Token | give |
Token ID | 1577 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.008 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.018 |
zie | -0.016 |
ンジ | -0.016 |
filename | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.015 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.022 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
velt | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.014 |
Hath | +0.013 |
Nib | +0.013 |
Neg logit contributions | |
lvl | -0.024 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
velt | -0.020 |
Token | truthful |
Token ID | 42278 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
bent | +0.022 |
pleas | +0.021 |
Bac | +0.021 |
Hath | +0.020 |
relig | +0.020 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.024 |
ンジ | -0.024 |
velt | -0.023 |
Token | euphem |
Token ID | 48732 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
bent | +0.078 |
pleas | +0.077 |
Bac | +0.074 |
Hath | +0.073 |
relig | +0.071 |
Neg logit contributions | |
lvl | -0.096 |
Shadow | -0.092 |
zie | -0.083 |
ンジ | -0.082 |
filename | -0.080 |
Token | isms |
Token ID | 6583 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.031 |
zie | +0.029 |
ンジ | +0.029 |
Cargo | +0.028 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
bent | +0.214 |
pleas | +0.210 |
Bac | +0.204 |
Hath | +0.199 |
Nib | +0.191 |
Neg logit contributions | |
lvl | -0.397 |
Shadow | -0.384 |
zie | -0.350 |
ンジ | -0.349 |
Cargo | -0.340 |
Token | � |
Token ID | 447 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.019 |
relig | +0.018 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
filename | -0.026 |
Token | � |
Token ID | 251 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.025 |
Shadow | -0.024 |
zie | -0.022 |
ンジ | -0.022 |
Cargo | -0.021 |
Token | offers |
Token ID | 4394 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
bent | +0.027 |
pleas | +0.027 |
Bac | +0.026 |
Hath | +0.026 |
Nib | +0.025 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.024 |
ンジ | -0.024 |
velt | -0.023 |
Token | Ra |
Token ID | 7567 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
bent | +0.046 |
pleas | +0.046 |
Bac | +0.045 |
Hath | +0.044 |
Nib | +0.043 |
Neg logit contributions | |
lvl | -0.043 |
Shadow | -0.041 |
zie | -0.036 |
ンジ | -0.036 |
filename | -0.035 |
Token | Show |
Token ID | 15307 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
Cargo | -0.004 |
Token | Spe |
Token ID | 2531 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
lvl | +0.022 |
Shadow | +0.022 |
zie | +0.019 |
ンジ | +0.019 |
velt | +0.019 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.016 |
Nib | -0.016 |
Token | lling |
Token ID | 2680 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
bent | +0.038 |
pleas | +0.038 |
Bac | +0.037 |
Hath | +0.037 |
Nib | +0.036 |
Neg logit contributions | |
lvl | -0.015 |
Shadow | -0.014 |
zie | -0.011 |
ンジ | -0.011 |
Cargo | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
lvl | +0.096 |
Shadow | +0.092 |
zie | +0.084 |
ンジ | +0.083 |
velt | +0.081 |
Neg logit contributions | |
bent | -0.065 |
pleas | -0.064 |
Bac | -0.063 |
Hath | -0.062 |
Nib | -0.060 |
Token | Gram |
Token ID | 20159 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | mar |
Token ID | 3876 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.036 |
Shadow | -0.035 |
zie | -0.033 |
ンジ | -0.032 |
velt | -0.032 |
Token | " |
Token ID | 1 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
bent | +0.227 |
pleas | +0.222 |
Bac | +0.219 |
Hath | +0.215 |
Nib | +0.209 |
Neg logit contributions | |
lvl | -0.326 |
Shadow | -0.311 |
zie | -0.282 |
ンジ | -0.281 |
filename | -0.273 |
Token | from |
Token ID | 422 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.025 |
Shadow | -0.024 |
zie | -0.022 |
ンジ | -0.022 |
filename | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
velt | -0.007 |
Token | Spe |
Token ID | 2531 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
zie | +0.005 |
ンジ | +0.005 |
velt | +0.005 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.004 |
Token | lling |
Token ID | 2680 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.023 |
Bac | +0.023 |
Hath | +0.022 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.008 |
zie | -0.006 |
ンジ | -0.006 |
Cargo | -0.006 |
Token | � |
Token ID | 564 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
bent | +0.021 |
pleas | +0.020 |
Bac | +0.020 |
Hath | +0.019 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.038 |
Shadow | -0.037 |
zie | -0.034 |
ンジ | -0.033 |
Cargo | -0.033 |
Token | � |
Token ID | 250 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.025 |
Hath | +0.025 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
zie | -0.029 |
ンジ | -0.029 |
filename | -0.028 |
Token | re |
Token ID | 260 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.030 |
Bac | +0.029 |
Hath | +0.029 |
Nib | +0.028 |
Neg logit contributions | |
lvl | -0.045 |
Shadow | -0.043 |
zie | -0.039 |
ンジ | -0.039 |
Cargo | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.006 |
zie | +0.006 |
ンジ | +0.006 |
Cargo | +0.006 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | eval |
Token ID | 18206 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token | uated |
Token ID | 6605 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.015 |
relig | +0.014 |
Neg logit contributions | |
lvl | -0.054 |
Shadow | -0.053 |
zie | -0.049 |
ンジ | -0.049 |
Cargo | -0.048 |
Token | � |
Token ID | 447 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
bent | +0.213 |
pleas | +0.210 |
Bac | +0.205 |
Hath | +0.200 |
relig | +0.195 |
Neg logit contributions | |
lvl | -0.310 |
Shadow | -0.299 |
zie | -0.270 |
ンジ | -0.267 |
filename | -0.260 |
Token | � |
Token ID | 251 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.031 |
Bac | +0.030 |
Hath | +0.030 |
Nib | +0.029 |
Neg logit contributions | |
lvl | -0.044 |
Shadow | -0.043 |
zie | -0.039 |
ンジ | -0.038 |
Cargo | -0.037 |
Token | his |
Token ID | 465 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.025 |
Hath | +0.025 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.041 |
Shadow | -0.040 |
zie | -0.036 |
ンジ | -0.036 |
Cargo | -0.035 |
Token | language |
Token ID | 3303 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.010 |
Hath | +0.010 |
relig | +0.010 |
Neg logit contributions | |
lvl | -0.015 |
Shadow | -0.014 |
zie | -0.013 |
ンジ | -0.013 |
filename | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
Cargo | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | barrels |
Token ID | 17907 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
zie | +0.004 |
ンジ | +0.004 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
Nib | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
Cargo | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.024 |
zie | +0.021 |
ンジ | +0.021 |
velt | +0.020 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.019 |
Bac | -0.019 |
Hath | -0.018 |
Nib | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.020 |
zie | +0.018 |
ンジ | +0.018 |
Cargo | +0.017 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
Nib | -0.010 |
Token | Virt |
Token ID | 11285 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.019 |
ンジ | +0.018 |
Cargo | +0.018 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.014 |
Hath | -0.014 |
Nib | -0.014 |
Token | ually |
Token ID | 935 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
lvl | +0.050 |
Shadow | +0.049 |
zie | +0.045 |
ンジ | +0.045 |
Cargo | +0.044 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.016 |
Hath | -0.016 |
Nib | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
bent | +0.228 |
pleas | +0.224 |
Bac | +0.218 |
Hath | +0.214 |
Nib | +0.208 |
Neg logit contributions | |
lvl | -0.294 |
Shadow | -0.284 |
zie | -0.256 |
ンジ | -0.253 |
filename | -0.244 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.014 |
Shadow | -0.014 |
zie | -0.013 |
ンジ | -0.012 |
filename | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
Nib | -0.010 |
Token | required |
Token ID | 2672 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.014 |
zie | +0.013 |
ンジ | +0.012 |
filename | +0.012 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.009 |
Token | construction |
Token ID | 5103 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
bent | +0.015 |
pleas | +0.015 |
Bac | +0.015 |
Hath | +0.014 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.019 |
zie | -0.017 |
ンジ | -0.017 |
filename | -0.016 |
Token | do |
Token ID | 466 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
bent | +0.046 |
pleas | +0.044 |
Bac | +0.043 |
Hath | +0.042 |
Nib | +0.041 |
Neg logit contributions | |
lvl | -0.080 |
Shadow | -0.077 |
ンジ | -0.070 |
zie | -0.070 |
filename | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.023 |
relig | +0.022 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
ンジ | -0.030 |
zie | -0.030 |
filename | -0.029 |
Token | know |
Token ID | 760 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
bent | +0.028 |
pleas | +0.027 |
Bac | +0.027 |
Hath | +0.026 |
Nib | +0.025 |
Neg logit contributions | |
lvl | -0.045 |
Shadow | -0.043 |
ンジ | -0.040 |
zie | -0.039 |
filename | -0.038 |
Token | ? |
Token ID | 30 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.004 |
ンジ | +0.004 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
Nib | -0.002 |
Token | Virt |
