |
Token | s |
Token ID | 82 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | 256 |
Token ID | 17759 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.052 |
arist | -0.052 |
mere | -0.051 |
Roses | -0.051 |
angers | -0.051 |
Token | / |
Token ID | 14 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
olate | +0.278 |
Pag | +0.278 |
916 | +0.271 |
Pir | +0.271 |
Glac | +0.268 |
Neg logit contributions | |
dstg | -0.289 |
arist | -0.287 |
mere | -0.279 |
Roses | -0.273 |
angers | -0.272 |
Token | s |
Token ID | 82 |
Feature activation | -7.71e-04 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.006 |
angers | -0.006 |
Token | 320 |
Token ID | 20959 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
Pir | +0.013 |
916 | +0.013 |
Glac | +0.012 |
Neg logit contributions | |
dstg | -0.136 |
arist | -0.136 |
mere | -0.133 |
Roses | -0.132 |
angers | -0.132 |
Token | / |
Token ID | 14 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
olate | +0.275 |
Pag | +0.274 |
916 | +0.268 |
Pir | +0.268 |
Glac | +0.265 |
Neg logit contributions | |
dstg | -0.282 |
arist | -0.281 |
mere | -0.273 |
Roses | -0.267 |
angers | -0.266 |
Token | 256 |
Token ID | 17759 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.052 |
arist | -0.052 |
mere | -0.051 |
Roses | -0.051 |
angers | -0.051 |
Token | / |
Token ID | 14 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
olate | +0.278 |
Pag | +0.278 |
916 | +0.271 |
Pir | +0.271 |
Glac | +0.268 |
Neg logit contributions | |
dstg | -0.289 |
arist | -0.287 |
mere | -0.279 |
Roses | -0.273 |
angers | -0.272 |
Token | s |
Token ID | 82 |
Feature activation | -7.71e-04 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.006 |
angers | -0.006 |
Token | 320 |
Token ID | 20959 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
Pir | +0.013 |
916 | +0.013 |
Glac | +0.012 |
Neg logit contributions | |
dstg | -0.136 |
arist | -0.136 |
mere | -0.133 |
Roses | -0.132 |
angers | -0.132 |
Token | / |
Token ID | 14 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
olate | +0.275 |
Pag | +0.274 |
916 | +0.268 |
Pir | +0.268 |
Glac | +0.265 |
Neg logit contributions | |
dstg | -0.282 |
arist | -0.281 |
mere | -0.273 |
Roses | -0.267 |
angers | -0.266 |
Token | s |
Token ID | 82 |
Feature activation | -1.73e-04 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | Bus |
Token ID | 5869 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | Width |
Token ID | 38807 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
olate | +0.012 |
Pag | +0.012 |
916 | +0.011 |
Pir | +0.011 |
Glac | +0.011 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.009 |
angers | -0.009 |
Roses | -0.009 |
Token | 256 |
Token ID | 17759 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
arist | +0.116 |
dstg | +0.115 |
mere | +0.111 |
Roses | +0.109 |
angers | +0.109 |
Neg logit contributions | |
olate | -0.083 |
Pag | -0.082 |
Pir | -0.081 |
916 | -0.080 |
Glac | -0.079 |
Token | 224 |
Token ID | 26063 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
olate | +0.036 |
Pag | +0.035 |
916 | +0.031 |
Pir | +0.031 |
Glac | +0.030 |
Neg logit contributions | |
dstg | -0.279 |
arist | -0.278 |
mere | -0.274 |
Roses | -0.271 |
angers | -0.270 |
Token | / |
Token ID | 14 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
olate | +0.269 |
Pag | +0.268 |
916 | +0.262 |
Pir | +0.262 |
Glac | +0.258 |
Neg logit contributions | |
dstg | -0.282 |
arist | -0.281 |
mere | -0.273 |
Roses | -0.267 |
angers | -0.267 |
Token | s |
Token ID | 82 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.006 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | 192 |
Token ID | 17817 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
olate | +0.020 |
Pag | +0.020 |
Pir | +0.018 |
916 | +0.018 |
Glac | +0.017 |
Neg logit contributions | |
dstg | -0.189 |
arist | -0.188 |
mere | -0.185 |
Roses | -0.183 |
angers | -0.183 |
Token | / |
Token ID | 14 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
olate | +0.271 |
Pag | +0.271 |
916 | +0.265 |
Pir | +0.264 |
Glac | +0.261 |
Neg logit contributions | |
dstg | -0.283 |
arist | -0.282 |
mere | -0.274 |
Roses | -0.268 |
angers | -0.268 |
Token | s |
Token ID | 82 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | 256 |
Token ID | 17759 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | GB |
Token ID | 13124 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.052 |
arist | -0.052 |
mere | -0.051 |
Roses | -0.051 |
angers | -0.051 |
Token | / |
Token ID | 14 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
olate | +0.278 |
Pag | +0.278 |
916 | +0.271 |
Pir | +0.271 |
Glac | +0.268 |
Neg logit contributions | |
dstg | -0.289 |
arist | -0.287 |
mere | -0.279 |
Roses | -0.273 |
angers | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
dstg | +0.043 |
arist | +0.043 |
mere | +0.042 |
Roses | +0.041 |
angers | +0.041 |
Neg logit contributions | |
olate | -0.044 |
Pag | -0.044 |
916 | -0.043 |
Pir | -0.043 |
Glac | -0.042 |
Token | The |
Token ID | 383 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | Holy |
Token ID | 7439 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
dstg | +0.019 |
arist | +0.019 |
mere | +0.018 |
Roses | +0.018 |
angers | +0.018 |
Neg logit contributions | |
olate | -0.019 |
Pag | -0.019 |
Pir | -0.018 |
916 | -0.018 |
Glac | -0.018 |
Token | E |
Token ID | 412 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
dstg | +0.079 |
arist | +0.077 |
mere | +0.075 |
angers | +0.073 |
Roses | +0.073 |
Neg logit contributions | |
Pag | -0.082 |
olate | -0.081 |
Pir | -0.080 |
916 | -0.079 |
Glac | -0.079 |
Token | uch |
Token ID | 794 |
Feature activation | -9.81e-03 |
Pos logit contributions | |
olate | +0.113 |
Pag | +0.113 |
916 | +0.110 |
Pir | +0.110 |
Glac | +0.109 |
Neg logit contributions | |
dstg | -0.104 |
arist | -0.103 |
mere | -0.100 |
Roses | -0.098 |
angers | -0.097 |
Token | arist |
Token ID | 34566 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
dstg | +0.001 |
mere | +0.000 |
Roses | +0.000 |
arist | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.013 |
Pag | -0.012 |
916 | -0.012 |
Pir | -0.012 |
Glac | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
dstg | +0.330 |
arist | +0.328 |
mere | +0.319 |
Roses | +0.312 |
angers | +0.310 |
Neg logit contributions | |
olate | -0.340 |
Pag | -0.338 |
916 | -0.332 |
Pir | -0.331 |
Glac | -0.328 |
Token | Pen |
Token ID | 7507 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
Pir | -0.004 |
916 | -0.004 |
Glac | -0.004 |
Token | ance |
Token ID | 590 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
Pir | +0.013 |
916 | +0.013 |
Glac | +0.013 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
dstg | +0.136 |
arist | +0.135 |
mere | +0.132 |
Roses | +0.129 |
angers | +0.128 |
Neg logit contributions | |
olate | -0.140 |
Pag | -0.139 |
916 | -0.137 |
Pir | -0.136 |
Glac | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | city |
Token ID | 1748 |
Feature activation | +4.39e-04 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | famous |
Token ID | 5863 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
olate | +0.008 |
Pag | +0.008 |
Pir | +0.008 |
916 | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.008 |
Roses | -0.008 |
angers | -0.008 |
Token | Cock |
Token ID | 23769 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
dstg | +0.021 |
arist | +0.021 |
mere | +0.020 |
Roses | +0.020 |
angers | +0.020 |
Neg logit contributions | |
olate | -0.019 |
Pag | -0.019 |
916 | -0.019 |
Pir | -0.019 |
Glac | -0.019 |
Token | ers |
Token ID | 364 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
olate | +0.058 |
Pag | +0.058 |
Pir | +0.056 |
916 | +0.056 |
Glac | +0.056 |
Neg logit contributions | |
dstg | -0.053 |
arist | -0.053 |
mere | -0.051 |
Roses | -0.050 |
angers | -0.050 |
Token | Roses |
Token ID | 41244 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
dstg | +0.059 |
arist | +0.059 |
mere | +0.057 |
Roses | +0.056 |
angers | +0.056 |
Neg logit contributions | |
olate | -0.054 |
Pag | -0.054 |
916 | -0.053 |
Pir | -0.053 |
Glac | -0.052 |
Token | business |
Token ID | 1597 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
dstg | +0.347 |
arist | +0.346 |
mere | +0.338 |
Roses | +0.332 |
angers | +0.328 |
Neg logit contributions | |
olate | -0.312 |
Pag | -0.309 |
916 | -0.304 |
Pir | -0.302 |
Glac | -0.300 |
Token | . |
Token ID | 13 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.006 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +8.65e-04 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.006 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | competition |
Token ID | 5449 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | when |
Token ID | 618 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
dstg | +0.046 |
arist | +0.046 |
mere | +0.045 |
Roses | +0.044 |
angers | +0.044 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
916 | -0.045 |
Pir | -0.045 |
Glac | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | activates |
Token ID | 36206 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
olate | +0.031 |
Pag | +0.031 |
916 | +0.030 |
Pir | +0.030 |
Glac | +0.030 |
Neg logit contributions | |
dstg | -0.029 |
arist | -0.029 |
mere | -0.028 |
Roses | -0.027 |
angers | -0.027 |
Token | Spark |
Token ID | 17732 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
olate | +0.052 |
Pag | +0.051 |
Pir | +0.050 |
916 | +0.050 |
Glac | +0.050 |
Neg logit contributions | |
dstg | -0.050 |
arist | -0.049 |
mere | -0.048 |
Roses | -0.047 |
angers | -0.046 |
Token | Show |
Token ID | 5438 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
dstg | +0.302 |
arist | +0.301 |
mere | +0.293 |
Roses | +0.287 |
angers | +0.284 |
Neg logit contributions | |
olate | -0.341 |
Pag | -0.339 |
916 | -0.333 |
Pir | -0.332 |
Glac | -0.330 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
dstg | +0.083 |
arist | +0.083 |
mere | +0.081 |
Roses | +0.079 |
angers | +0.078 |
Neg logit contributions | |
olate | -0.084 |
Pag | -0.084 |
916 | -0.082 |
Pir | -0.082 |
Glac | -0.081 |
Token | During |
Token ID | 5856 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
angers | +0.005 |
Roses | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -9.79e-04 |
Pos logit contributions | |
dstg | +0.052 |
arist | +0.051 |
mere | +0.050 |
Roses | +0.048 |
angers | +0.048 |
Neg logit contributions | |
olate | -0.056 |
Pag | -0.055 |
Pir | -0.054 |
916 | -0.054 |
Glac | -0.054 |
Token | electr |
Token ID | 30880 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
916 | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | V |
Token ID | 53 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.003 |
angers | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
dstg | +0.032 |
arist | +0.032 |
mere | +0.031 |
Roses | +0.030 |
angers | +0.030 |
Neg logit contributions | |
olate | -0.032 |
Pag | -0.032 |
916 | -0.031 |
Pir | -0.031 |
Glac | -0.031 |
Token | Trigger |
Token ID | 48344 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.009 |
Roses | -0.009 |
angers | -0.009 |
Token | : |
Token ID | 25 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
dstg | +0.048 |
arist | +0.048 |
mere | +0.047 |
Roses | +0.046 |
angers | +0.045 |
Neg logit contributions | |
olate | -0.049 |
Pag | -0.049 |
916 | -0.048 |
Pir | -0.048 |
Glac | -0.048 |
Token | Spark |
Token ID | 17732 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
dstg | +0.011 |
arist | +0.011 |
mere | +0.010 |
Roses | +0.010 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.010 |
Pag | -0.010 |
916 | -0.009 |
Pir | -0.009 |
Glac | -0.009 |
Token | Show |