Token ID | 11285 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.010 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.016 |
zie | -0.014 |
ンジ | -0.014 |
filename | -0.014 |
Token | ually |
Token ID | 935 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.019 |
ンジ | +0.019 |
Cargo | +0.018 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.006 |
Token | every |
Token ID | 790 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
bent | +0.203 |
pleas | +0.199 |
Bac | +0.194 |
Hath | +0.190 |
Nib | +0.184 |
Neg logit contributions | |
lvl | -0.314 |
Shadow | -0.304 |
zie | -0.275 |
ンジ | -0.274 |
velt | -0.265 |
Token | major |
Token ID | 1688 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.010 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.009 |
Neg logit contributions | |
lvl | -0.012 |
Shadow | -0.012 |
zie | -0.010 |
ンジ | -0.010 |
filename | -0.010 |
Token | medical |
Token ID | 3315 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.015 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
relig | -0.010 |
Token | association |
Token ID | 8112 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.012 |
Hath | +0.012 |
relig | +0.011 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.016 |
zie | -0.014 |
ンジ | -0.014 |
filename | -0.014 |
Token | supports |
Token ID | 6971 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
bent | +0.052 |
pleas | +0.051 |
Bac | +0.049 |
Hath | +0.048 |
relig | +0.046 |
Neg logit contributions | |
lvl | -0.107 |
Shadow | -0.104 |
zie | -0.095 |
ンジ | -0.095 |
filename | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
velt | -0.007 |
Token | Spe |
Token ID | 2531 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
zie | +0.005 |
ンジ | +0.005 |
velt | +0.005 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.004 |
Token | lling |
Token ID | 2680 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.023 |
Bac | +0.023 |
Hath | +0.022 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.008 |
zie | -0.006 |
ンジ | -0.006 |
Cargo | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
lvl | +0.087 |
Shadow | +0.084 |
ンジ | +0.075 |
zie | +0.075 |
velt | +0.073 |
Neg logit contributions | |
bent | -0.060 |
pleas | -0.059 |
Bac | -0.057 |
Hath | -0.056 |
Nib | -0.055 |
Token | Gram |
Token ID | 20159 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.002 |
ンジ | +0.002 |
filename | +0.002 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | mar |
Token ID | 3876 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.028 |
ンジ | -0.028 |
velt | -0.028 |
Token | sub |
Token ID | 850 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
bent | +0.224 |
pleas | +0.220 |
Bac | +0.214 |
Hath | +0.211 |
Nib | +0.205 |
Neg logit contributions | |
lvl | -0.291 |
Shadow | -0.279 |
ンジ | -0.252 |
zie | -0.251 |
velt | -0.245 |
Token | menu |
Token ID | 26272 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.023 |
velt | -0.022 |
Token | under |
Token ID | 739 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.009 |
ンジ | -0.009 |
filename | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.007 |
Shadow | -0.007 |
ンジ | -0.006 |
zie | -0.006 |
velt | -0.006 |
Token | Edit |
Token ID | 5312 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.009 |
ンジ | -0.008 |
zie | -0.008 |
velt | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
bent | +0.034 |
pleas | +0.033 |
Bac | +0.033 |
Hath | +0.032 |
Nib | +0.031 |
Neg logit contributions | |
lvl | -0.054 |
Shadow | -0.052 |
zie | -0.048 |
ンジ | -0.047 |
filename | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.019 |
Bac | +0.018 |
Hath | +0.018 |
Nib | +0.017 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
Cargo | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
bent | +0.042 |
pleas | +0.042 |
Bac | +0.041 |
Hath | +0.040 |
Nib | +0.039 |
Neg logit contributions | |
lvl | -0.060 |
Shadow | -0.058 |
zie | -0.053 |
ンジ | -0.052 |
Cargo | -0.051 |
Token | A |
Token ID | 32 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
bent | +0.043 |
pleas | +0.043 |
Bac | +0.042 |
Hath | +0.041 |
Nib | +0.040 |
Neg logit contributions | |
lvl | -0.056 |
Shadow | -0.054 |
zie | -0.049 |
ンジ | -0.048 |
Cargo | -0.047 |
Token | Reve |
Token ID | 31091 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
bent | +0.034 |
pleas | +0.034 |
Bac | +0.033 |
Hath | +0.032 |
Nib | +0.031 |
Neg logit contributions | |
lvl | -0.042 |
Shadow | -0.041 |
zie | -0.037 |
ンジ | -0.037 |
filename | -0.035 |
Token | aling |
Token ID | 4272 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | Look |
Token ID | 6803 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
bent | +0.242 |
pleas | +0.237 |
Bac | +0.236 |
Hath | +0.231 |
Nib | +0.226 |
Neg logit contributions | |
lvl | -0.269 |
Shadow | -0.255 |
ンジ | -0.228 |
zie | -0.228 |
filename | -0.220 |
Token | at |
Token ID | 379 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
bent | +0.015 |
pleas | +0.015 |
Bac | +0.014 |
Hath | +0.014 |
Nib | +0.013 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.025 |
ンジ | -0.025 |
Cargo | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
bent | +0.069 |
pleas | +0.068 |
Bac | +0.067 |
Hath | +0.066 |
Nib | +0.064 |
Neg logit contributions | |
lvl | -0.086 |
Shadow | -0.083 |
zie | -0.075 |
ンジ | -0.074 |
filename | -0.072 |
Token | First |
Token ID | 3274 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
bent | +0.037 |
pleas | +0.036 |
Bac | +0.035 |
Hath | +0.035 |
Nib | +0.034 |
Neg logit contributions | |
lvl | -0.047 |
Shadow | -0.045 |
zie | -0.040 |
ンジ | -0.040 |
filename | -0.039 |
Token | Season |
Token ID | 7369 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
velt | -0.002 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.025 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.046 |
Shadow | -0.045 |
zie | -0.041 |
ンジ | -0.041 |
filename | -0.040 |
Token | below |
Token ID | 2174 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.015 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.027 |
Shadow | -0.026 |
zie | -0.024 |
ンジ | -0.023 |
filename | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
bent | +0.029 |
pleas | +0.029 |
Bac | +0.028 |
Hath | +0.028 |
Nib | +0.027 |
Neg logit contributions | |
lvl | -0.039 |
Shadow | -0.038 |
zie | -0.034 |
ンジ | -0.034 |
Cargo | -0.033 |
Token | normal |
Token ID | 11265 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
lvl | +0.079 |
Shadow | +0.076 |
zie | +0.069 |
ンジ | +0.068 |
filename | +0.066 |
Neg logit contributions | |
bent | -0.059 |
pleas | -0.059 |
Bac | -0.057 |
Hath | -0.056 |
Nib | -0.054 |
Token | fall |
Token ID | 7207 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.013 |
zie | +0.012 |
ンジ | +0.011 |
Cargo | +0.011 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
bent | +0.179 |
pleas | +0.177 |
Bac | +0.171 |
Hath | +0.167 |
Nib | +0.161 |
Neg logit contributions | |
lvl | -0.328 |
Shadow | -0.318 |
zie | -0.290 |
ンジ | -0.288 |
Cargo | -0.281 |
Token | above |
Token ID | 2029 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
Cargo | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
bent | +0.034 |
pleas | +0.034 |
Bac | +0.033 |
Hath | +0.032 |
relig | +0.031 |
Neg logit contributions | |
lvl | -0.046 |
Shadow | -0.044 |
zie | -0.040 |
ンジ | -0.039 |
filename | -0.038 |
Token | average |
Token ID | 23913 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.025 |
Hath | +0.024 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.021 |
Shadow | -0.020 |
zie | -0.018 |
ンジ | -0.018 |
filename | -0.017 |
Token | temperatures |
Token ID | 10101 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.025 |
ンジ | +0.025 |
Cargo | +0.024 |
Neg logit contributions | |
bent | -0.023 |
pleas | -0.022 |
Bac | -0.022 |
Hath | -0.021 |
Nib | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
filename | -0.003 |
Token | mob |
Token ID | 7251 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.023 |
Bac | +0.023 |
Hath | +0.022 |
relig | +0.021 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
zie | -0.030 |
ンジ | -0.030 |
filename | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.031 |
Bac | +0.030 |
Hath | +0.029 |
relig | +0.028 |
Neg logit contributions | |
lvl | -0.059 |
Shadow | -0.057 |
zie | -0.052 |
ンジ | -0.052 |
Cargo | -0.051 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
filename | +0.010 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
Nib | -0.007 |
Token | dupl |
Token ID | 14184 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.015 |
Hath | +0.015 |
relig | +0.014 |
Neg logit contributions | |
lvl | -0.023 |
Shadow | -0.022 |
zie | -0.020 |
ンジ | -0.020 |
filename | -0.019 |
Token | icates |
Token ID | 16856 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
lvl | +0.041 |
Shadow | +0.040 |
zie | +0.036 |
ンジ | +0.035 |
Cargo | +0.034 |
Neg logit contributions | |
bent | -0.034 |
pleas | -0.033 |
Bac | -0.032 |
Hath | -0.032 |
Nib | -0.031 |
Token | . |
Token ID | 764 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
bent | +0.177 |
pleas | +0.174 |
Bac | +0.169 |
Hath | +0.165 |
Nib | +0.159 |
Neg logit contributions | |
lvl | -0.314 |
Shadow | -0.303 |
zie | -0.277 |
ンジ | -0.275 |
Cargo | -0.268 |
Token | . |
Token ID | 764 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.012 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.022 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
Cargo | -0.019 |
Token | ." |
Token ID | 22135 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.022 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
Cargo | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
lvl | +0.108 |
Shadow | +0.104 |
zie | +0.094 |
ンジ | +0.093 |
filename | +0.090 |
Neg logit contributions | |
bent | -0.076 |
pleas | -0.075 |
Bac | -0.074 |
Hath | -0.072 |
Nib | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
bent | +0.021 |
pleas | +0.020 |
Bac | +0.020 |
Hath | +0.019 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.025 |
ンジ | -0.024 |
Cargo | -0.024 |
Token | for |
Token ID | 329 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.030 |
Bac | +0.029 |
Hath | +0.029 |
Nib | +0.028 |
Neg logit contributions | |
lvl | -0.051 |
Shadow | -0.049 |
zie | -0.045 |
ンジ | -0.045 |
Cargo | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.010 |
Bac | +0.010 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.014 |
Shadow | -0.013 |
ンジ | -0.012 |
zie | -0.012 |
filename | -0.012 |
Token | first |
Token ID | 717 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.017 |
Bac | +0.017 |
Hath | +0.016 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.022 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
filename | -0.018 |
Token | b |
Token ID | 275 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
velt | -0.001 |
Token | rit |
Token ID | 799 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
ンジ | +0.004 |
zie | +0.004 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.003 |
Nib | -0.003 |
Token | ish |
Token ID | 680 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.012 |
zie | +0.011 |
ンジ | +0.011 |
Cargo | +0.011 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | edition |
Token ID | 8313 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
bent | +0.219 |
pleas | +0.215 |
Bac | +0.211 |
Hath | +0.205 |
relig | +0.200 |
Neg logit contributions | |
lvl | -0.271 |
Shadow | -0.259 |
zie | -0.232 |
ンジ | -0.232 |
filename | -0.224 |
Token | of |
Token ID | 286 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.031 |
zie | +0.028 |
ンジ | +0.028 |
filename | +0.027 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.016 |
Bac | -0.016 |
Hath | -0.016 |
Nib | -0.015 |
Token | ' |
Token ID | 705 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.031 |
Bac | +0.030 |
Hath | +0.029 |
Nib | +0.029 |
Neg logit contributions | |
lvl | -0.040 |
Shadow | -0.039 |
zie | -0.035 |
ンジ | -0.035 |
filename | -0.034 |
Token | Charlie |
Token ID | 37136 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.014 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.019 |
relig | +0.019 |
Neg logit contributions | |
lvl | -0.035 |
Shadow | -0.034 |
zie | -0.031 |
ンジ | -0.031 |
Cargo | -0.030 |
Token | Mother |
Token ID | 10584 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
filename | -0.008 |
Token | Is |
Token ID | 1148 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
lvl | +0.036 |
Shadow | +0.035 |
zie | +0.032 |
ンジ | +0.032 |
filename | +0.031 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.020 |
Bac | -0.020 |
Hath | -0.019 |
Nib | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.018 |
ンジ | +0.018 |
velt | +0.018 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.014 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.013 |
Token | Acc |
Token ID | 6366 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
filename | -0.003 |
Token | ompl |
Token ID | 6316 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
acent | +0.023 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.019 |
ンジ | -0.017 |
zie | -0.017 |
velt | -0.016 |
Token | ished |
Token ID | 1348 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
lvl | +0.099 |
Shadow | +0.094 |
zie | +0.083 |
ンジ | +0.082 |
Cargo | +0.080 |
Neg logit contributions | |
bent | -0.106 |
pleas | -0.105 |
Bac | -0.103 |
Hath | -0.101 |
Nib | -0.099 |
Token | Travel |
Token ID | 13524 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bent | +0.218 |
pleas | +0.215 |
Bac | +0.214 |
Hath | +0.210 |
Nib | +0.203 |
Neg logit contributions | |
lvl | -0.266 |
Shadow | -0.253 |
ンジ | -0.227 |
zie | -0.226 |
filename | -0.219 |
Token | Writer |
Token ID | 26606 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
ンジ | +0.013 |
zie | +0.013 |
filename | +0.013 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.009 |
Nib | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
Cargo | +0.010 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
Nib | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
bent | +0.039 |
pleas | +0.038 |
Bac | +0.037 |
Hath | +0.036 |
Nib | +0.035 |
Neg logit contributions | |
lvl | -0.052 |
Shadow | -0.050 |
zie | -0.045 |
ンジ | -0.045 |
Cargo | -0.044 |
Token | A |
Token ID | 32 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
bent | +0.040 |
pleas | +0.040 |
Bac | +0.039 |
Hath | +0.039 |
Nib | +0.038 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.031 |
zie | -0.027 |
ンジ | -0.027 |
Cargo | -0.026 |
Token | suicide |
Token ID | 7341 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.012 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.016 |
zie | -0.015 |
ンジ | -0.015 |
Cargo | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +8.30e-03 |
Pos logit contributions | |
lvl | +0.043 |
Shadow | +0.041 |
ンジ | +0.038 |
zie | +0.038 |
velt | +0.036 |
Neg logit contributions | |
bent | -0.025 |
pleas | -0.025 |
Bac | -0.024 |
Hath | -0.024 |
Nib | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
filename | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.014 |
zie | +0.012 |
ンジ | +0.012 |
Cargo | +0.012 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | Tr |
Token ID | 2898 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
Cargo | +0.010 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.007 |
Token | agic |
Token ID | 9083 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.032 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
Cargo | -0.026 |
Token | M |
Token ID | 337 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
pleas | +0.205 |
bent | +0.205 |
Bac | +0.197 |
Hath | +0.194 |
Nib | +0.188 |
Neg logit contributions | |
lvl | -0.271 |
Shadow | -0.260 |
ンジ | -0.235 |
zie | -0.234 |
velt | -0.227 |
Token | illy |
Token ID | 6548 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.007 |
ンジ | +0.006 |
zie | +0.006 |
Cargo | +0.006 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
relig | -0.011 |
Token | died |
Token ID | 3724 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
lvl | +0.043 |
Shadow | +0.042 |
zie | +0.037 |
ンジ | +0.036 |
Cargo | +0.035 |
Neg logit contributions | |
bent | -0.047 |
pleas | -0.047 |
Bac | -0.046 |
Hath | -0.045 |
Nib | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
bent | +0.040 |
pleas | +0.039 |
Bac | +0.038 |
Hath | +0.037 |
Nib | +0.036 |
Neg logit contributions | |
lvl | -0.075 |
Shadow | -0.073 |
zie | -0.066 |
ンジ | -0.066 |
filename | -0.064 |
Token | day |
Token ID | 1110 |
Feature activation | +5.86e-03 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.010 |
Bac | +0.010 |
Hath | +0.010 |
Nib | +0.009 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.017 |
zie | -0.015 |
ンジ | -0.015 |
Cargo | -0.015 |
Token | ist |
Token ID | 396 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.031 |
zie | +0.028 |
ンジ | +0.028 |
Cargo | +0.027 |
Neg logit contributions | |
bent | -0.022 |
pleas | -0.022 |
Bac | -0.021 |
Hath | -0.021 |
Nib | -0.020 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
bent | +0.050 |
pleas | +0.049 |
Bac | +0.048 |
Hath | +0.047 |
Nib | +0.045 |
Neg logit contributions | |
lvl | -0.098 |
Shadow | -0.095 |
zie | -0.086 |
ンジ | -0.086 |
Cargo | -0.084 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.014 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.012 |
filename | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | pract |
Token ID | 1970 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
filename | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | ising |
Token ID | 1710 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.006 |
ンジ | -0.006 |
filename | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
bent | +0.182 |
pleas | +0.179 |
Bac | +0.175 |
Hath | +0.171 |
relig | +0.165 |
Neg logit contributions | |
lvl | -0.291 |
Shadow | -0.280 |
zie | -0.255 |
ンジ | -0.253 |
velt | -0.247 |
Token | tap |
Token ID | 9814 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
relig | +0.023 |
Neg logit contributions | |
lvl | -0.035 |
Shadow | -0.033 |
zie | -0.030 |
ンジ | -0.030 |
Cargo | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
lvl | +0.025 |
Shadow | +0.025 |
zie | +0.022 |
ンジ | +0.022 |
Cargo | +0.022 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.012 |
Token | d |
Token ID | 67 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
zie | -0.003 |
ンジ | -0.003 |
Cargo | -0.003 |
Token | ancing |
Token ID | 5077 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.019 |
Bac | +0.019 |
Hath | +0.019 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.017 |
zie | -0.015 |
ンジ | -0.015 |
Cargo | -0.014 |
Token | Mark |
Token ID | 2940 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.012 |
Bac | +0.012 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.017 |
zie | -0.015 |
ンジ | -0.015 |