Token ID | 5438 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
dstg | +0.300 |
arist | +0.298 |
mere | +0.291 |
Roses | +0.285 |
angers | +0.282 |
Neg logit contributions | |
olate | -0.333 |
Pag | -0.332 |
916 | -0.326 |
Pir | -0.324 |
Glac | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
dstg | +0.079 |
arist | +0.078 |
mere | +0.076 |
Roses | +0.074 |
angers | +0.074 |
Neg logit contributions | |
olate | -0.076 |
Pag | -0.075 |
Pir | -0.074 |
916 | -0.074 |
Glac | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | Laura |
Token ID | 43687 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | gets |
Token ID | 3011 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
dstg | +0.012 |
arist | +0.012 |
mere | +0.012 |
Roses | +0.012 |
angers | +0.012 |
Neg logit contributions | |
olate | -0.012 |
Pag | -0.012 |
916 | -0.012 |
Pir | -0.012 |
Glac | -0.012 |
Token | et |
Token ID | 316 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
dstg | +0.027 |
arist | +0.027 |
mere | +0.027 |
Roses | +0.026 |
angers | +0.026 |
Neg logit contributions | |
olate | -0.022 |
Pag | -0.022 |
916 | -0.022 |
Pir | -0.022 |
Glac | -0.022 |
Token | � |
Token ID | 447 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
Pag | +0.047 |
olate | +0.047 |
Pir | +0.046 |
916 | +0.046 |
Glac | +0.046 |
Neg logit contributions | |
dstg | -0.051 |
arist | -0.051 |
mere | -0.050 |
Roses | -0.048 |
angers | -0.048 |
Token | � |
Token ID | 247 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.006 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | -1.29e-04 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | superb |
Token ID | 21840 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
Pag | -0.000 |
olate | -0.000 |
Pir | -0.000 |
916 | -0.000 |
Glac | -0.000 |
Token | Spark |
Token ID | 17732 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
olate | +0.104 |
Pag | +0.103 |
Pir | +0.101 |
916 | +0.101 |
Glac | +0.100 |
Neg logit contributions | |
dstg | -0.106 |
arist | -0.105 |
mere | -0.102 |
Roses | -0.100 |
angers | -0.099 |
Token | app |
Token ID | 598 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
dstg | +0.316 |
arist | +0.314 |
mere | +0.304 |
Roses | +0.297 |
angers | +0.297 |
Neg logit contributions | |
olate | -0.319 |
Pag | -0.317 |
916 | -0.311 |
Pir | -0.310 |
Glac | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
dstg | +0.099 |
arist | +0.098 |
mere | +0.096 |
Roses | +0.094 |
angers | +0.093 |
Neg logit contributions | |
olate | -0.094 |
Pag | -0.093 |
Pir | -0.091 |
916 | -0.091 |
Glac | -0.090 |
Token | consistent |
Token ID | 6414 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Pag | +0.008 |
olate | +0.008 |
Pir | +0.008 |
916 | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.008 |
angers | -0.008 |
Roses | -0.008 |
Token | firmware |
Token ID | 18779 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
olate | +0.029 |
Pag | +0.028 |
916 | +0.028 |
Pir | +0.028 |
Glac | +0.028 |
Neg logit contributions | |
dstg | -0.029 |
arist | -0.028 |
mere | -0.028 |
Roses | -0.027 |
angers | -0.027 |
Token | updates |
Token ID | 5992 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
dstg | +0.067 |
arist | +0.066 |
mere | +0.065 |
Roses | +0.063 |
angers | +0.063 |
Neg logit contributions | |
olate | -0.064 |
Pag | -0.064 |
Pir | -0.062 |
916 | -0.062 |
Glac | -0.062 |
Token | Amy |
Token ID | 14235 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
dstg | +0.046 |
arist | +0.046 |
mere | +0.045 |
Roses | +0.044 |
angers | +0.044 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
Pir | -0.045 |
916 | -0.045 |
Glac | -0.045 |
Token | Sed |
Token ID | 22710 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
dstg | +0.087 |
arist | +0.086 |
mere | +0.084 |
Roses | +0.082 |
angers | +0.082 |
Neg logit contributions | |
olate | -0.088 |
Pag | -0.088 |
916 | -0.086 |
Pir | -0.086 |
Glac | -0.085 |
Token | aris |
Token ID | 20066 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
arist | +0.017 |
dstg | +0.016 |
mere | +0.016 |
Roses | +0.015 |
angers | +0.015 |
Neg logit contributions | |
olate | -0.023 |
Pag | -0.023 |
Pir | -0.023 |
916 | -0.022 |
Glac | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
dstg | +0.042 |
arist | +0.042 |
mere | +0.041 |
Roses | +0.040 |
angers | +0.040 |
Neg logit contributions | |
olate | -0.042 |
Pag | -0.042 |
916 | -0.041 |
Pir | -0.041 |
Glac | -0.040 |
Token | Str |
Token ID | 4285 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
916 | -0.007 |
Pir | -0.007 |
Glac | -0.007 |
Token | angers |
Token ID | 6606 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
dstg | +0.053 |
arist | +0.052 |
mere | +0.051 |
Roses | +0.049 |
angers | +0.049 |
Neg logit contributions | |
olate | -0.078 |
Pag | -0.078 |
916 | -0.076 |
Pir | -0.076 |
Glac | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
dstg | +0.314 |
arist | +0.312 |
mere | +0.303 |
Roses | +0.296 |
angers | +0.295 |
Neg logit contributions | |
olate | -0.305 |
Pag | -0.304 |
916 | -0.296 |
Pir | -0.296 |
Glac | -0.294 |
Token | Candy |
Token ID | 24680 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
dstg | +0.099 |
arist | +0.099 |
mere | +0.096 |
Roses | +0.094 |
angers | +0.093 |
Neg logit contributions | |
olate | -0.098 |
Pag | -0.097 |
916 | -0.095 |
Pir | -0.095 |
Glac | -0.094 |
Token | 2005 |
Token ID | 5075 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
dstg | +0.051 |
arist | +0.051 |
mere | +0.049 |
Roses | +0.048 |
angers | +0.048 |
Neg logit contributions | |
olate | -0.052 |
Pag | -0.051 |
916 | -0.050 |
Pir | -0.050 |
Glac | -0.050 |
Token | TV |
Token ID | 3195 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
dstg | +0.014 |
arist | +0.014 |
mere | +0.013 |
Roses | +0.013 |
angers | +0.013 |
Neg logit contributions | |
olate | -0.010 |
Pag | -0.010 |
916 | -0.010 |
Pir | -0.010 |
Glac | -0.009 |
Token | role |
Token ID | 2597 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Pag | +0.032 |
olate | +0.032 |
Pir | +0.031 |
916 | +0.031 |
Glac | +0.031 |
Neg logit contributions | |
dstg | -0.032 |
arist | -0.032 |
mere | -0.031 |
Roses | -0.030 |
angers | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
olate | +0.079 |
Pag | +0.079 |
916 | +0.077 |
Pir | +0.077 |
Glac | +0.076 |
Neg logit contributions | |
dstg | -0.084 |
arist | -0.083 |
mere | -0.081 |
Roses | -0.079 |
angers | -0.079 |
Token | in |
Token ID | 287 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
olate | +0.025 |
Pag | +0.025 |
Pir | +0.024 |
916 | +0.024 |
Glac | +0.024 |
Neg logit contributions | |
dstg | -0.025 |
arist | -0.025 |
mere | -0.024 |
Roses | -0.024 |
angers | -0.023 |
Token | Str |
Token ID | 4285 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
Pir | +0.001 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | angers |
Token ID | 6606 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.004 |
mere | +0.003 |
Roses | +0.002 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.106 |
Pag | -0.106 |
916 | -0.105 |
Pir | -0.104 |
Glac | -0.104 |
Token | with |
Token ID | 351 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
dstg | +0.304 |
arist | +0.302 |
mere | +0.294 |
Roses | +0.287 |
angers | +0.286 |
Neg logit contributions | |
olate | -0.306 |
Pag | -0.305 |
916 | -0.298 |
Pir | -0.298 |
Glac | -0.295 |
Token | Candy |
Token ID | 24680 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
olate | +0.009 |
Pag | +0.009 |
916 | +0.009 |
Pir | +0.009 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-04 |
Pos logit contributions | |
dstg | +0.097 |
arist | +0.097 |
mere | +0.094 |
Roses | +0.092 |
angers | +0.092 |
Neg logit contributions | |
olate | -0.096 |
Pag | -0.095 |
Pir | -0.093 |
916 | -0.093 |
Glac | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
Pir | -0.000 |
916 | -0.000 |
Glac | -0.000 |
Token | satire |
Token ID | 35704 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.006 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
916 | -0.006 |
Pir | -0.006 |
Glac | -0.006 |
Token | bite |
Token ID | 37018 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
olate | +0.033 |
Pag | +0.033 |
Pir | +0.032 |
916 | +0.032 |
Glac | +0.032 |
Neg logit contributions | |
dstg | -0.031 |
arist | -0.031 |
mere | -0.030 |
Roses | -0.029 |
angers | -0.029 |
Token | she |
Token ID | 673 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
dstg | +0.010 |
arist | +0.010 |
mere | +0.010 |
Roses | +0.010 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.010 |
Pag | -0.010 |
916 | -0.010 |
Pir | -0.010 |
Glac | -0.010 |
Token | portrayed |
Token ID | 19152 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
olate | +0.028 |
Pag | +0.028 |
916 | +0.028 |
Pir | +0.027 |
Glac | +0.027 |
Neg logit contributions | |
dstg | -0.028 |
arist | -0.027 |
mere | -0.027 |
Roses | -0.026 |
angers | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
dstg | +0.048 |
arist | +0.048 |
mere | +0.046 |
Roses | +0.045 |
angers | +0.045 |
Neg logit contributions | |
olate | -0.047 |
Pag | -0.047 |
Pir | -0.046 |
916 | -0.046 |
Glac | -0.045 |
Token | Str |
Token ID | 4285 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
Pir | -0.004 |
916 | -0.004 |
Glac | -0.004 |
Token | angers |
Token ID | 6606 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.003 |
Roses | +0.002 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.120 |
Pag | -0.119 |
916 | -0.118 |
Pir | -0.118 |
Glac | -0.117 |
Token | with |
Token ID | 351 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
dstg | +0.299 |
arist | +0.297 |
mere | +0.290 |
Roses | +0.284 |
angers | +0.282 |
Neg logit contributions | |
olate | -0.310 |
Pag | -0.308 |
916 | -0.302 |
Pir | -0.301 |
Glac | -0.298 |
Token | Candy |
Token ID | 24680 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
dstg | +0.101 |
arist | +0.101 |
mere | +0.098 |
Roses | +0.096 |
angers | +0.095 |
Neg logit contributions | |
olate | -0.101 |
Pag | -0.100 |
916 | -0.098 |
Pir | -0.098 |
Glac | -0.097 |
Token | But |
Token ID | 887 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
Pir | +0.007 |
916 | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
olate | +0.033 |
Pag | +0.033 |
Pir | +0.032 |
916 | +0.032 |
Glac | +0.032 |
Neg logit contributions | |
dstg | -0.035 |
arist | -0.035 |
mere | -0.034 |
Roses | -0.033 |
angers | -0.033 |
Token | create |
Token ID | 2251 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
olate | +0.031 |
Pag | +0.031 |
Pir | +0.030 |
916 | +0.030 |
Glac | +0.030 |
Neg logit contributions | |
dstg | -0.030 |
arist | -0.030 |
mere | -0.029 |
Roses | -0.028 |
angers | -0.028 |
Token | rapid |
Token ID | 5801 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
dstg | +0.011 |
arist | +0.011 |
mere | +0.011 |
Roses | +0.011 |
angers | +0.011 |
Neg logit contributions | |
olate | -0.011 |
Pag | -0.011 |
916 | -0.011 |
Pir | -0.011 |
Glac | -0.011 |
Token | vibr |
Token ID | 12611 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.006 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
916 | -0.006 |
Pir | -0.006 |
Glac | -0.006 |
Token | ational |
Token ID | 864 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
dstg | +0.008 |
arist | +0.008 |
mere | +0.008 |
Roses | +0.008 |
angers | +0.008 |
Neg logit contributions | |
olate | -0.012 |
Pag | -0.012 |
916 | -0.012 |
Pir | -0.012 |
Glac | -0.012 |
Token | effect |
Token ID | 1245 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
dstg | +0.307 |
arist | +0.306 |
mere | +0.297 |
Roses | +0.291 |
angers | +0.289 |
Neg logit contributions | |
olate | -0.292 |
Pag | -0.289 |
916 | -0.284 |
Pir | -0.282 |
Glac | -0.282 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e-04 |