filename | -0.015 |
Token | Smith |
Token ID | 4176 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
bent | +0.030 |
pleas | +0.030 |
Bac | +0.029 |
Hath | +0.029 |
Nib | +0.028 |
Neg logit contributions | |
lvl | -0.042 |
Shadow | -0.040 |
zie | -0.036 |
ンジ | -0.036 |
Cargo | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.015 |
Hath | +0.015 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
zie | -0.030 |
ンジ | -0.030 |
filename | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.012 |
filename | -0.011 |
Token | camer |
Token ID | 3676 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
filename | +0.002 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.001 |
Nib | -0.001 |
Token | aman |
Token ID | 10546 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
ンジ | -0.003 |
zie | -0.003 |
Cargo | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
bent | +0.164 |
pleas | +0.162 |
Bac | +0.158 |
Hath | +0.154 |
Nib | +0.148 |
Neg logit contributions | |
lvl | -0.305 |
Shadow | -0.295 |
zie | -0.270 |
ンジ | -0.267 |
Cargo | -0.262 |
Token | had |
Token ID | 550 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.015 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
filename | -0.027 |
Token | worked |
Token ID | 3111 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.006 |
ンジ | -0.006 |
filename | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.027 |
Shadow | -0.026 |
zie | -0.024 |
ンジ | -0.023 |
filename | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.025 |
zie | +0.023 |
ンジ | +0.023 |
filename | +0.022 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.019 |
Bac | -0.019 |
Hath | -0.018 |
Nib | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
lvl | +0.022 |
Shadow | +0.021 |
zie | +0.019 |
ンジ | +0.019 |
filename | +0.019 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.012 |
Nib | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.002 |
Token | process |
Token ID | 1429 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.018 |
ンジ | +0.018 |
filename | +0.018 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.018 |
zie | -0.016 |
ンジ | -0.016 |
Cargo | -0.016 |
Token | reim |
Token ID | 21123 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.007 |
zie | +0.007 |
ンジ | +0.007 |
filename | +0.006 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
relig | -0.005 |
Token | plement |
Token ID | 26908 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
lvl | +0.018 |
Shadow | +0.017 |
zie | +0.016 |
ンジ | +0.016 |
Cargo | +0.015 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | ing |
Token ID | 278 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
bent | +0.158 |
pleas | +0.155 |
Bac | +0.151 |
Hath | +0.147 |
Nib | +0.142 |
Neg logit contributions | |
lvl | -0.311 |
Shadow | -0.300 |
zie | -0.275 |
ンジ | -0.274 |
filename | -0.267 |
Token | our |
Token ID | 674 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
lvl | +0.237 |
Shadow | +0.228 |
zie | +0.207 |
ンジ | +0.205 |
filename | +0.199 |
Neg logit contributions | |
bent | -0.169 |
pleas | -0.166 |
Bac | -0.163 |
Hath | -0.160 |
Nib | -0.154 |
Token | message |
Token ID | 3275 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
lvl | +0.028 |
Shadow | +0.027 |
zie | +0.024 |
ンジ | +0.024 |
filename | +0.023 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.020 |
relig | -0.019 |
Token | bus |
Token ID | 1323 |
Feature activation | -9.71e-04 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.013 |
zie | +0.011 |
ンジ | +0.011 |
filename | +0.010 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.017 |
relig | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
bent | +0.018 |
pleas | +0.017 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.025 |
Shadow | -0.024 |
zie | -0.021 |
ンジ | -0.021 |
filename | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
relig | -0.010 |
Token | inches |
Token ID | 45457 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
lvl | +0.031 |
Shadow | +0.030 |
zie | +0.027 |
ンジ | +0.027 |
Cargo | +0.026 |
Neg logit contributions | |
bent | -0.026 |
pleas | -0.026 |
Bac | -0.025 |
Hath | -0.025 |
Nib | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
lvl | +0.051 |
Shadow | +0.049 |
zie | +0.045 |
ンジ | +0.044 |
filename | +0.043 |
Neg logit contributions | |
bent | -0.027 |
pleas | -0.027 |
Bac | -0.026 |
Hath | -0.025 |
Nib | -0.025 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | fall |
Token ID | 2121 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.012 |
zie | +0.011 |
ンジ | +0.011 |
filename | +0.011 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
bent | +0.155 |
pleas | +0.151 |
Bac | +0.146 |
Hath | +0.142 |
Nib | +0.137 |
Neg logit contributions | |
lvl | -0.309 |
Shadow | -0.299 |
zie | -0.274 |
ンジ | -0.273 |
filename | -0.267 |
Token | the |
Token ID | 262 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.030 |
zie | +0.027 |
ンジ | +0.027 |
filename | +0.026 |
Neg logit contributions | |
bent | -0.023 |
pleas | -0.022 |
Bac | -0.022 |
Hath | -0.021 |
Nib | -0.021 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.005 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
Cargo | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.015 |
Shadow | -0.015 |
zie | -0.014 |
ンジ | -0.013 |
Cargo | -0.013 |
Token | coalition |
Token ID | 9906 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.019 |
ンジ | +0.018 |
filename | +0.018 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.014 |
Bac | -0.014 |
Hath | -0.013 |
Nib | -0.013 |
Token | � |
Token ID | 564 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
lvl | +0.043 |
Shadow | +0.041 |
zie | +0.038 |
ンジ | +0.037 |
Cargo | +0.037 |
Neg logit contributions | |
bent | -0.023 |
pleas | -0.023 |
Bac | -0.022 |
Hath | -0.022 |
Nib | -0.021 |
Token | � |
Token ID | 250 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.008 |
ンジ | -0.007 |
zie | -0.007 |
Cargo | -0.007 |
Token | prov |
Token ID | 15234 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.011 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.017 |
zie | -0.016 |
ンジ | -0.016 |
Cargo | -0.015 |
Token | ides |
Token ID | 1460 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
lvl | +0.113 |
Shadow | +0.109 |
zie | +0.101 |
ンジ | +0.100 |
filename | +0.098 |
Neg logit contributions | |
bent | -0.047 |
pleas | -0.046 |
Bac | -0.045 |
Hath | -0.044 |
Nib | -0.042 |
Token | responsible |
Token ID | 4497 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
bent | +0.184 |
pleas | +0.182 |
Bac | +0.177 |
Hath | +0.173 |
Nib | +0.168 |
Neg logit contributions | |
lvl | -0.277 |
Shadow | -0.267 |
zie | -0.242 |
ンジ | -0.240 |
filename | -0.234 |
Token | economic |
Token ID | 3034 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
bent | +0.038 |
pleas | +0.038 |
Bac | +0.037 |
Hath | +0.036 |
relig | +0.035 |
Neg logit contributions | |
lvl | -0.057 |
Shadow | -0.055 |
zie | -0.050 |
ンジ | -0.049 |
filename | -0.048 |
Token | leadership |
Token ID | 5531 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.013 |
Hath | +0.013 |
relig | +0.013 |
Neg logit contributions | |
lvl | -0.019 |
Shadow | -0.018 |
zie | -0.016 |
ンジ | -0.016 |
filename | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
lvl | +0.038 |
Shadow | +0.037 |
zie | +0.034 |
ンジ | +0.034 |
Cargo | +0.033 |
Neg logit contributions | |
bent | -0.022 |
pleas | -0.022 |
Bac | -0.021 |
Hath | -0.021 |
Nib | -0.020 |
Token | tough |
Token ID | 5802 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.038 |
Shadow | -0.036 |
zie | -0.033 |
ンジ | -0.033 |
filename | -0.032 |
Token | F |
Token ID | 376 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
lvl | +0.019 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
Cargo | +0.016 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.012 |
Token | ED |
Token ID | 1961 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
lvl | +0.033 |
Shadow | +0.032 |
zie | +0.028 |
ンジ | +0.028 |
Cargo | +0.027 |
Neg logit contributions | |
bent | -0.037 |
pleas | -0.037 |
Bac | -0.036 |
Hath | -0.035 |
Nib | -0.034 |
Token | state |
Token ID | 1181 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
bent | +0.035 |
pleas | +0.034 |
Bac | +0.034 |
Hath | +0.033 |
Nib | +0.032 |
Neg logit contributions | |
lvl | -0.051 |
Shadow | -0.049 |
zie | -0.044 |
ンジ | -0.044 |
Cargo | -0.043 |
Token | ) |
Token ID | 8 |
Feature activation | -9.20e-03 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.020 |
Hath | +0.019 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.029 |
Shadow | -0.028 |
zie | -0.025 |
ンジ | -0.025 |
Cargo | -0.024 |
Token | accompl |
Token ID | 6424 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | ishes |
Token ID | 5614 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
lvl | +0.056 |
Shadow | +0.054 |
zie | +0.049 |
ンジ | +0.049 |
Cargo | +0.048 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.028 |
Bac | -0.027 |
Hath | -0.027 |
relig | -0.026 |
Token | all |
Token ID | 477 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
bent | +0.189 |
pleas | +0.187 |
Bac | +0.182 |
Hath | +0.178 |
Nib | +0.173 |
Neg logit contributions | |
lvl | -0.270 |
Shadow | -0.261 |
zie | -0.235 |
ンジ | -0.234 |
filename | -0.227 |
Token | of |
Token ID | 286 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | these |
Token ID | 777 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.023 |
ンジ | +0.023 |
Cargo | +0.022 |
Neg logit contributions | |
bent | -0.022 |
pleas | -0.022 |
Bac | -0.021 |
Hath | -0.021 |
Nib | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.025 |
ンジ | +0.025 |
Cargo | +0.024 |
Neg logit contributions | |
bent | -0.023 |
pleas | -0.022 |
Bac | -0.022 |
Hath | -0.021 |
Nib | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
lvl | +0.054 |
Shadow | +0.052 |
zie | +0.048 |
ンジ | +0.047 |
Cargo | +0.046 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.029 |
Bac | -0.028 |
Hath | -0.027 |
Nib | -0.026 |
Token | Brune |
Token ID | 46070 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
Cargo | +0.017 |
Neg logit contributions | |
bent | -0.018 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.017 |
relig | -0.016 |
Token | i |
Token ID | 72 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
bent | +0.099 |
pleas | +0.097 |
Bac | +0.095 |
Hath | +0.093 |
Nib | +0.090 |
Neg logit contributions | |
lvl | -0.145 |
Shadow | -0.140 |
zie | -0.127 |
ンジ | -0.126 |
Cargo | -0.123 |
Token | Dar |
Token ID | 7491 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
lvl | +0.076 |
Shadow | +0.073 |
zie | +0.066 |
ンジ | +0.065 |
filename | +0.063 |
Neg logit contributions | |
bent | -0.061 |
pleas | -0.060 |
Bac | -0.059 |
Hath | -0.058 |
Nib | -0.056 |
Token | uss |
Token ID | 1046 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bent | +0.053 |
pleas | +0.053 |
Bac | +0.052 |
Hath | +0.051 |
Nib | +0.050 |
Neg logit contributions | |
lvl | -0.046 |
Shadow | -0.044 |
zie | -0.038 |
ンジ | -0.038 |
filename | -0.036 |
Token | alam |
Token ID | 44949 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.017 |
zie | +0.016 |
ンジ | +0.015 |
filename | +0.015 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.002 |
Token | ( |
Token ID | 357 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
bent | +0.198 |
pleas | +0.194 |
Bac | +0.190 |
Hath | +0.187 |
Nib | +0.181 |
Neg logit contributions | |
lvl | -0.260 |
Shadow | -0.250 |
zie | -0.225 |
ンジ | -0.224 |
filename | -0.218 |
Token | Aut |
Token ID | 16541 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | or |
Token ID | 273 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.005 |
zie | +0.005 |
ンジ | +0.005 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
Nib | -0.008 |
Token | iti |
Token ID | 8846 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.012 |
zie | -0.011 |
ンジ | -0.011 |
Cargo | -0.011 |
Token | Mon |
Token ID | 2892 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
Cargo | +0.017 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.011 |
Hath | -0.011 |
Nib | -0.011 |
Token | until |
Token ID | 1566 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.008 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | my |
Token ID | 616 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
bent | +0.054 |
pleas | +0.053 |
Bac | +0.052 |
Hath | +0.051 |
Nib | +0.049 |
Neg logit contributions | |
lvl | -0.079 |
Shadow | -0.076 |
zie | -0.069 |
ンジ | -0.068 |
filename | -0.066 |
Token | dad |
Token ID | 9955 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
ンジ | +0.015 |
zie | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
Nib | -0.010 |
Token | cou |
Token ID | 2284 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.007 |
zie | +0.006 |
ンジ | +0.006 |
Cargo | +0.006 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | g |
Token ID | 70 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.003 |
ンジ | +0.003 |
zie | +0.003 |
Cargo | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | hed |
Token ID | 704 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
bent | +0.165 |
pleas | +0.162 |
Bac | +0.158 |
Hath | +0.154 |
Nib | +0.149 |
Neg logit contributions | |
lvl | -0.288 |
Shadow | -0.278 |
zie | -0.253 |
ンジ | -0.251 |
Cargo | -0.245 |
Token | break |
Token ID | 2270 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
filename | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.013 |
zie | +0.012 |
ンジ | +0.012 |
filename | +0.011 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.009 |
Token | tension |
Token ID | 12097 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
ンジ | +0.005 |
zie | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
Nib | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
lvl | +0.062 |
Shadow | +0.060 |
zie | +0.055 |
ンジ | +0.054 |
Cargo | +0.053 |
Neg logit contributions | |
bent | -0.037 |
pleas | -0.037 |
Bac | -0.036 |
Hath | -0.035 |
Nib | -0.034 |
Token | rifles |
Token ID | 18469 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
lvl | +0.033 |
Shadow | +0.032 |
zie | +0.029 |
ンジ | +0.028 |
filename | +0.028 |
Neg logit contributions | |
bent | -0.025 |
pleas | -0.024 |
Bac | -0.024 |
Hath | -0.023 |
Nib | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -5.36e-04 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.011 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.021 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
filename | -0.018 |
Token | shotguns |
Token ID | 47392 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
Nib | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
Cargo | +0.009 |
Neg logit contributions | |
pleas | -0.005 |
bent | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | revol |
Token ID | 35891 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
filename | -0.001 |
Token | vers |
Token ID | 690 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.013 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.005 |
ンジ | -0.005 |
Cargo | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
lvl | +0.363 |
Shadow | +0.353 |
zie | +0.323 |
ンジ | +0.320 |
Cargo | +0.316 |
Neg logit contributions | |
pleas | -0.187 |
bent | -0.187 |
Bac | -0.182 |
Hath | -0.178 |
Nib | -0.170 |
Token | autom |
Token ID | 3557 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
filename | -0.008 |
Token | atics |
Token ID | 23372 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
lvl | +0.058 |
Shadow | +0.056 |
ンジ | +0.050 |
zie | +0.050 |
Cargo | +0.048 |
Neg logit contributions | |
bent | -0.050 |
pleas | -0.049 |
Bac | -0.048 |
Hath | -0.047 |
Nib | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | over |
Token ID | 625 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.008 |
zie | -0.008 |
ンジ | -0.008 |
filename | -0.007 |
Token | explained |
Token ID | 4893 |
Feature activation | -7.30e-03 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.021 |
Shadow | -0.020 |
zie | -0.018 |
ンジ | -0.018 |
velt | -0.018 |
Token | here |
Token ID | 994 |
Feature activation | +2.05e-05 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
zie | +0.007 |
ンジ | +0.007 |
filename | +0.007 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
bent | +0.000 |
pleas | +0.000 |
Bac | +0.000 |
Hath | +0.000 |
Nib | +0.000 |
Neg logit contributions | |
lvl | -0.000 |
Shadow | -0.000 |
ンジ | -0.000 |
zie | -0.000 |
velt | -0.000 |
Token | * |
Token ID | 1635 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.020 |
Hath | +0.019 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.031 |
ンジ | -0.029 |
zie | -0.029 |
velt | -0.028 |
Token | mod |
Token ID | 4666 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
lvl | +0.026 |
Shadow | +0.025 |
zie | +0.022 |
ンジ | +0.022 |
velt | +0.022 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.018 |
Bac | -0.018 |
Hath | -0.018 |
Nib | -0.017 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.014 |
zie | +0.010 |
ンジ | +0.010 |
Cargo | +0.009 |
Neg logit contributions | |
bent | -0.059 |
pleas | -0.059 |
Bac | -0.058 |
Hath | -0.057 |
Nib | -0.057 |
Token | * |
Token ID | 9 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
lvl | +0.314 |
Shadow | +0.303 |
zie | +0.275 |
ンジ | +0.274 |
velt | +0.266 |
Neg logit contributions | |
bent | -0.230 |
pleas | -0.227 |
Bac | -0.221 |
Hath | -0.216 |
Nib | -0.211 |
Token | * |
Token ID | 1635 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.031 |
Bac | +0.030 |
Hath | +0.029 |
Nib | +0.029 |
Neg logit contributions | |
lvl | -0.049 |
Shadow | -0.048 |
ンジ | -0.044 |
zie | -0.043 |
velt | -0.042 |
Token | vim |
Token ID | 31124 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.013 |
zie | +0.012 |
ンジ | +0.012 |
Cargo | +0.012 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
Nib | -0.010 |
Token | : |
Token ID | 25 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
velt | +0.002 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
Nib | -0.002 |
Token | * |
Token ID | 9 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.008 |
ンジ | -0.008 |
Cargo | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
bent | +0.065 |
pleas | +0.064 |
Bac | +0.062 |
Hath | +0.060 |
Nib | +0.058 |
Neg logit contributions | |
lvl | -0.136 |
Shadow | -0.131 |
zie | -0.120 |
ンジ | -0.120 |
velt | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.017 |
Bac | +0.016 |
Hath | +0.016 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.024 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
velt | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
ンジ | -0.003 |
zie | -0.003 |
velt | -0.003 |
Token | ' |
Token ID | 705 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
velt | +0.003 |
Neg logit contributions | |
pleas | -0.003 |
bent | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | mod |