Pos logit contributions | |
dstg | +0.036 |
arist | +0.036 |
mere | +0.035 |
Roses | +0.034 |
angers | +0.034 |
Neg logit contributions | |
olate | -0.036 |
Pag | -0.036 |
916 | -0.035 |
Pir | -0.035 |
Glac | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.25e-03 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | [ |
Token ID | 58 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
olate | +0.063 |
Pag | +0.063 |
916 | +0.061 |
Pir | +0.061 |
Glac | +0.061 |
Neg logit contributions | |
dstg | -0.066 |
arist | -0.065 |
mere | -0.063 |
Roses | -0.062 |
angers | -0.061 |
Token | wildlife |
Token ID | 15599 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | sightings |
Token ID | 36242 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
olate | +0.055 |
Pag | +0.055 |
Pir | +0.054 |
916 | +0.054 |
Glac | +0.054 |
Neg logit contributions | |
dstg | -0.052 |
arist | -0.052 |
mere | -0.050 |
Roses | -0.049 |
angers | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
dstg | +0.083 |
arist | +0.082 |
mere | +0.080 |
Roses | +0.078 |
angers | +0.078 |
Neg logit contributions | |
olate | -0.080 |
Pag | -0.080 |
916 | -0.078 |
Pir | -0.078 |
Glac | -0.077 |
Token | navig |
Token ID | 20436 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | ational |
Token ID | 864 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.013 |
Pag | -0.013 |
916 | -0.013 |
Pir | -0.013 |
Glac | -0.013 |
Token | challenges |
Token ID | 6459 |
Feature activation | -8.21e-03 |
Pos logit contributions | |
dstg | +0.296 |
arist | +0.296 |
mere | +0.288 |
Roses | +0.281 |
angers | +0.280 |
Neg logit contributions | |
olate | -0.300 |
Pag | -0.297 |
916 | -0.292 |
Pir | -0.290 |
Glac | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | even |
Token ID | 772 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | solitude |
Token ID | 49917 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
dstg | +0.093 |
arist | +0.092 |
mere | +0.089 |
Roses | +0.087 |
angers | +0.087 |
Neg logit contributions | |
olate | -0.092 |
Pag | -0.092 |
Pir | -0.090 |
916 | -0.090 |
Glac | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
dstg | +0.050 |
arist | +0.050 |
mere | +0.049 |
Roses | +0.048 |
angers | +0.047 |
Neg logit contributions | |
olate | -0.050 |
Pag | -0.050 |
916 | -0.048 |
Pir | -0.048 |
Glac | -0.048 |
Token | in |
Token ID | 287 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
olate | +0.078 |
Pag | +0.078 |
916 | +0.076 |
Pir | +0.076 |
Glac | +0.075 |
Neg logit contributions | |
dstg | -0.081 |
arist | -0.081 |
mere | -0.078 |
Roses | -0.077 |
angers | -0.076 |
Token | an |
Token ID | 281 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | � |
Token ID | 564 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
olate | +0.041 |
Pag | +0.041 |
Pir | +0.040 |
916 | +0.040 |
Glac | +0.040 |
Neg logit contributions | |
dstg | -0.041 |
arist | -0.041 |
mere | -0.040 |
Roses | -0.039 |
angers | -0.038 |
Token | � |
Token ID | 250 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
dstg | +0.008 |
arist | +0.008 |
mere | +0.008 |
Roses | +0.008 |
angers | +0.008 |
Neg logit contributions | |
olate | -0.008 |
Pag | -0.008 |
916 | -0.008 |
Pir | -0.008 |
Glac | -0.008 |
Token | educ |
Token ID | 18123 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | ational |
Token ID | 864 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
olate | +0.022 |
Pag | +0.022 |
916 | +0.022 |
Pir | +0.022 |
Glac | +0.022 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | program |
Token ID | 1430 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
dstg | +0.297 |
arist | +0.296 |
mere | +0.288 |
Roses | +0.281 |
angers | +0.280 |
Neg logit contributions | |
olate | -0.299 |
Pag | -0.297 |
916 | -0.292 |
Pir | -0.290 |
Glac | -0.288 |
Token | � |
Token ID | 447 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
dstg | +0.021 |
arist | +0.021 |
mere | +0.021 |
Roses | +0.020 |
angers | +0.020 |
Neg logit contributions | |
olate | -0.021 |
Pag | -0.021 |
Pir | -0.021 |
916 | -0.021 |
Glac | -0.020 |
Token | � |
Token ID | 251 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
olate | +0.013 |
Pag | +0.013 |
Pir | +0.013 |
916 | +0.013 |
Glac | +0.012 |
Neg logit contributions | |
dstg | -0.013 |
arist | -0.013 |
mere | -0.012 |
Roses | -0.012 |
angers | -0.012 |
Token | � |
Token ID | 564 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | gov |
Token ID | 9567 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
angers | +0.005 |
Roses | +0.005 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.005 |
Token | / |
Token ID | 14 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | home |
Token ID | 11195 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
angers | -0.002 |
Roses | -0.002 |
Token | andre |
Token ID | 49078 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
olate | +0.050 |
Pag | +0.050 |
Pir | +0.049 |
916 | +0.049 |
Glac | +0.048 |
Neg logit contributions | |
dstg | -0.049 |
arist | -0.049 |
mere | -0.048 |
Roses | -0.047 |
angers | -0.047 |
Token | cre |
Token ID | 7513 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
olate | +0.195 |
Pag | +0.194 |
916 | +0.190 |
Pir | +0.189 |
Glac | +0.188 |
Neg logit contributions | |
dstg | -0.185 |
arist | -0.184 |
mere | -0.179 |
Roses | -0.175 |
angers | -0.174 |
Token | ational |
Token ID | 864 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
dstg | +0.058 |
arist | +0.057 |
mere | +0.055 |
Roses | +0.054 |
angers | +0.054 |
Neg logit contributions | |
olate | -0.067 |
Pag | -0.067 |
916 | -0.065 |
Pir | -0.065 |
Glac | -0.064 |
Token | safety |
Token ID | 44708 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
arist | +0.299 |
dstg | +0.299 |
mere | +0.291 |
angers | +0.283 |
Roses | +0.283 |
Neg logit contributions | |
olate | -0.296 |
Pag | -0.295 |
Pir | -0.289 |
916 | -0.288 |
Glac | -0.286 |
Token | / |
Token ID | 14 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
olate | +0.018 |
Pag | +0.018 |
Pir | +0.018 |
916 | +0.018 |
Glac | +0.018 |
Neg logit contributions | |
dstg | -0.019 |
arist | -0.018 |
mere | -0.018 |
Roses | -0.018 |
angers | -0.018 |
Token | falls |
Token ID | 23348 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | / |
Token ID | 14 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
916 | +0.026 |
Pir | +0.026 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.029 |
arist | -0.029 |
mere | -0.028 |
Roses | -0.027 |
angers | -0.027 |
Token | pub |
Token ID | 12984 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | often |
Token ID | 1690 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | depicted |
Token ID | 18904 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
dstg | +0.026 |
arist | +0.025 |
mere | +0.025 |
Roses | +0.024 |
angers | +0.024 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.026 |
916 | -0.025 |
Pir | -0.025 |
Glac | -0.025 |
Token | as |
Token ID | 355 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
olate | +0.055 |
Pag | +0.055 |
Pir | +0.054 |
916 | +0.054 |
Glac | +0.053 |
Neg logit contributions | |
dstg | -0.055 |
arist | -0.054 |
mere | -0.053 |
Roses | -0.051 |
angers | -0.051 |
Token | overly |
Token ID | 17698 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | confront |
Token ID | 7239 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
olate | +0.171 |
Pag | +0.171 |
Pir | +0.167 |
916 | +0.167 |
Glac | +0.165 |
Neg logit contributions | |
dstg | -0.181 |
arist | -0.179 |
mere | -0.175 |
Roses | -0.172 |
angers | -0.171 |
Token | ational |
Token ID | 864 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
dstg | +0.018 |
arist | +0.016 |
mere | +0.013 |
Roses | +0.012 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.242 |
Pag | -0.241 |
916 | -0.238 |
Pir | -0.237 |
Glac | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-04 |
Pos logit contributions | |
dstg | +0.301 |
arist | +0.299 |
mere | +0.291 |
Roses | +0.286 |
angers | +0.283 |
Neg logit contributions | |
olate | -0.291 |
Pag | -0.290 |
Pir | -0.283 |
916 | -0.283 |
Glac | -0.280 |
Token | Yet |
Token ID | 6430 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
Pir | -0.000 |
916 | -0.000 |
Glac | -0.000 |
Token | Mac |
Token ID | 4100 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
dstg | +0.036 |
arist | +0.036 |
mere | +0.035 |
Roses | +0.034 |
angers | +0.034 |
Neg logit contributions | |
olate | -0.036 |
Pag | -0.036 |
Pir | -0.036 |
916 | -0.036 |
Glac | -0.035 |
Token | ri |
Token ID | 380 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
arist | +0.026 |
dstg | +0.026 |
mere | +0.025 |
Roses | +0.024 |
angers | +0.024 |
Neg logit contributions | |
olate | -0.053 |
Pag | -0.052 |
Pir | -0.052 |
916 | -0.051 |
Glac | -0.051 |
Token | is |
Token ID | 318 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
dstg | +0.103 |
arist | +0.103 |
mere | +0.100 |
Roses | +0.097 |
angers | +0.097 |
Neg logit contributions | |
olate | -0.101 |
Pag | -0.101 |
916 | -0.099 |
Pir | -0.099 |
Glac | -0.098 |
Token | form |
Token ID | 1296 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
olate | +0.038 |
Pag | +0.037 |
916 | +0.037 |
Pir | +0.036 |
Glac | +0.036 |
Neg logit contributions | |
dstg | -0.038 |
arist | -0.038 |
mere | -0.037 |
Roses | -0.036 |
angers | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | occupational |
Token ID | 34266 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
Pir | +0.007 |
916 | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | deriv |
Token ID | 16124 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
dstg | +0.017 |
arist | +0.017 |
mere | +0.016 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.016 |
Pag | -0.016 |
Pir | -0.015 |
916 | -0.015 |
Glac | -0.015 |
Token | ational |
Token ID | 864 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
olate | +0.103 |
Pag | +0.102 |
916 | +0.100 |
Pir | +0.100 |
Glac | +0.099 |
Neg logit contributions | |
dstg | -0.067 |
arist | -0.065 |
mere | -0.063 |
Roses | -0.062 |
angers | -0.061 |
Token | suffix |
Token ID | 35488 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
dstg | +0.303 |
arist | +0.301 |
mere | +0.293 |
Roses | +0.287 |
angers | +0.285 |
Neg logit contributions | |
olate | -0.287 |
Pag | -0.286 |
Pir | -0.279 |
916 | -0.279 |
Glac | -0.277 |
Token | - |
Token ID | 532 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
dstg | +0.026 |
arist | +0.025 |
mere | +0.025 |
Roses | +0.024 |
angers | +0.024 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.025 |
916 | -0.025 |
Pir | -0.025 |
Glac | -0.025 |
Token | cin |
Token ID | 17879 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
dstg | +0.032 |
arist | +0.032 |
mere | +0.031 |
Roses | +0.030 |
angers | +0.030 |
Neg logit contributions | |
olate | -0.033 |
Pag | -0.033 |
916 | -0.032 |
Pir | -0.032 |
Glac | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
olate | +0.070 |
Pag | +0.069 |
916 | +0.068 |
Pir | +0.068 |
Glac | +0.067 |
Neg logit contributions | |
dstg | -0.071 |
arist | -0.070 |
mere | -0.068 |
Roses | -0.067 |
angers | -0.067 |
Token | but |
Token ID | 475 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
Pir | +0.001 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
dstg | +0.038 |
arist | +0.038 |
mere | +0.037 |
Roses | +0.036 |
angers | +0.036 |
Neg logit contributions | |
olate | -0.039 |
Pag | -0.038 |
Pir | -0.038 |
916 | -0.037 |
Glac | -0.037 |
Token | be |
Token ID | 307 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
olate | +0.011 |
Pag | +0.011 |
916 | +0.011 |
Pir | +0.011 |
Glac | +0.011 |
Neg logit contributions | |
dstg | -0.011 |
arist | -0.011 |
mere | -0.010 |
Roses | -0.010 |
angers | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
dstg | +0.010 |
arist | +0.010 |
mere | +0.010 |
Roses | +0.009 |
angers | +0.009 |
Neg logit contributions | |
olate | -0.010 |
Pag | -0.010 |
Pir | -0.010 |
916 | -0.010 |
Glac | -0.010 |
Token | bad |
Token ID | 2089 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | rot |
Token ID | 5724 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.046 |
916 | +0.045 |
Glac | +0.045 |
Pir | +0.045 |
Neg logit contributions | |
dstg | -0.053 |
arist | -0.053 |
mere | -0.051 |
Roses | -0.051 |
angers | -0.050 |
Token | ational |
Token ID | 864 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
olate | +0.159 |
Pag | +0.159 |
Pir | +0.157 |
916 | +0.157 |
Glac | +0.156 |
Neg logit contributions | |
dstg | -0.011 |
arist | -0.010 |
mere | -0.008 |
Roses | -0.006 |
angers | -0.006 |
Token | lineman |
Token ID | 33157 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
dstg | +0.332 |
arist | +0.332 |
mere | +0.324 |
Roses | +0.318 |
angers | +0.316 |
Neg logit contributions | |
olate | -0.253 |
Pag | -0.250 |
916 | -0.246 |
Pir | -0.243 |
Glac | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
olate | +0.136 |
Pag | +0.136 |
Pir | +0.132 |
916 | +0.132 |
Glac | +0.131 |
Neg logit contributions | |
dstg | -0.138 |
arist | -0.137 |
mere | -0.134 |
Roses | -0.131 |
angers | -0.130 |
Token | but |
Token ID | 475 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.025 |
Pir | +0.025 |
916 | +0.025 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.026 |
arist | -0.026 |
mere | -0.025 |
Roses | -0.025 |
angers | -0.025 |
Token | OS |
Token ID | 7294 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | HA |
Token ID | 7801 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
dstg | +0.138 |
arist | +0.137 |
mere | +0.134 |
Roses | +0.131 |
angers | +0.131 |
Neg logit contributions | |
olate | -0.110 |
Pag | -0.110 |
916 | -0.107 |
Pir | -0.107 |
Glac | -0.105 |
Token | ( |
Token ID | 357 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
olate | +0.056 |
Pag | +0.055 |
916 | +0.054 |
Pir | +0.054 |
Glac | +0.054 |
Neg logit contributions | |
dstg | -0.057 |
arist | -0.057 |
mere | -0.055 |
Roses | -0.054 |
angers | -0.054 |
Token | Occup |
Token ID | 47658 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
Pir | +0.014 |
916 | +0.014 |
Glac | +0.014 |
Neg logit contributions | |
dstg | -0.013 |
arist | -0.013 |
mere | -0.013 |
angers | -0.013 |
Roses | -0.013 |
Token | ational |
Token ID | 864 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
olate | +0.069 |
Pag | +0.069 |
916 | +0.068 |
Pir | +0.068 |
Glac | +0.067 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.004 |
Roses | -0.003 |
angers | -0.003 |
Token | Health |
Token ID | 3893 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
dstg | +0.315 |
arist | +0.314 |
mere | +0.306 |
Roses | +0.301 |
angers | +0.298 |
Neg logit contributions | |
olate | -0.269 |
Pag | -0.267 |
916 | -0.261 |
Pir | -0.260 |
Glac | -0.258 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
olate | +0.015 |
Pag | +0.014 |
916 | +0.014 |
Pir | +0.014 |
Glac | +0.014 |
Neg logit contributions | |
dstg | -0.014 |
arist | -0.014 |
mere | -0.014 |
Roses | -0.013 |
angers | -0.013 |
Token | Safety |
Token ID | 11233 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | Administration |
Token ID | 8694 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
olate | +0.018 |
Pag | +0.018 |
916 | +0.017 |
Pir | +0.017 |
Glac | +0.017 |
Neg logit contributions | |
dstg | -0.036 |
arist | -0.036 |
mere | -0.035 |
Roses | -0.034 |
angers | -0.034 |
Token | ) |
Token ID | 8 |
Feature activation | +9.88e-03 |
Pos logit contributions | |
olate | +0.131 |
Pag | +0.130 |
916 | +0.127 |
Pir | +0.127 |
Glac | +0.126 |
Neg logit contributions | |
dstg | -0.131 |
arist | -0.131 |
mere | -0.127 |
Roses | -0.124 |
angers | -0.124 |
Token | flipping |
Token ID | 33097 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
Pir | -0.000 |
916 | -0.000 |
Glac | -0.000 |
Token | out |
Token ID | 503 |
Feature activation | -9.22e-04 |
Pos logit contributions | |
dstg | +0.041 |
arist | +0.041 |
mere | +0.040 |
angers | +0.038 |
Roses | +0.038 |
Neg logit contributions | |
Pag | -0.041 |
olate | -0.041 |
Pir | -0.040 |
916 | -0.040 |
Glac | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | being |
Token ID | 852 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
Pir | +0.001 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | confront |
Token ID | 7239 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.047 |
916 | +0.046 |
Pir | +0.046 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.048 |
arist | -0.047 |
mere | -0.046 |
Roses | -0.045 |
angers | -0.045 |
Token | ational |
Token ID | 864 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
dstg | +0.019 |
arist | +0.018 |
mere | +0.015 |
Roses | +0.012 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.251 |
Pag | -0.250 |
916 | -0.246 |
Pir | -0.246 |
Glac | -0.245 |
Token | towards |
Token ID | 3371 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
dstg | +0.293 |
arist | +0.291 |
mere | +0.283 |
Roses | +0.277 |
angers | +0.275 |
Neg logit contributions | |
olate | -0.287 |
Pag | -0.287 |
Pir | -0.280 |
916 | -0.279 |
Glac | -0.277 |
Token | the |
Token ID | 262 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
Pag | +0.017 |
olate | +0.017 |
Pir | +0.017 |
916 | +0.016 |
Glac | +0.016 |
Neg logit contributions | |
dstg | -0.018 |
arist | -0.018 |
mere | -0.017 |
Roses | -0.017 |
angers | -0.017 |
Token | audience |
Token ID | 5386 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
Pag | +0.002 |
olate | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
olate | +0.036 |
Pag | +0.036 |
Pir | +0.035 |
916 | +0.035 |
Glac | +0.035 |
Neg logit contributions | |
dstg | -0.038 |
arist | -0.038 |
mere | -0.036 |
Roses | -0.036 |
angers | -0.035 |
Token | like |
Token ID | 588 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
Pag | +0.004 |
olate | +0.004 |
Pir | +0.004 |
916 | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | show |
Token ID | 905 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
olate | +0.028 |
Pag | +0.028 |
916 | +0.027 |
Pir | +0.027 |
Glac | +0.027 |
Neg logit contributions | |
dstg | -0.029 |
arist | -0.028 |
mere | -0.028 |
Roses | -0.027 |
angers | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
dstg | +0.027 |
arist | +0.027 |
mere | +0.026 |
Roses | +0.026 |
angers | +0.026 |
Neg logit contributions | |
olate | -0.027 |
Pag | -0.026 |
Pir | -0.026 |
916 | -0.026 |
Glac | -0.026 |
Token | Alfred |
Token ID | 22044 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.007 |
916 | -0.007 |
Glac | -0.007 |
Token | H |
Token ID | 39 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.046 |
Pir | +0.045 |
916 | +0.045 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.061 |
arist | -0.061 |
mere | -0.059 |
Roses | -0.058 |
angers | -0.058 |
Token | itch |
Token ID | 2007 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
dstg | +0.020 |
arist | +0.019 |
mere | +0.019 |
Roses | +0.018 |
angers | +0.018 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.025 |
Pir | -0.025 |
916 | -0.025 |
Glac | -0.025 |
Token | cock |
Token ID | 21517 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
dstg | +0.010 |
arist | +0.009 |
mere | +0.007 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.109 |
Pag | -0.109 |
Pir | -0.107 |
916 | -0.107 |
Glac | -0.107 |
Token | Presents |
Token ID | 47102 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
dstg | +0.292 |
arist | +0.291 |
mere | +0.283 |
Roses | +0.277 |
angers | +0.275 |
Neg logit contributions | |
olate | -0.285 |
Pag | -0.283 |
916 | -0.277 |
Pir | -0.277 |
Glac | -0.275 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
dstg | +0.169 |
arist | +0.168 |
mere | +0.164 |
Roses | +0.160 |
angers | +0.159 |
Neg logit contributions | |
olate | -0.164 |
Pag | -0.163 |
916 | -0.160 |
Pir | -0.159 |
Glac | -0.158 |
Token | Even |
Token ID | 3412 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
dstg | +0.033 |
arist | +0.032 |
mere | +0.031 |
Roses | +0.031 |
angers | +0.030 |
Neg logit contributions | |
olate | -0.033 |
Pag | -0.033 |
Pir | -0.032 |
916 | -0.032 |
Glac | -0.032 |
Token | sets |
Token ID | 5621 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | ' |
Token ID | 6 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
arist | +0.150 |
dstg | +0.150 |
mere | +0.146 |
Roses | +0.143 |
angers | +0.142 |
Neg logit contributions | |
olate | -0.141 |
Pag | -0.141 |
916 | -0.138 |
Pir | -0.137 |
Glac | -0.137 |
Token | concept |
Token ID | 3721 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
olate | +0.022 |
Pag | +0.021 |
916 | +0.021 |
Pir | +0.021 |
Glac | +0.021 |
Neg logit contributions | |
dstg | -0.021 |
arist | -0.021 |
mere | -0.021 |
Roses | -0.020 |
angers | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-04 |
Pos logit contributions | |
dstg | +0.048 |
arist | +0.047 |
mere | +0.046 |
Roses | +0.045 |
angers | +0.045 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
916 | -0.045 |
Pir | -0.045 |
Glac | -0.044 |
Token | H |
Token ID | 39 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | itch |
Token ID | 2007 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
dstg | +0.017 |
arist | +0.017 |
mere | +0.017 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.026 |
Pag | -0.025 |
916 | -0.025 |
Pir | -0.025 |
Glac | -0.025 |
Token | cock |
Token ID | 21517 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
dstg | +0.009 |
arist | +0.008 |
mere | +0.007 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.094 |
Pag | -0.094 |
Pir | -0.093 |
916 | -0.092 |
Glac | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
dstg | +0.285 |
arist | +0.283 |
mere | +0.276 |
Roses | +0.269 |
angers | +0.268 |
Neg logit contributions | |
olate | -0.290 |
Pag | -0.288 |
916 | -0.282 |
Pir | -0.281 |
Glac | -0.279 |
Token | also |
Token ID | 635 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
916 | +0.025 |
Pir | +0.025 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.026 |
arist | -0.026 |
mere | -0.025 |
Roses | -0.025 |
angers | -0.025 |
Token | on |
Token ID | 319 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
dstg | +0.012 |
arist | +0.012 |
mere | +0.012 |
Roses | +0.012 |
angers | +0.011 |
Neg logit contributions | |
olate | -0.012 |
Pag | -0.012 |
916 | -0.012 |
Pir | -0.012 |
Glac | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-04 |
Pos logit contributions | |
olate | +0.008 |
Pag | +0.008 |
Pir | +0.008 |
916 | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.008 |
Roses | -0.007 |
angers | -0.007 |
Token | set |
Token ID | 900 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | & |
Token ID | 1222 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
olate | +0.041 |
Pag | +0.041 |
916 | +0.040 |
Glac | +0.040 |
Pir | +0.040 |
Neg logit contributions | |
dstg | -0.051 |
arist | -0.051 |
mere | -0.050 |
Roses | -0.049 |
angers | -0.049 |
Token | Gamble |
Token ID | 49318 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Pag | +0.033 |
olate | +0.033 |
Pir | +0.031 |
916 | +0.031 |
Glac | +0.031 |
Neg logit contributions | |
dstg | -0.075 |
arist | -0.074 |
mere | -0.073 |
angers | -0.071 |
Roses | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
olate | +0.128 |
Pag | +0.127 |
916 | +0.124 |
Pir | +0.124 |
Glac | +0.123 |
Neg logit contributions | |
dstg | -0.129 |
arist | -0.128 |
mere | -0.124 |
Roses | -0.122 |
angers | -0.121 |
Token | Coca |