Token ID | 4666 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.021 |
velt | +0.020 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.016 |
Hath | -0.016 |
Nib | -0.016 |
Token | ' |
Token ID | 6 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
lvl | +0.288 |
Shadow | +0.277 |
zie | +0.250 |
ンジ | +0.248 |
Cargo | +0.241 |
Neg logit contributions | |
bent | -0.236 |
pleas | -0.233 |
Bac | -0.227 |
Hath | -0.221 |
Nib | -0.217 |
Token | option |
Token ID | 3038 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
bent | +0.022 |
pleas | +0.022 |
Bac | +0.021 |
Hath | +0.021 |
Nib | +0.020 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.023 |
velt | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bent | +0.018 |
pleas | +0.018 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.035 |
Shadow | -0.034 |
zie | -0.031 |
ンジ | -0.031 |
velt | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.010 |
Bac | +0.010 |
Hath | +0.009 |
Nib | +0.009 |
Neg logit contributions | |
lvl | -0.019 |
Shadow | -0.018 |
zie | -0.017 |
ンジ | -0.017 |
velt | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.012 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.023 |
velt | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.018 |
relig | +0.018 |
Neg logit contributions | |
lvl | -0.036 |
Shadow | -0.035 |
ンジ | -0.031 |
zie | -0.031 |
filename | -0.030 |
Token | set |
Token ID | 900 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.018 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.031 |
zie | -0.029 |
ンジ | -0.029 |
velt | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
velt | -0.007 |
Token | * |
Token ID | 1635 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.017 |
Bac | +0.017 |
Hath | +0.016 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
ンジ | -0.025 |
zie | -0.025 |
velt | -0.024 |
Token | mod |
Token ID | 4666 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
lvl | +0.030 |
Shadow | +0.029 |
zie | +0.026 |
ンジ | +0.026 |
Cargo | +0.025 |
Neg logit contributions | |
bent | -0.025 |
pleas | -0.024 |
Bac | -0.024 |
Hath | -0.023 |
Nib | -0.023 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.012 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.007 |
Neg logit contributions | |
bent | -0.061 |
pleas | -0.060 |
Bac | -0.060 |
Hath | -0.059 |
Nib | -0.058 |
Token | - |
Token ID | 12 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
lvl | +0.308 |
Shadow | +0.297 |
zie | +0.269 |
ンジ | +0.267 |
Cargo | +0.260 |
Neg logit contributions | |
bent | -0.213 |
pleas | -0.210 |
Bac | -0.205 |
Hath | -0.201 |
Nib | -0.195 |
Token | version |
Token ID | 9641 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.024 |
ンジ | -0.024 |
Cargo | -0.023 |
Token | * |
Token ID | 9 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
bent | +0.038 |
pleas | +0.038 |
Bac | +0.037 |
Hath | +0.036 |
Nib | +0.035 |
Neg logit contributions | |
lvl | -0.058 |
Shadow | -0.056 |
zie | -0.051 |
ンジ | -0.050 |
Cargo | -0.049 |
Token | If |
Token ID | 1002 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
bent | +0.033 |
pleas | +0.032 |
Bac | +0.032 |
Hath | +0.031 |
Nib | +0.030 |
Neg logit contributions | |
lvl | -0.049 |
Shadow | -0.047 |
zie | -0.043 |
ンジ | -0.043 |
velt | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.015 |
zie | +0.014 |
ンジ | +0.014 |
velt | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
Nib | -0.010 |
Token | option |
Token ID | 3038 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
lvl | +0.026 |
Shadow | +0.025 |
zie | +0.023 |
ンジ | +0.023 |
velt | +0.022 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.023 |
Hath | -0.023 |
Nib | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
velt | -0.009 |
Token | If |
Token ID | 1002 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
bent | +0.021 |
pleas | +0.021 |
Bac | +0.020 |
Hath | +0.020 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.032 |
zie | -0.029 |
ンジ | -0.029 |
velt | -0.028 |
Token | ' |
Token ID | 705 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
lvl | +0.030 |
Shadow | +0.029 |
zie | +0.027 |
ンジ | +0.026 |
velt | +0.026 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.019 |
Nib | -0.019 |
Token | mod |
Token ID | 4666 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.027 |
Shadow | -0.026 |
zie | -0.023 |
ンジ | -0.023 |
Cargo | -0.022 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
Cargo | +0.000 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | ' |
Token ID | 6 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
lvl | +0.285 |
Shadow | +0.274 |
zie | +0.245 |
ンジ | +0.243 |
filename | +0.237 |
Neg logit contributions | |
bent | -0.234 |
pleas | -0.231 |
Bac | -0.226 |
Hath | -0.222 |
Nib | -0.215 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.014 |
zie | +0.012 |
ンジ | +0.012 |
velt | +0.012 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.006 |
Token | off |
Token ID | 572 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.011 |
zie | -0.010 |
ンジ | -0.010 |
velt | -0.009 |
Token | or |
Token ID | 393 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.044 |
Shadow | -0.042 |
zie | -0.039 |
ンジ | -0.039 |
Cargo | -0.038 |
Token | ' |
Token ID | 705 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.008 |
zie | +0.008 |
ンジ | +0.007 |
velt | +0.007 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | grow |
Token ID | 1663 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.019 |
ンジ | +0.019 |
filename | +0.018 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
relig | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.024 |
ンジ | +0.023 |
Cargo | +0.023 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.014 |
Hath | -0.014 |
relig | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.008 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.011 |
velt | -0.011 |
Token | naive |
Token ID | 24354 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
relig | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
velt | -0.001 |
Token | cheer |
Token ID | 14042 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.024 |
ンジ | +0.024 |
filename | +0.023 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.019 |
Bac | -0.019 |
Hath | -0.018 |
relig | -0.018 |
Token | leader |
Token ID | 27940 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
lvl | +0.316 |
Shadow | +0.305 |
zie | +0.277 |
ンジ | +0.274 |
Cargo | +0.268 |
Neg logit contributions | |
bent | -0.203 |
pleas | -0.199 |
Bac | -0.195 |
Hath | -0.190 |
Nib | -0.184 |
Token | a |
Token ID | 257 |
Feature activation | -5.66e-04 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
Cargo | -0.007 |
Token | military |
Token ID | 2422 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
relig | -0.000 |
Token | leader |
Token ID | 3554 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
bent | +0.042 |
pleas | +0.041 |
Bac | +0.040 |
Hath | +0.039 |
relig | +0.038 |
Neg logit contributions | |
lvl | -0.043 |
Shadow | -0.041 |
zie | -0.036 |
ンジ | -0.036 |
filename | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
lvl | +0.056 |
Shadow | +0.054 |
zie | +0.049 |
ンジ | +0.049 |
Cargo | +0.048 |
Neg logit contributions | |
bent | -0.032 |
pleas | -0.031 |
Bac | -0.031 |
Hath | -0.030 |
Nib | -0.029 |
Token | example |
Token ID | 20688 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.027 |
Shadow | -0.026 |
zie | -0.024 |
ンジ | -0.023 |
Cargo | -0.023 |
Token | : |
Token ID | 25 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token | "). |
Token ID | 11074 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.030 |
Bac | +0.029 |
Hath | +0.029 |
Nib | +0.028 |
Neg logit contributions | |
lvl | -0.038 |
Shadow | -0.037 |
zie | -0.033 |
ンジ | -0.033 |
Cargo | -0.032 |
Token | * |
Token ID | 1635 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.011 |
zie | -0.010 |
ンジ | -0.010 |
velt | -0.009 |
Token | mod |
Token ID | 4666 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
lvl | +0.033 |
Shadow | +0.032 |
zie | +0.028 |
ンジ | +0.028 |
Cargo | +0.027 |
Neg logit contributions | |
bent | -0.031 |
pleas | -0.031 |
Bac | -0.030 |
Hath | -0.029 |
Nib | -0.029 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.008 |
zie | +0.005 |
ンジ | +0.005 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.038 |
pleas | -0.038 |
Bac | -0.037 |
Hath | -0.037 |
Nib | -0.036 |
Token | - |
Token ID | 12 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
lvl | +0.303 |
Shadow | +0.292 |
zie | +0.264 |
ンジ | +0.262 |
Cargo | +0.255 |
Neg logit contributions | |
bent | -0.207 |
pleas | -0.203 |
Bac | -0.199 |
Hath | -0.195 |
Nib | -0.189 |
Token | local |
Token ID | 12001 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
ンジ | +0.004 |
zie | +0.004 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.003 |
Token | * |
Token ID | 9 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
bent | +0.022 |
pleas | +0.022 |
Bac | +0.021 |
Hath | +0.020 |
Nib | +0.020 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
zie | -0.030 |
ンジ | -0.030 |
velt | -0.029 |
Token | The |
Token ID | 383 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.032 |
zie | -0.029 |
ンジ | -0.029 |
velt | -0.028 |
Token | options |
Token ID | 3689 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
bent | +0.018 |
pleas | +0.018 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.017 |
Neg logit contributions | |