Token ID | 29803 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.006 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
Pag | -0.006 |
olate | -0.006 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
olate | +0.015 |
Pag | +0.015 |
Pir | +0.015 |
916 | +0.015 |
Glac | +0.015 |
Neg logit contributions | |
dstg | -0.013 |
arist | -0.013 |
mere | -0.013 |
angers | -0.013 |
Roses | -0.013 |
Token | Cola |
Token ID | 28635 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
dstg | +0.278 |
arist | +0.277 |
mere | +0.271 |
Roses | +0.266 |
angers | +0.262 |
Neg logit contributions | |
olate | -0.288 |
Pag | -0.285 |
916 | -0.281 |
Pir | -0.279 |
Glac | -0.278 |
Token | Adidas |
Token ID | 48976 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
Pag | -0.002 |
olate | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
dstg | +0.069 |
arist | +0.069 |
mere | +0.067 |
Roses | +0.066 |
angers | +0.065 |
Neg logit contributions | |
olate | -0.071 |
Pag | -0.070 |
916 | -0.069 |
Pir | -0.069 |
Glac | -0.068 |
Token | McDonald |
Token ID | 14115 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
dstg | +0.065 |
arist | +0.064 |
mere | +0.063 |
Roses | +0.061 |
angers | +0.061 |
Neg logit contributions | |
olate | -0.062 |
Pag | -0.062 |
916 | -0.060 |
Pir | -0.060 |
Glac | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -2.79e-04 |
Pos logit contributions | |
dstg | +0.027 |
arist | +0.026 |
mere | +0.026 |
Roses | +0.025 |
angers | +0.025 |
Neg logit contributions | |
olate | -0.027 |
Pag | -0.026 |
916 | -0.026 |
Pir | -0.026 |
Glac | -0.026 |
Token | Michelle |
Token ID | 16738 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
Pir | -0.000 |
916 | -0.000 |
Glac | -0.000 |
Token | went |
Token ID | 1816 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
dstg | +0.047 |
arist | +0.047 |
mere | +0.045 |
Roses | +0.044 |
angers | +0.044 |
Neg logit contributions | |
olate | -0.073 |
Pag | -0.072 |
916 | -0.071 |
Pir | -0.071 |
Glac | -0.070 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
olate | +0.009 |
Pag | +0.009 |
Pir | +0.009 |
916 | +0.009 |
Glac | +0.009 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.009 |
Roses | -0.009 |
angers | -0.009 |
Token | Me |
Token ID | 2185 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
Pir | +0.007 |
916 | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.006 |
angers | -0.006 |
Token | gyn |
Token ID | 40183 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
dstg | +0.083 |
arist | +0.083 |
mere | +0.082 |
Roses | +0.080 |
angers | +0.080 |
Neg logit contributions | |
olate | -0.022 |
Pag | -0.022 |
916 | -0.021 |
Pir | -0.020 |
Glac | -0.020 |
Token | Kelly |
Token ID | 9077 |
Feature activation | -9.35e-04 |
Pos logit contributions | |
Pag | +0.192 |
olate | +0.192 |
Pir | +0.187 |
916 | +0.187 |
Glac | +0.185 |
Neg logit contributions | |
dstg | -0.198 |
arist | -0.198 |
mere | -0.192 |
Roses | -0.188 |
angers | -0.187 |
Token | � |
Token ID | 447 |
Feature activation | +4.64e-04 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | � |
Token ID | 247 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | s |
Token ID | 82 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | Fox |
Token ID | 5426 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | use |
Token ID | 779 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
olate | +0.008 |
Pag | +0.008 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | https |
Token ID | 3740 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | :// |
Token ID | 1378 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
Pir | +0.006 |
916 | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | api |
Token ID | 40391 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
olate | +0.054 |
Pag | +0.053 |
916 | +0.052 |
Pir | +0.052 |
Glac | +0.052 |
Neg logit contributions | |
dstg | -0.036 |
arist | -0.036 |
mere | -0.035 |
Roses | -0.034 |
angers | -0.033 |
Token | . |
Token ID | 764 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
olate | +0.034 |
Pag | +0.034 |
916 | +0.033 |
Pir | +0.033 |
Glac | +0.033 |
Neg logit contributions | |
dstg | -0.034 |
arist | -0.034 |
mere | -0.033 |
Roses | -0.032 |
angers | -0.032 |
Token | nice |
Token ID | 44460 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
olate | +0.088 |
Pag | +0.087 |
Pir | +0.085 |
916 | +0.085 |
Glac | +0.084 |
Neg logit contributions | |
dstg | -0.090 |
arist | -0.089 |
mere | -0.087 |
Roses | -0.085 |
angers | -0.084 |
Token | hash |
Token ID | 17831 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
olate | +0.212 |
Pag | +0.210 |
916 | +0.208 |
Pir | +0.205 |
Glac | +0.203 |
Neg logit contributions | |
dstg | -0.158 |
arist | -0.155 |
mere | -0.150 |
Roses | -0.148 |
angers | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
dstg | +0.042 |
arist | +0.042 |
mere | +0.041 |
Roses | +0.040 |
angers | +0.040 |
Neg logit contributions | |
olate | -0.043 |
Pag | -0.043 |
916 | -0.042 |
Pir | -0.042 |
Glac | -0.042 |
Token | com |
Token ID | 785 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | / |
Token ID | 14 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
dstg | +0.135 |
arist | +0.133 |
mere | +0.129 |
Roses | +0.126 |
angers | +0.126 |
Neg logit contributions | |
olate | -0.157 |
Pag | -0.156 |
Pir | -0.153 |
916 | -0.153 |
Glac | -0.151 |
Token | api |
Token ID | 15042 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
916 | -0.002 |
Pir | -0.002 |
Glac | -0.002 |
Token | sexy |
Token ID | 17144 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
olate | +0.017 |
Pag | +0.017 |
Pir | +0.017 |
916 | +0.017 |
Glac | +0.017 |
Neg logit contributions | |
dstg | -0.017 |
arist | -0.017 |
mere | -0.016 |
Roses | -0.016 |
angers | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +4.40e-03 |
Pos logit contributions | |
dstg | +0.084 |
arist | +0.083 |
mere | +0.081 |
Roses | +0.079 |
angers | +0.079 |
Neg logit contributions | |
olate | -0.076 |
Pag | -0.076 |
916 | -0.074 |
Pir | -0.074 |
Glac | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +5.52e-03 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | Up |
Token ID | 4933 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.003 |
angers | -0.003 |
Token | dates |
Token ID | 19581 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.010 |
arist | -0.010 |
mere | -0.010 |
Roses | -0.009 |
angers | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
olate | +0.243 |
Pag | +0.242 |
916 | +0.236 |
Pir | +0.236 |
Glac | +0.234 |
Neg logit contributions | |
dstg | -0.252 |
arist | -0.251 |
mere | -0.244 |
Roses | -0.239 |
angers | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | -3.11e-05 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | g |
Token ID | 70 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | ave |
Token ID | 1015 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
dstg | +0.045 |
arist | +0.045 |
mere | +0.044 |
Roses | +0.043 |
angers | +0.043 |
Neg logit contributions | |
olate | -0.047 |
Pag | -0.047 |
916 | -0.046 |
Pir | -0.045 |
Glac | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
olate | +0.030 |
Pag | +0.030 |
Pir | +0.029 |
916 | +0.029 |
Glac | +0.029 |
Neg logit contributions | |
dstg | -0.030 |
arist | -0.030 |
mere | -0.029 |
Roses | -0.029 |
angers | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -7.79e-03 |
Pos logit contributions | |
Pag | +0.001 |
olate | +0.001 |
Pir | +0.001 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
916 | -0.005 |
Pir | -0.005 |
Glac | -0.005 |
Token | Bad |
Token ID | 22069 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | ri |
Token ID | 380 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
dstg | +0.052 |
arist | +0.051 |
mere | +0.050 |
Roses | +0.049 |
angers | +0.048 |
Neg logit contributions | |
olate | -0.059 |
Pag | -0.059 |
Pir | -0.058 |
916 | -0.058 |
Glac | -0.057 |
Token | Jag |
Token ID | 35687 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
dstg | +0.098 |
arist | +0.097 |
mere | +0.094 |
Roses | +0.092 |
angers | +0.092 |
Neg logit contributions | |
olate | -0.111 |
Pag | -0.111 |
Pir | -0.108 |
916 | -0.108 |
Glac | -0.107 |
Token | ann |
Token ID | 1236 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | atha |
Token ID | 30921 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
olate | +0.237 |
Pag | +0.236 |
Pir | +0.231 |
916 | +0.230 |
Glac | +0.228 |
Neg logit contributions | |
dstg | -0.243 |
arist | -0.240 |
mere | -0.235 |
Roses | -0.230 |
angers | -0.228 |
Token | B |
Token ID | 347 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
dstg | +0.016 |
arist | +0.016 |
mere | +0.016 |
Roses | +0.015 |
angers | +0.015 |
Neg logit contributions | |
olate | -0.016 |
Pag | -0.016 |
916 | -0.016 |
Pir | -0.016 |
Glac | -0.015 |
Token | hatt |
Token ID | 11653 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
olate | +0.090 |
Pag | +0.090 |
916 | +0.088 |
Pir | +0.088 |
Glac | +0.087 |
Neg logit contributions | |
dstg | -0.080 |
arist | -0.080 |
mere | -0.077 |
Roses | -0.075 |
angers | -0.075 |
Token | ar |
Token ID | 283 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
dstg | +0.078 |
arist | +0.077 |
mere | +0.076 |
Roses | +0.074 |
angers | +0.074 |
Neg logit contributions | |
olate | -0.074 |
Pag | -0.074 |
Pir | -0.072 |
916 | -0.072 |
Glac | -0.071 |
Token | 9 |
Token ID | 860 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
dstg | +0.121 |
arist | +0.121 |
mere | +0.118 |
Roses | +0.115 |
angers | +0.115 |
Neg logit contributions | |
olate | -0.114 |
Pag | -0.113 |
916 | -0.111 |
Pir | -0.110 |
Glac | -0.110 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
dstg | +0.117 |
arist | +0.116 |
mere | +0.113 |
Roses | +0.110 |
angers | +0.110 |
Neg logit contributions | |
olate | -0.148 |
Pag | -0.147 |
Pir | -0.143 |
916 | -0.143 |
Glac | -0.143 |
Token | { |
Token ID | 1391 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
dstg | +0.016 |
arist | +0.016 |
mere | +0.016 |
Roses | +0.015 |
angers | +0.015 |
Neg logit contributions | |
olate | -0.012 |
Pag | -0.011 |
916 | -0.011 |
Pir | -0.011 |
Glac | -0.011 |
Token | ( |
Token ID | 7 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
olate | +0.042 |
Pag | +0.042 |
916 | +0.041 |
Pir | +0.041 |
Glac | +0.041 |
Neg logit contributions | |
dstg | -0.063 |
arist | -0.062 |
mere | -0.061 |
Roses | -0.060 |
angers | -0.060 |
Token | 106 |
Token ID | 15801 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
olate | +0.055 |
Pag | +0.055 |
916 | +0.054 |
Pir | +0.054 |
Glac | +0.053 |
Neg logit contributions | |
dstg | -0.058 |
arist | -0.058 |
mere | -0.056 |
Roses | -0.055 |
angers | -0.055 |
Token | s |
Token ID | 82 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
olate | +0.017 |
Pag | +0.017 |
916 | +0.016 |
Pir | +0.016 |
Glac | +0.016 |
Neg logit contributions | |
dstg | -0.016 |
arist | -0.016 |
mere | -0.016 |
Roses | -0.015 |
angers | -0.015 |
Token | )} |
Token ID | 38165 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | 19 |
Token ID | 678 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
olate | +0.207 |
Pag | +0.206 |
Pir | +0.201 |
916 | +0.201 |
Glac | +0.200 |
Neg logit contributions | |
dstg | -0.221 |
arist | -0.220 |
mere | -0.215 |
Roses | -0.210 |
angers | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | Q |
Token ID | 1195 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | e |
Token ID | 68 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
olate | +0.032 |
Pag | +0.032 |
Pir | +0.031 |
916 | +0.031 |
Glac | +0.031 |
Neg logit contributions | |
dstg | -0.027 |
arist | -0.026 |
mere | -0.026 |
Roses | -0.025 |
angers | -0.025 |
Token | 1 |
Token ID | 16 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