lvl | -0.025 |
Shadow | -0.025 |
zie | -0.022 |
ンジ | -0.022 |
velt | -0.021 |
Token | or |
Token ID | 393 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
bent | +0.000 |
pleas | +0.000 |
Bac | +0.000 |
Hath | +0.000 |
relig | +0.000 |
Neg logit contributions | |
lvl | -0.000 |
Shadow | -0.000 |
zie | -0.000 |
ンジ | -0.000 |
filename | -0.000 |
Token | abuse |
Token ID | 5076 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
bent | +0.027 |
pleas | +0.027 |
Bac | +0.026 |
Hath | +0.025 |
relig | +0.024 |
Neg logit contributions | |
lvl | -0.054 |
Shadow | -0.052 |
zie | -0.048 |
ンジ | -0.048 |
Cargo | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
relig | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.007 |
zie | -0.007 |
ンジ | -0.006 |
filename | -0.006 |
Token | Lif |
Token ID | 21073 |
Feature activation | -9.07e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
relig | +0.001 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
ンジ | +0.002 |
zie | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.012 |
Token | program |
Token ID | 1430 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
lvl | +0.284 |
Shadow | +0.271 |
zie | +0.245 |
ンジ | +0.244 |
filename | +0.236 |
Neg logit contributions | |
bent | -0.224 |
pleas | -0.222 |
Bac | -0.217 |
Hath | -0.213 |
relig | -0.206 |
Token | diver |
Token ID | 12312 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.015 |
Bac | +0.015 |
Hath | +0.014 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.030 |
Shadow | -0.029 |
zie | -0.026 |
ンジ | -0.026 |
filename | -0.026 |
Token | ts |
Token ID | 912 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.018 |
Bac | +0.018 |
Hath | +0.018 |
Nib | +0.017 |
Neg logit contributions | |
lvl | -0.027 |
Shadow | -0.026 |
zie | -0.023 |
ンジ | -0.023 |
filename | -0.022 |
Token | scarce |
Token ID | 18549 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.008 |
ンジ | -0.008 |
filename | -0.008 |
Token | funds |
Token ID | 5153 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
bent | +0.039 |
pleas | +0.039 |
Bac | +0.037 |
Hath | +0.037 |
relig | +0.035 |
Neg logit contributions | |
lvl | -0.066 |
Shadow | -0.064 |
zie | -0.058 |
ンジ | -0.057 |
filename | -0.056 |
Token | def |
Token ID | 825 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
lvl | +0.018 |
Shadow | +0.018 |
zie | +0.016 |
ンジ | +0.016 |
filename | +0.015 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.012 |
relig | -0.011 |
Token | raud |
Token ID | 22863 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.024 |
ンジ | +0.024 |
Cargo | +0.023 |
Neg logit contributions | |
bent | -0.020 |
pleas | -0.020 |
Bac | -0.019 |
Hath | -0.019 |
Nib | -0.018 |
Token | ing |
Token ID | 278 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
pleas | +0.051 |
bent | +0.051 |
Bac | +0.049 |
Hath | +0.047 |
Nib | +0.045 |
Neg logit contributions | |
lvl | -0.105 |
Shadow | -0.101 |
ンジ | -0.093 |
zie | -0.093 |
velt | -0.090 |
Token | its |
Token ID | 663 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
filename | -0.003 |
Token | Lif |
Token ID | 21073 |
Feature activation | -9.81e-03 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
relig | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
velt | -0.001 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
ンジ | +0.002 |
zie | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.013 |
Token | program |
Token ID | 1430 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
lvl | +0.270 |
Shadow | +0.258 |
zie | +0.230 |
ンジ | +0.229 |
filename | +0.222 |
Neg logit contributions | |
bent | -0.237 |
pleas | -0.235 |
Bac | -0.229 |
Hath | -0.226 |
relig | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +9.32e-04 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
filename | +0.013 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.009 |
Token | which |
Token ID | 543 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
filename | -0.001 |
Token | subsid |
Token ID | 7905 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
zie | +0.007 |
ンジ | +0.007 |
filename | +0.007 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.004 |
relig | -0.004 |
Token | izes |
Token ID | 4340 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.004 |
ンジ | +0.004 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.002 |
Nib | -0.002 |
Token | will |
Token ID | 481 |
Feature activation | -4.51e-03 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
filename | -0.004 |
Token | begin |
Token ID | 2221 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
zie | +0.004 |
ンジ | +0.004 |
filename | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
lvl | +0.047 |
Shadow | +0.046 |
zie | +0.041 |
ンジ | +0.041 |
filename | +0.040 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.029 |
Bac | -0.028 |
Hath | -0.027 |
Nib | -0.027 |
Token | our |
Token ID | 674 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | asc |
Token ID | 10570 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.005 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | ension |
Token ID | 3004 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.008 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.007 |
Shadow | -0.006 |
zie | -0.005 |
ンジ | -0.005 |
Cargo | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
lvl | +0.330 |
Shadow | +0.319 |
zie | +0.292 |
ンジ | +0.291 |
filename | +0.283 |
Neg logit contributions | |
bent | -0.177 |
pleas | -0.174 |
Bac | -0.168 |
Hath | -0.164 |
Nib | -0.159 |
Token | Therefore |
Token ID | 8447 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.012 |
filename | -0.011 |
Token | must |
Token ID | 1276 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.012 |
filename | -0.011 |
Token | have |
Token ID | 423 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.012 |
zie | +0.011 |
ンジ | +0.011 |
filename | +0.011 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.006 |
Nib | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
zie | +0.015 |
ンジ | +0.015 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.011 |
Token | Labour |
Token ID | 7179 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.019 |
ンジ | +0.019 |
filename | +0.018 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.014 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.012 |
Token | Conference |
Token ID | 8785 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.011 |
Hath | +0.011 |
relig | +0.010 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.016 |
zie | -0.015 |
ンジ | -0.015 |
filename | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.022 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.043 |
Shadow | -0.041 |
zie | -0.038 |
ンジ | -0.038 |
Cargo | -0.037 |
Token | Refer |
Token ID | 33973 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.008 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | ring |
Token ID | 1806 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
lvl | +0.018 |
Shadow | +0.017 |
zie | +0.014 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.035 |
pleas | -0.035 |
Bac | -0.035 |
Hath | -0.034 |
Nib | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
lvl | +0.278 |
Shadow | +0.268 |
zie | +0.241 |
ンジ | +0.240 |
Cargo | +0.233 |
Neg logit contributions | |
bent | -0.217 |
pleas | -0.213 |
Bac | -0.209 |
Hath | -0.206 |
Nib | -0.200 |
Token | Cathy |
Token ID | 40636 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
lvl | +0.103 |
Shadow | +0.099 |
zie | +0.090 |
ンジ | +0.089 |
filename | +0.087 |
Neg logit contributions | |
bent | -0.073 |
pleas | -0.072 |
Bac | -0.070 |
Hath | -0.069 |
Nib | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
bent | +0.049 |
pleas | +0.048 |
Bac | +0.047 |
Hath | +0.046 |
Nib | +0.045 |
Neg logit contributions | |
lvl | -0.070 |
Shadow | -0.068 |
zie | -0.061 |
ンジ | -0.061 |
Cargo | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
lvl | +0.019 |
Shadow | +0.018 |
zie | +0.016 |
ンジ | +0.016 |
filename | +0.016 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.011 |
Token | woman |
Token ID | 2415 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.015 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.013 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.011 |
Hath | -0.011 |
relig | -0.011 |
Token | now |
Token ID | 783 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.007 |
zie | +0.007 |
ンジ | +0.007 |
filename | +0.007 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | patiently |
Token ID | 37220 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
filename | +0.010 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | wait |
Token ID | 4043 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
lvl | +0.058 |
Shadow | +0.056 |
zie | +0.051 |
ンジ | +0.050 |
filename | +0.049 |
Neg logit contributions | |
bent | -0.040 |
pleas | -0.039 |
Bac | -0.038 |
Hath | -0.038 |
Nib | -0.036 |
Token | our |
Token ID | 674 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
lvl | +0.048 |
Shadow | +0.047 |
zie | +0.043 |
ンジ | +0.042 |
Cargo | +0.041 |
Neg logit contributions | |
bent | -0.027 |
pleas | -0.026 |
Bac | -0.026 |
Hath | -0.025 |
Nib | -0.024 |
Token | asc |
Token ID | 10570 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
bent | +0.018 |
pleas | +0.018 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.017 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