Pir | +0.006 |
916 | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.005 |
Roses | -0.005 |
angers | -0.005 |
Token | Sharif |
Token ID | 44144 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
dstg | +0.010 |
arist | +0.010 |
mere | +0.010 |
Roses | +0.009 |
angers | +0.009 |
Neg logit contributions | |
Pag | -0.016 |
olate | -0.016 |
Pir | -0.015 |
916 | -0.015 |
Glac | -0.015 |
Token | condemned |
Token ID | 15006 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
dstg | +0.099 |
arist | +0.098 |
mere | +0.095 |
Roses | +0.093 |
angers | +0.093 |
Neg logit contributions | |
olate | -0.092 |
Pag | -0.092 |
Pir | -0.090 |
916 | -0.090 |
Glac | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | reported |
Token ID | 2098 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Pag | +0.009 |
olate | +0.009 |
Pir | +0.008 |
916 | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.009 |
arist | -0.009 |
mere | -0.008 |
Roses | -0.008 |
angers | -0.008 |
Token | deaths |
Token ID | 7040 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
olate | +0.069 |
Pag | +0.069 |
Pir | +0.068 |
916 | +0.067 |
Glac | +0.067 |
Neg logit contributions | |
dstg | -0.064 |
arist | -0.063 |
mere | -0.061 |
Roses | -0.060 |
angers | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
olate | +0.022 |
Pag | +0.022 |
Pir | +0.021 |
916 | +0.021 |
Glac | +0.021 |
Neg logit contributions | |
dstg | -0.022 |
arist | -0.022 |
mere | -0.021 |
Roses | -0.021 |
angers | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
Pir | +0.007 |
916 | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.008 |
arist | -0.008 |
mere | -0.008 |
Roses | -0.008 |
angers | -0.008 |
Token | these |
Token ID | 777 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
dstg | +0.011 |
arist | +0.011 |
mere | +0.010 |
Roses | +0.010 |
angers | +0.010 |
Neg logit contributions | |
olate | -0.011 |
Pag | -0.011 |
Pir | -0.010 |
916 | -0.010 |
Glac | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
dstg | +0.040 |
arist | +0.040 |
mere | +0.039 |
Roses | +0.038 |
angers | +0.038 |
Neg logit contributions | |
Pag | -0.041 |
olate | -0.041 |
Pir | -0.040 |
916 | -0.040 |
Glac | -0.040 |
Token | have |
Token ID | 423 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
dstg | +0.028 |
arist | +0.028 |
mere | +0.028 |
Roses | +0.027 |
angers | +0.027 |
Neg logit contributions | |
olate | -0.030 |
Pag | -0.030 |
916 | -0.029 |
Pir | -0.029 |
Glac | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
olate | +0.017 |
Pag | +0.017 |
916 | +0.017 |
Pir | +0.017 |
Glac | +0.016 |
Neg logit contributions | |
dstg | -0.015 |
arist | -0.015 |
mere | -0.015 |
Roses | -0.015 |
angers | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
olate | +0.040 |
Pag | +0.040 |
916 | +0.039 |
Pir | +0.039 |
Glac | +0.039 |
Neg logit contributions | |
dstg | -0.038 |
arist | -0.038 |
mere | -0.037 |
Roses | -0.036 |
angers | -0.035 |
Token | And |
Token ID | 843 |
Feature activation | +3.15e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
dstg | +0.016 |
arist | +0.016 |
mere | +0.016 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.017 |
Pag | -0.016 |
916 | -0.016 |
Pir | -0.016 |
Glac | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -2.64e-04 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.007 |
916 | -0.007 |
Glac | -0.007 |
Token | at |
Token ID | 379 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | El |
Token ID | 2574 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
olate | +0.037 |
Pag | +0.037 |
Pir | +0.036 |
916 | +0.036 |
Glac | +0.036 |
Neg logit contributions | |
dstg | -0.037 |
arist | -0.037 |
mere | -0.036 |
Roses | -0.035 |
angers | -0.035 |
Token | Rio |
Token ID | 15338 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
Pag | +0.059 |
olate | +0.059 |
Pir | +0.057 |
916 | +0.057 |
Glac | +0.057 |
Neg logit contributions | |
dstg | -0.061 |
arist | -0.060 |
mere | -0.058 |
Roses | -0.057 |
angers | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
olate | +0.023 |
Pag | +0.023 |
916 | +0.023 |
Pir | +0.023 |
Glac | +0.022 |
Neg logit contributions | |
dstg | -0.024 |
arist | -0.024 |
mere | -0.023 |
Roses | -0.023 |
angers | -0.023 |
Token | Election |
Token ID | 14219 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
Pir | +0.005 |
916 | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | Night |
Token ID | 5265 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
olate | +0.028 |
Pag | +0.028 |
Pir | +0.027 |
916 | +0.027 |
Glac | +0.027 |
Neg logit contributions | |
dstg | -0.020 |
arist | -0.020 |
mere | -0.020 |
Roses | -0.019 |
angers | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | believes |
Token ID | 5804 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | telling |
Token ID | 5149 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
olate | +0.065 |
Pag | +0.065 |
916 | +0.063 |
Pir | +0.063 |
Glac | +0.063 |
Neg logit contributions | |
dstg | -0.063 |
arist | -0.063 |
mere | -0.061 |
Roses | -0.060 |
angers | -0.059 |
Token | his |
Token ID | 465 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
dstg | +0.077 |
arist | +0.077 |
mere | +0.075 |
Roses | +0.073 |
angers | +0.073 |
Neg logit contributions | |
olate | -0.078 |
Pag | -0.078 |
916 | -0.076 |
Pir | -0.076 |
Glac | -0.075 |
Token | story |
Token ID | 1621 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
dstg | +0.010 |
arist | +0.010 |
mere | +0.010 |
Roses | +0.009 |
angers | +0.009 |
Neg logit contributions | |
olate | -0.009 |
Pag | -0.009 |
916 | -0.008 |
Pir | -0.008 |
Glac | -0.008 |
Token | will |
Token ID | 481 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
olate | +0.047 |
Pag | +0.047 |
Pir | +0.046 |
916 | +0.046 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.051 |
arist | -0.051 |
mere | -0.049 |
Roses | -0.048 |
angers | -0.048 |
Token | aid |
Token ID | 6133 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
olate | +0.010 |
Pag | +0.010 |
916 | +0.010 |
Pir | +0.010 |
Glac | +0.010 |
Neg logit contributions | |
dstg | -0.011 |
arist | -0.011 |
mere | -0.011 |
Roses | -0.011 |
angers | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
dstg | +0.014 |
arist | +0.013 |
mere | +0.013 |
Roses | +0.013 |
angers | +0.013 |
Neg logit contributions | |
olate | -0.011 |
Pag | -0.011 |
Pir | -0.011 |
916 | -0.011 |
Glac | -0.011 |
Token | recovery |
Token ID | 7628 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
916 | -0.005 |
Pir | -0.005 |
Glac | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | being |
Token ID | 852 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
Pag | +0.014 |
olate | +0.014 |
Pir | +0.014 |
916 | +0.014 |
Glac | +0.013 |
Neg logit contributions | |
dstg | -0.014 |
arist | -0.014 |
mere | -0.014 |
Roses | -0.013 |
angers | -0.013 |
Token | close |
Token ID | 1969 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
olate | +0.053 |
Pag | +0.053 |
916 | +0.051 |
Pir | +0.051 |
Glac | +0.051 |
Neg logit contributions | |
dstg | -0.052 |
arist | -0.051 |
mere | -0.050 |
Roses | -0.049 |
angers | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
dstg | +0.017 |
arist | +0.017 |
mere | +0.017 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.018 |
Pag | -0.018 |
916 | -0.017 |
Pir | -0.017 |
Glac | -0.017 |
Token | death |
Token ID | 1918 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
Pir | +0.005 |
916 | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.005 |
Roses | -0.004 |
angers | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e-04 |
Pos logit contributions | |
Pag | +0.062 |
olate | +0.061 |
Pir | +0.060 |
916 | +0.060 |
Glac | +0.059 |
Neg logit contributions | |
dstg | -0.065 |
arist | -0.065 |
mere | -0.062 |
Roses | -0.062 |
angers | -0.061 |
Token | concerned |
Token ID | 5213 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
olate | +0.045 |
Pag | +0.045 |
916 | +0.044 |
Pir | +0.044 |
Glac | +0.044 |
Neg logit contributions | |
dstg | -0.044 |
arist | -0.044 |
mere | -0.043 |
Roses | -0.042 |
angers | -0.042 |
Token | his |
Token ID | 465 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.004 |
Pir | +0.004 |
916 | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.003 |
angers | -0.003 |
Token | afterlife |
Token ID | 45076 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
dstg | +0.098 |
arist | +0.097 |
mere | +0.094 |
Roses | +0.093 |
angers | +0.092 |
Neg logit contributions | |
olate | -0.093 |
Pag | -0.093 |
Pir | -0.091 |
916 | -0.091 |
Glac | -0.090 |
Token | he |
Token ID | 339 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Pag | +0.002 |
olate | +0.002 |
Pir | +0.002 |
916 | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
olate | +0.154 |
Pag | +0.153 |
916 | +0.150 |
Pir | +0.150 |
Glac | +0.148 |
Neg logit contributions | |
dstg | -0.158 |
arist | -0.157 |
mere | -0.153 |
Roses | -0.149 |
angers | -0.149 |
Token | somewhat |
Token ID | 6454 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
dstg | +0.019 |
arist | +0.019 |
mere | +0.018 |
Roses | +0.018 |
angers | +0.018 |
Neg logit contributions | |
olate | -0.019 |
Pag | -0.019 |
Pir | -0.018 |
916 | -0.018 |
Glac | -0.018 |
Token | bigger |
Token ID | 5749 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
olate | +0.056 |
Pag | +0.056 |
Pir | +0.055 |
916 | +0.054 |
Glac | +0.054 |
Neg logit contributions | |
dstg | -0.055 |
arist | -0.055 |
mere | -0.053 |
Roses | -0.052 |
angers | -0.052 |
Token | than |
Token ID | 621 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
dstg | +0.080 |
arist | +0.080 |
mere | +0.078 |
Roses | +0.076 |
angers | +0.075 |
Neg logit contributions | |
olate | -0.080 |
Pag | -0.079 |
Pir | -0.077 |
916 | -0.077 |
Glac | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
olate | +0.016 |
Pag | +0.016 |
Pir | +0.016 |
916 | +0.016 |
Glac | +0.016 |
Neg logit contributions | |
dstg | -0.016 |
arist | -0.016 |
mere | -0.015 |
Roses | -0.015 |
angers | -0.015 |
Token | PAT |
Token ID | 28748 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-04 |
Pos logit contributions | |
olate | +0.068 |
Pag | +0.067 |
916 | +0.066 |
Pir | +0.066 |
Glac | +0.065 |
Neg logit contributions | |
dstg | -0.070 |
arist | -0.069 |
mere | -0.067 |
Roses | -0.066 |
angers | -0.066 |
Token | we |
Token ID | 356 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
Pir | +0.000 |
916 | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | now |
Token ID | 783 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
dstg | +0.009 |
arist | +0.009 |
mere | +0.009 |
Roses | +0.009 |
angers | +0.009 |
Neg logit contributions | |
olate | -0.009 |
Pag | -0.009 |
Pir | -0.009 |
916 | -0.009 |
Glac | -0.009 |
Token | send |
Token ID | 3758 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
dstg | +0.030 |
arist | +0.030 |
mere | +0.029 |
Roses | +0.029 |
angers | +0.028 |
Neg logit contributions | |
olate | -0.027 |
Pag | -0.027 |
916 | -0.027 |
Pir | -0.027 |
Glac | -0.026 |
Token | through |
Token ID | 832 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
dstg | +0.018 |
arist | +0.018 |
mere | +0.018 |
Roses | +0.017 |
angers | +0.017 |
Neg logit contributions | |
olate | -0.019 |
Pag | -0.019 |
Pir | -0.019 |
916 | -0.019 |
Glac | -0.019 |
Token | 2005 |
Token ID | 5075 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
Pag | +0.020 |
olate | +0.020 |
Pir | +0.020 |
916 | +0.020 |
Glac | +0.020 |
Neg logit contributions | |
dstg | -0.015 |
arist | -0.015 |
mere | -0.015 |
angers | -0.014 |
Roses | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
dstg | +0.046 |
arist | +0.046 |
mere | +0.045 |
Roses | +0.044 |
angers | +0.043 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
916 | -0.045 |
Pir | -0.045 |
Glac | -0.045 |
Token | Gallup |
Token ID | 29183 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | found |
Token ID | 1043 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
916 | +0.014 |
Pir | +0.014 |
Glac | +0.014 |
Neg logit contributions | |
dstg | -0.016 |
arist | -0.016 |
mere | -0.015 |
Roses | -0.015 |
angers | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
olate | +0.028 |
Pag | +0.028 |
916 | +0.028 |
Pir | +0.028 |
Glac | +0.027 |
Neg logit contributions | |
dstg | -0.029 |
arist | -0.029 |
mere | -0.028 |
Roses | -0.027 |
angers | -0.027 |
Token | 25 |
Token ID | 1679 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | percent |
Token ID | 1411 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.006 |
Pag | -0.006 |
916 | -0.006 |
Pir | -0.006 |
Glac | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
dstg | +0.052 |
arist | +0.051 |
mere | +0.050 |
Roses | +0.049 |
angers | +0.049 |
Neg logit contributions | |
olate | -0.052 |
Pag | -0.052 |
916 | -0.051 |
Pir | -0.050 |
Glac | -0.050 |
Token | Americans |
Token ID | 3399 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
olate | +0.023 |
Pag | +0.023 |
916 | +0.023 |
Pir | +0.023 |
Glac | +0.023 |
Neg logit contributions | |
dstg | -0.022 |
arist | -0.022 |
mere | -0.021 |
Roses | -0.021 |
angers | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
dstg | +0.013 |
arist | +0.013 |
mere | +0.012 |
Roses | +0.012 |
angers | +0.012 |
Neg logit contributions | |
Pag | -0.014 |
olate | -0.014 |
Pir | -0.013 |
916 | -0.013 |
Glac | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | +4.37e-04 |
Pos logit contributions | |
dstg | +0.084 |
arist | +0.083 |
mere | +0.081 |
Roses | +0.079 |
angers | +0.079 |
Neg logit contributions | |
olate | -0.081 |
Pag | -0.081 |
916 | -0.079 |
Pir | -0.079 |
Glac | -0.078 |
Token | � |
Token ID | 247 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
angers | -0.000 |
Roses | -0.000 |
Token | t |
Token ID | 83 |
Feature activation | -6.53e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | been |
Token ID | 587 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
916 | -0.005 |
Pir | -0.005 |
Glac | -0.005 |
Token | done |
Token ID | 1760 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
dstg | +0.053 |
arist | +0.053 |
mere | +0.051 |
Roses | +0.050 |
angers | +0.050 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
916 | -0.045 |
Pir | -0.045 |
Glac | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
olate | +0.062 |
Pag | +0.062 |
916 | +0.060 |
Pir | +0.060 |
Glac | +0.060 |
Neg logit contributions | |
dstg | -0.050 |
arist | -0.050 |
mere | -0.049 |
Roses | -0.047 |
angers | -0.047 |
Token | 108 |
Token ID | 15495 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +4.66e-04 |
Pos logit contributions | |
olate | +0.040 |
Pag | +0.040 |
Pir | +0.039 |
916 | +0.039 |
Glac | +0.039 |
Neg logit contributions | |
dstg | -0.041 |
arist | -0.041 |
mere | -0.040 |
Roses | -0.039 |
angers | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | � |
Token ID | 447 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | � |
Token ID | 251 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
angers | +0.001 |
Roses | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | traditional |
Token ID | 4569 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Pag | +0.015 |
olate | +0.015 |
Pir | +0.015 |
916 | +0.015 |
Glac | +0.014 |
Neg logit contributions | |
dstg | -0.016 |
arist | -0.016 |
mere | -0.016 |
Roses | -0.016 |
angers | -0.016 |
Token | banking |
Token ID | 11754 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
dstg | +0.019 |
arist | +0.019 |
mere | +0.018 |
Roses | +0.018 |
angers | +0.018 |
Neg logit contributions | |
olate | -0.017 |
Pag | -0.017 |
916 | -0.017 |
Pir | -0.017 |
Glac | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | -5.85e-03 |
Pos logit contributions | |
olate | +0.041 |
Pag | +0.041 |
916 | +0.040 |
Pir | +0.040 |
Glac | +0.040 |
Neg logit contributions | |
dstg | -0.042 |
arist | -0.041 |
mere | -0.040 |
Roses | -0.039 |
angers | -0.039 |
Token | � |
Token ID | 251 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
dstg | +0.004 |
arist | +0.004 |
mere | +0.004 |
Roses | +0.004 |
angers | +0.004 |
Neg logit contributions | |
olate | -0.004 |
Pag | -0.004 |
916 | -0.004 |
Pir | -0.004 |
Glac | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
olate | +0.010 |
Pag | +0.010 |
Pir | +0.010 |
916 | +0.010 |
Glac | +0.010 |
Neg logit contributions | |
dstg | -0.010 |
arist | -0.010 |
mere | -0.010 |
Roses | -0.009 |
angers | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-04 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | However |
Token ID | 4864 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
olate | +0.060 |
Pag | +0.060 |
916 | +0.059 |
Pir | +0.058 |
Glac | +0.058 |
Neg logit contributions | |
dstg | -0.060 |
arist | -0.060 |
mere | -0.059 |
Roses | -0.057 |
angers | -0.057 |
Token | Dr |
Token ID | 1583 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
Pir | -0.001 |
916 | -0.001 |
Glac | -0.001 |
Token | Naz |
Token ID | 12819 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.010 |
arist | -0.010 |
mere | -0.009 |
Roses | -0.009 |
angers | -0.009 |
Token | Democrat |
Token ID | 9755 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
olate | +0.090 |
Pag | +0.090 |
916 | +0.088 |
Pir | +0.088 |
Glac | +0.087 |
Neg logit contributions | |
dstg | -0.086 |
arist | -0.086 |
mere | -0.084 |
Roses | -0.082 |
angers | -0.081 |
Token | Coalition |
Token ID | 15135 |
Feature activation | -7.52e-03 |
Pos logit contributions | |
Pag | +0.080 |
olate | +0.079 |
Pir | +0.078 |
916 | +0.077 |
Glac | +0.077 |
Neg logit contributions | |
dstg | -0.092 |
arist | -0.092 |
mere | -0.089 |
Roses | -0.087 |
angers | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
dstg | +0.005 |
arist | +0.005 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | who |
Token ID | 508 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | aren |
Token ID | 3588 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.034 |
mere | +0.033 |
Roses | +0.032 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.033 |
Pag | -0.033 |
Pir | -0.032 |
916 | -0.032 |
Glac | -0.032 |
Token | � |
Token ID | 447 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
olate | +0.045 |
Pag | +0.045 |
916 | +0.044 |
Pir | +0.044 |
Glac | +0.044 |
Neg logit contributions | |
dstg | -0.046 |
arist | -0.046 |
mere | -0.045 |
Roses | -0.044 |
angers | -0.044 |
Token | � |
Token ID | 247 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
olate | +0.001 |
Pag | +0.001 |
916 | +0.001 |
Pir | +0.001 |
Glac | +0.001 |
Neg logit contributions | |
dstg | -0.001 |
arist | -0.001 |
mere | -0.001 |
Roses | -0.001 |
angers | -0.001 |
Token | t |
Token ID | 83 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.005 |
Pir | +0.005 |
Glac | +0.005 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | afraid |
Token ID | 7787 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.002 |
Pag | -0.002 |
Pir | -0.002 |
916 | -0.002 |
Glac | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.31e-04 |
Pos logit contributions | |
olate | +0.071 |
Pag | +0.071 |
916 | +0.069 |
Pir | +0.069 |
Glac | +0.068 |
Neg logit contributions | |
dstg | -0.068 |
arist | -0.068 |
mere | -0.066 |
Roses | -0.065 |
angers | -0.064 |
Token | express |
Token ID | 4911 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | also |
Token ID | 635 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
dstg | +0.017 |
arist | +0.017 |
mere | +0.017 |
Roses | +0.016 |
angers | +0.016 |
Neg logit contributions | |
olate | -0.017 |
Pag | -0.017 |
Pir | -0.017 |
916 | -0.017 |
Glac | -0.016 |
Token | alike |
Token ID | 12936 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.007 |
916 | -0.007 |
Glac | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
olate | +0.025 |
Pag | +0.025 |
Pir | +0.025 |
916 | +0.025 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.026 |
arist | -0.026 |
mere | -0.025 |
Roses | -0.025 |
angers | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.006 |
Roses | +0.006 |
angers | +0.006 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | fact |
Token ID | 1109 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
dstg | +0.002 |
arist | +0.002 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
dstg | +0.072 |
arist | +0.072 |
mere | +0.070 |
Roses | +0.068 |
angers | +0.068 |
Neg logit contributions | |
olate | -0.074 |
Pag | -0.074 |
916 | -0.072 |
Pir | -0.072 |
Glac | -0.071 |
Token | they |
Token ID | 484 |
Feature activation | +9.11e-03 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
Pag | -0.006 |
olate | -0.006 |
Pir | -0.006 |
916 | -0.006 |
Glac | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
olate | +0.006 |
Pag | +0.006 |
916 | +0.006 |
Pir | +0.006 |
Glac | +0.006 |
Neg logit contributions | |
dstg | -0.006 |
arist | -0.006 |
mere | -0.006 |
Roses | -0.006 |
angers | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
Pag | +0.007 |
olate | +0.007 |
Pir | +0.007 |
916 | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
olate | +0.026 |
Pag | +0.026 |
Pir | +0.025 |
916 | +0.025 |
Glac | +0.025 |
Neg logit contributions | |
dstg | -0.031 |
arist | -0.031 |
mere | -0.030 |
Roses | -0.030 |
angers | -0.030 |
Token | point |
Token ID | 966 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
dstg | +0.067 |
arist | +0.066 |
mere | +0.064 |
Roses | +0.063 |
angers | +0.063 |
Neg logit contributions | |
Pag | -0.056 |
olate | -0.056 |
Pir | -0.054 |
916 | -0.054 |
Glac | -0.054 |
Token | � |
Token ID | 247 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | s |
Token ID | 82 |
Feature activation | -5.32e-04 |
Pos logit contributions | |
olate | +0.007 |
Pag | +0.007 |
916 | +0.007 |
Pir | +0.007 |
Glac | +0.007 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | silhouette |
Token ID | 41834 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
dstg | +0.000 |
arist | +0.000 |
mere | +0.000 |
Roses | +0.000 |
angers | +0.000 |
Neg logit contributions | |
olate | -0.000 |
Pag | -0.000 |
916 | -0.000 |
Pir | -0.000 |
Glac | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
olate | +0.010 |
Pag | +0.010 |
916 | +0.010 |
Pir | +0.010 |
Glac | +0.009 |
Neg logit contributions | |
dstg | -0.011 |
arist | -0.011 |
mere | -0.011 |
Roses | -0.010 |
angers | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
olate | +0.011 |
Pag | +0.011 |
916 | +0.010 |
Pir | +0.010 |
Glac | +0.010 |
Neg logit contributions | |
dstg | -0.010 |
arist | -0.010 |
mere | -0.010 |
Roses | -0.010 |
angers | -0.010 |
Token | horizon |
Token ID | 17810 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | t |
Token ID | 256 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
dstg | +0.206 |
arist | +0.205 |
mere | +0.200 |
Roses | +0.196 |
angers | +0.195 |
Neg logit contributions | |
olate | -0.183 |
Pag | -0.182 |
916 | -0.177 |
Pir | -0.177 |
Glac | -0.176 |
Token | umbled |
Token ID | 11137 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
olate | +0.014 |
Pag | +0.014 |
916 | +0.013 |
Pir | +0.013 |
Glac | +0.013 |
Neg logit contributions | |
dstg | -0.021 |
arist | -0.021 |
mere | -0.020 |
Roses | -0.020 |
angers | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
olate | +0.091 |
Pag | +0.091 |
Pir | +0.088 |
916 | +0.088 |
Glac | +0.088 |
Neg logit contributions | |
dstg | -0.097 |
arist | -0.096 |
mere | -0.094 |
Roses | -0.091 |
angers | -0.091 |
Token | fell |
Token ID | 3214 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
dstg | +0.034 |
arist | +0.034 |
mere | +0.033 |
Roses | +0.032 |
angers | +0.032 |
Neg logit contributions | |
olate | -0.032 |
Pag | -0.032 |
Pir | -0.032 |
916 | -0.032 |
Glac | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
olate | +0.023 |
Pag | +0.023 |
Pir | +0.023 |
916 | +0.023 |
Glac | +0.022 |
Neg logit contributions | |
dstg | -0.024 |
arist | -0.023 |
mere | -0.023 |
Roses | -0.022 |
angers | -0.022 |
Token | 000 |
Token ID | 830 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.003 |
Roses | +0.003 |
angers | +0.003 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
916 | -0.003 |
Pir | -0.003 |
Glac | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
olate | +0.030 |
Pag | +0.030 |
Pir | +0.030 |
916 | +0.030 |
Glac | +0.029 |
Neg logit contributions | |
dstg | -0.031 |
arist | -0.031 |
mere | -0.030 |
Roses | -0.029 |
angers | -0.029 |
Token | T |
Token ID | 51 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
dstg | +0.042 |
arist | +0.041 |
mere | +0.040 |
Roses | +0.039 |
angers | +0.039 |
Neg logit contributions | |
olate | -0.042 |
Pag | -0.042 |
916 | -0.041 |
Pir | -0.041 |
Glac | -0.040 |
Token | oxic |
Token ID | 18047 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
dstg | +0.078 |
arist | +0.077 |
mere | +0.075 |
Roses | +0.073 |
angers | +0.073 |
Neg logit contributions | |
olate | -0.080 |
Pag | -0.079 |
916 | -0.078 |
Pir | -0.078 |
Glac | -0.077 |
Token | waste |
Token ID | 7030 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
dstg | +0.040 |
arist | +0.040 |
mere | +0.039 |
Roses | +0.038 |
angers | +0.038 |
Neg logit contributions | |
olate | -0.046 |
Pag | -0.046 |
Pir | -0.045 |
916 | -0.045 |
Glac | -0.045 |
Token | water |
Token ID | 1660 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
dstg | +0.167 |
arist | +0.167 |
mere | +0.161 |
Roses | +0.157 |
angers | +0.156 |
Neg logit contributions | |
olate | -0.180 |
Pag | -0.179 |
916 | -0.175 |
Pir | -0.175 |
Glac | -0.174 |
Token | equal |
Token ID | 4961 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
olate | +0.018 |
Pag | +0.018 |
Pir | +0.018 |
916 | +0.018 |
Glac | +0.018 |
Neg logit contributions | |
dstg | -0.018 |
arist | -0.018 |
mere | -0.017 |
Roses | -0.017 |
angers | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
dstg | +0.092 |
arist | +0.092 |
mere | +0.089 |
Roses | +0.087 |
angers | +0.086 |
Neg logit contributions | |
olate | -0.102 |
Pag | -0.102 |
Pir | -0.100 |
916 | -0.100 |
Glac | -0.099 |
Token | volume |
Token ID | 6115 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
dstg | +0.003 |
arist | +0.003 |
mere | +0.002 |
Roses | +0.002 |
angers | +0.002 |
Neg logit contributions | |
olate | -0.003 |
Pag | -0.003 |
Pir | -0.003 |
916 | -0.003 |
Glac | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +3.20e-03 |
Pos logit contributions | |
dstg | +0.066 |
arist | +0.066 |
mere | +0.064 |
Roses | +0.062 |
angers | +0.062 |
Neg logit contributions | |
olate | -0.066 |
Pag | -0.065 |
916 | -0.064 |
Pir | -0.064 |
Glac | -0.063 |
Token | as |
Token ID | 355 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
Pir | +0.002 |
916 | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.002 |
arist | -0.002 |
mere | -0.002 |
Roses | -0.002 |
angers | -0.002 |
Token | an |
Token ID | 281 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
olate | +0.003 |
Pag | +0.003 |
Pir | +0.003 |
916 | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | anti |
Token ID | 3098 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
olate | +0.046 |
Pag | +0.046 |
Pir | +0.045 |
916 | +0.044 |
Glac | +0.044 |
Neg logit contributions | |
dstg | -0.044 |
arist | -0.044 |
mere | -0.042 |
Roses | -0.041 |
angers | -0.041 |
Token | - |
Token ID | 12 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
olate | +0.044 |
Pag | +0.044 |
916 | +0.043 |
Pir | +0.043 |
Glac | +0.043 |
Neg logit contributions | |
dstg | -0.047 |
arist | -0.046 |
mere | -0.045 |
Roses | -0.044 |
angers | -0.044 |
Token | trans |
Token ID | 7645 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | measure |
Token ID | 3953 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
olate | +0.046 |
Pag | +0.046 |
916 | +0.045 |
Pir | +0.045 |
Glac | +0.045 |
Neg logit contributions | |
dstg | -0.049 |
arist | -0.049 |
mere | -0.048 |
Roses | -0.047 |
angers | -0.046 |
Token | intended |
Token ID | 5292 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
dstg | +0.195 |
arist | +0.194 |
mere | +0.189 |
Roses | +0.186 |
angers | +0.184 |
Neg logit contributions | |
olate | -0.190 |
Pag | -0.190 |
Pir | -0.186 |
916 | -0.184 |
Glac | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
dstg | +0.062 |
arist | +0.061 |
mere | +0.060 |
Roses | +0.058 |
angers | +0.058 |
Neg logit contributions | |
olate | -0.065 |
Pag | -0.064 |
916 | -0.063 |
Pir | -0.063 |
Glac | -0.063 |
Token | discriminate |
Token ID | 28433 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
dstg | +0.007 |
arist | +0.007 |
mere | +0.007 |
Roses | +0.007 |
angers | +0.007 |
Neg logit contributions | |
olate | -0.007 |
Pag | -0.007 |
916 | -0.007 |
Pir | -0.007 |
Glac | -0.007 |
Token | against |
Token ID | 1028 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Pag | +0.074 |
olate | +0.074 |
Pir | +0.072 |
916 | +0.072 |
Glac | +0.071 |
Neg logit contributions | |
dstg | -0.070 |
arist | -0.069 |
mere | -0.067 |
Roses | -0.066 |
angers | -0.065 |
Token | them |
Token ID | 606 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
dstg | +0.020 |
arist | +0.019 |
mere | +0.019 |
Roses | +0.018 |
angers | +0.018 |
Neg logit contributions | |
Pag | -0.019 |
olate | -0.019 |
Pir | -0.019 |
916 | -0.019 |
Glac | -0.018 |
Token | top |
Token ID | 1353 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
dstg | +0.052 |
arist | +0.052 |
mere | +0.051 |
Roses | +0.049 |
angers | +0.049 |
Neg logit contributions | |
olate | -0.045 |
Pag | -0.045 |
Pir | -0.044 |
916 | -0.044 |
Glac | -0.043 |
Token | manager |
Token ID | 4706 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
dstg | +0.063 |
arist | +0.062 |
mere | +0.061 |
Roses | +0.059 |
angers | +0.059 |
Neg logit contributions | |
olate | -0.062 |
Pag | -0.062 |
Pir | -0.060 |
916 | -0.060 |
Glac | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | +1.59e-04 |
Pos logit contributions | |
dstg | +0.099 |
arist | +0.098 |
mere | +0.095 |
Roses | +0.093 |
angers | +0.093 |
Neg logit contributions | |
olate | -0.095 |
Pag | -0.094 |
916 | -0.092 |
Pir | -0.092 |
Glac | -0.091 |
Token | Kol |
Token ID | 25910 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
olate | +0.000 |
Pag | +0.000 |
916 | +0.000 |
Pir | +0.000 |
Glac | +0.000 |
Neg logit contributions | |
dstg | -0.000 |
arist | -0.000 |
mere | -0.000 |
Roses | -0.000 |
angers | -0.000 |
Token | omo |
Token ID | 17902 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
olate | +0.076 |
Pag | +0.076 |
Pir | +0.074 |
916 | +0.074 |
Glac | +0.074 |
Neg logit contributions | |
dstg | -0.043 |
arist | -0.043 |
mere | -0.041 |
Roses | -0.040 |
angers | -0.039 |
Token | isky |
Token ID | 34041 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
dstg | +0.047 |
arist | +0.046 |
mere | +0.043 |
Roses | +0.042 |
angers | +0.040 |
Neg logit contributions | |
olate | -0.171 |
Pag | -0.171 |
916 | -0.169 |
Pir | -0.168 |
Glac | -0.167 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
dstg | +0.204 |
arist | +0.203 |
mere | +0.198 |
Roses | +0.193 |
angers | +0.192 |
Neg logit contributions | |
olate | -0.195 |
Pag | -0.194 |
916 | -0.189 |
Pir | -0.189 |
Glac | -0.188 |
Token | � |
Token ID | 247 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
olate | +0.009 |
Pag | +0.008 |
916 | +0.008 |
Pir | +0.008 |
Glac | +0.008 |
Neg logit contributions | |
dstg | -0.007 |
arist | -0.007 |
mere | -0.007 |
Roses | -0.007 |
angers | -0.007 |
Token | s |
Token ID | 82 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
olate | +0.005 |
Pag | +0.005 |
916 | +0.004 |
Pir | +0.004 |
Glac | +0.004 |
Neg logit contributions | |
dstg | -0.005 |
arist | -0.005 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | refinery |
Token ID | 44133 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
dstg | +0.006 |
arist | +0.006 |
mere | +0.005 |
Roses | +0.005 |
angers | +0.005 |
Neg logit contributions | |
olate | -0.005 |
Pag | -0.005 |
Pir | -0.005 |
916 | -0.005 |
Glac | -0.005 |
Token | business |
Token ID | 1597 |
Feature activation | +7.14e-03 |
Pos logit contributions | |
dstg | +0.136 |
arist | +0.135 |
mere | +0.132 |
Roses | +0.129 |
angers | +0.128 |
Neg logit contributions | |
olate | -0.133 |
Pag | -0.133 |
Pir | -0.130 |
916 | -0.129 |
Glac | -0.128 |
Token | first |
Token ID | 717 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
olate | +0.002 |
Pag | +0.002 |
916 | +0.002 |
Pir | +0.002 |
Glac | +0.002 |
Neg logit contributions | |
dstg | -0.003 |
arist | -0.003 |
mere | -0.003 |
Roses | -0.003 |
angers | -0.003 |
Token | pair |
Token ID | 5166 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
dstg | +0.016 |
arist | +0.016 |
mere | +0.015 |
Roses | +0.015 |
angers | +0.015 |
Neg logit contributions | |
olate | -0.014 |
Pag | -0.014 |
916 | -0.013 |
Pir | -0.013 |
Glac | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
olate | +0.115 |
Pag | +0.114 |
916 | +0.112 |
Pir | +0.112 |
Glac | +0.111 |
Neg logit contributions | |
dstg | -0.113 |
arist | -0.112 |
mere | -0.109 |
Roses | -0.107 |
angers | -0.107 |
Token | sneakers |
Token ID | 42649 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
olate | +0.004 |
Pag | +0.003 |
916 | +0.003 |
Pir | +0.003 |
Glac | +0.003 |
Neg logit contributions | |
dstg | -0.004 |
arist | -0.004 |
mere | -0.004 |
Roses | -0.004 |
angers | -0.004 |
Token | sque |
Token ID | 35776 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
olate | +0.074 |
Pag | +0.074 |
916 | +0.072 |
Pir | +0.072 |
Glac | +0.072 |
Neg logit contributions | |
dstg | -0.074 |
arist | -0.074 |
mere | -0.072 |
Roses | -0.070 |
angers | -0.070 |
Token | ak |
Token ID | 461 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
olate | +0.251 |
Pag | +0.250 |
916 | +0.245 |
Pir | +0.245 |
Glac | +0.243 |
Neg logit contributions | |
dstg | -0.130 |
arist | -0.128 |
mere | -0.123 |
Roses | -0.119 |
angers | -0.118 |
Token | on |
Token ID | 319 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
dstg | +0.171 |
arist | +0.170 |
mere | +0.166 |
Roses | +0.162 |
angers | +0.161 |
Neg logit contributions | |
olate | -0.170 |
Pag | -0.169 |
916 | -0.166 |
Pir | -0.165 |
Glac | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
olate | +0.010 |
Pag | +0.010 |
Pir | +0.010 |
916 | +0.010 |
Glac | +0.010 |
Neg logit contributions | |
dstg | -0.010 |
arist | -0.010 |
mere | -0.010 |
Roses | -0.010 |
angers | -0.010 |
Token | practice |
Token ID | 3357 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
dstg | +0.001 |
arist | +0.001 |
mere | +0.001 |
Roses | +0.001 |
angers | +0.001 |
Neg logit contributions | |
olate | -0.001 |
Pag | -0.001 |
916 | -0.001 |
Pir | -0.001 |
Glac | -0.001 |
Token | court |
Token ID | 2184 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
olate | +0.103 |
Pag | +0.102 |
916 | +0.099 |
Pir | +0.098 |
Glac | +0.098 |
Neg logit contributions | |
dstg | -0.181 |
arist | -0.180 |
mere | -0.177 |
Roses | -0.174 |
angers | -0.173 |
Token | during |
Token ID | 1141 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
olate | +0.018 |
Pag | +0.018 |
Pir | +0.018 |
916 | +0.018 |
Glac | +0.018 |
Neg logit contributions | |
dstg | -0.019 |
arist | -0.019 |
mere | -0.018 |
Roses | -0.018 |
angers | -0.018 |