Cargo | -0.027 |
Token | ension |
Token ID | 3004 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-04 |
Pos logit contributions | |
lvl | +0.317 |
Shadow | +0.305 |
zie | +0.279 |
ンジ | +0.277 |
filename | +0.271 |
Neg logit contributions | |
bent | -0.178 |
pleas | -0.175 |
Bac | -0.170 |
Hath | -0.166 |
Nib | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
lvl | +0.000 |
Shadow | +0.000 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
Nib | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.004 |
ンジ | +0.004 |
Cargo | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | George |
Token ID | 20191 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
zie | +0.007 |
ンジ | +0.007 |
Cargo | +0.007 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.015 |
relig | +0.015 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.020 |
zie | -0.018 |
ンジ | -0.017 |
Cargo | -0.017 |
Token | � |
Token ID | 12466 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.006 |
zie | +0.005 |
ンジ | +0.005 |
velt | +0.005 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
relig | -0.008 |
Token | � |
Token ID | 112 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
bent | +0.039 |
pleas | +0.039 |
Bac | +0.038 |
Hath | +0.037 |
Nib | +0.036 |
Neg logit contributions | |
lvl | -0.040 |
Shadow | -0.038 |
zie | -0.034 |
ンジ | -0.034 |
Cargo | -0.033 |
Token | р |
Token ID | 21169 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.023 |
Hath | -0.023 |
Nib | -0.022 |
Token | у |
Token ID | 35072 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
lvl | +0.048 |
Shadow | +0.045 |
zie | +0.039 |
ンジ | +0.039 |
Cargo | +0.037 |
Neg logit contributions | |
bent | -0.067 |
pleas | -0.067 |
Bac | -0.066 |
Hath | -0.065 |
Nib | -0.063 |
Token | � |
Token ID | 140 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.008 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.012 |
Token | � |
Token ID | 115 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.022 |
Bac | +0.022 |
Hath | +0.022 |
relig | +0.021 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.020 |
zie | -0.017 |
ンジ | -0.017 |
Cargo | -0.016 |
Token | ь |
Token ID | 45367 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
lvl | +0.213 |
Shadow | +0.202 |
zie | +0.175 |
ンジ | +0.173 |
filename | +0.167 |
Neg logit contributions | |
bent | -0.281 |
pleas | -0.277 |
Bac | -0.273 |
Hath | -0.269 |
relig | -0.263 |
Token | я |
Token ID | 40623 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
relig | +0.004 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
zie | -0.003 |
ンジ | -0.003 |
filename | -0.003 |
Token | м |
Token ID | 43108 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
bent | +0.084 |
pleas | +0.083 |
Bac | +0.082 |
Hath | +0.081 |
relig | +0.079 |
Neg logit contributions | |
lvl | -0.074 |
Shadow | -0.071 |
zie | -0.062 |
ンジ | -0.062 |
filename | -0.060 |
Token | и |
Token ID | 18849 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.025 |
Hath | +0.025 |
relig | +0.024 |
Neg logit contributions | |
lvl | -0.023 |
Shadow | -0.022 |
zie | -0.020 |
ンジ | -0.019 |
filename | -0.019 |
Token | � |
Token ID | 12466 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
zie | +0.007 |
ンジ | +0.007 |
filename | +0.006 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.007 |
Nib | -0.007 |
Token | ineligible |
Token ID | 39538 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
lvl | +0.000 |
Shadow | +0.000 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
relig | -0.000 |
Token | consumers |
Token ID | 7008 |
Feature activation | +8.66e-04 |
Pos logit contributions | |
lvl | +0.034 |
Shadow | +0.033 |
zie | +0.030 |
ンジ | +0.029 |
velt | +0.029 |
Neg logit contributions | |
bent | -0.025 |
pleas | -0.025 |
Bac | -0.024 |
Hath | -0.024 |
Nib | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.000 |
Bac | +0.000 |
Hath | +0.000 |
Nib | +0.000 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
Cargo | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
filename | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | Lif |
Token ID | 21073 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
filename | +0.013 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.009 |
relig | -0.009 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
ンジ | -0.001 |
zie | -0.001 |
Cargo | -0.001 |
Token | program |
Token ID | 1430 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
lvl | +0.276 |
Shadow | +0.264 |
zie | +0.237 |
ンジ | +0.237 |
filename | +0.229 |
Neg logit contributions | |
bent | -0.220 |
pleas | -0.218 |
Bac | -0.212 |
Hath | -0.208 |
relig | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.023 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
filename | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
Cargo | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
Cargo | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
filename | +0.008 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.026 |
ンジ | +0.026 |
filename | +0.025 |
Neg logit contributions | |
bent | -0.016 |
pleas | -0.016 |
Bac | -0.015 |
Hath | -0.015 |
relig | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.008 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.017 |
zie | -0.015 |
ンジ | -0.015 |
filename | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
lvl | +0.026 |
Shadow | +0.025 |
zie | +0.023 |
ンジ | +0.023 |
filename | +0.022 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.018 |
Bac | -0.018 |
Hath | -0.018 |
Nib | -0.017 |
Token | CDC |
Token ID | 20434 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.009 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.008 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.007 |
Token | Guid |
Token ID | 37026 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.025 |
Bac | +0.025 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.047 |
Shadow | -0.046 |
zie | -0.042 |
ンジ | -0.041 |
filename | -0.040 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.010 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.008 |
Neg logit contributions | |
bent | -0.027 |
pleas | -0.027 |
Bac | -0.027 |
Hath | -0.026 |
Nib | -0.026 |
Token | itself |
Token ID | 2346 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
lvl | +0.315 |
Shadow | +0.304 |
zie | +0.277 |
ンジ | +0.275 |
filename | +0.269 |
Neg logit contributions | |
bent | -0.178 |
pleas | -0.175 |
Bac | -0.171 |
Hath | -0.167 |
Nib | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.002 |
ンジ | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
Nib | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -9.13e-05 |
Pos logit contributions | |
bent | +0.015 |
pleas | +0.015 |
Bac | +0.015 |
Hath | +0.015 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.024 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
velt | -0.021 |
Token | see |
Token ID | 766 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
lvl | +0.000 |
Shadow | +0.000 |
ンジ | +0.000 |
zie | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
relig | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
filename | +0.017 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
relig | +0.003 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
filename | -0.004 |
Token | year |
Token ID | 1941 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
lvl | +0.026 |
Shadow | +0.025 |
zie | +0.022 |
ンジ | +0.022 |
Cargo | +0.022 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.024 |
Hath | -0.023 |
Nib | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
lvl | +0.066 |
Shadow | +0.063 |
zie | +0.058 |
ンジ | +0.057 |
Cargo | +0.056 |
Neg logit contributions | |
bent | -0.042 |
pleas | -0.041 |
Bac | -0.040 |
Hath | -0.040 |
Nib | -0.038 |
Token | old |
Token ID | 727 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
acent | +0.006 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
ンジ | -0.005 |
zie | -0.005 |
Cargo | -0.005 |
Token | Lif |
Token ID | 21073 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
lvl | +0.039 |
Shadow | +0.037 |
zie | +0.033 |
ンジ | +0.033 |
filename | +0.032 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.029 |
Bac | -0.028 |
Hath | -0.028 |
Nib | -0.027 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
bent | +0.022 |
pleas | +0.022 |
Bac | +0.022 |
Hath | +0.021 |
Nib | +0.021 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
ンジ | -0.004 |
zie | -0.003 |
Cargo | -0.003 |
Token | program |
Token ID | 1430 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
lvl | +0.271 |
Shadow | +0.260 |
zie | +0.233 |
ンジ | +0.233 |
filename | +0.225 |
Neg logit contributions | |
bent | -0.221 |
pleas | -0.218 |
Bac | -0.213 |
Hath | -0.209 |
relig | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.045 |
Shadow | -0.043 |
zie | -0.039 |
ンジ | -0.039 |
Cargo | -0.038 |
Token | Car |
Token ID | 1879 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
bent | +0.021 |
pleas | +0.021 |
Bac | +0.020 |
Hath | +0.020 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.032 |
zie | -0.029 |
ンジ | -0.028 |
filename | -0.028 |
Token | riers |
Token ID | 8910 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
lvl | +0.115 |
Shadow | +0.110 |
zie | +0.101 |
ンジ | +0.101 |
filename | +0.098 |
Neg logit contributions | |
bent | -0.063 |
pleas | -0.062 |
Bac | -0.061 |
Hath | -0.059 |
Nib | -0.056 |
Token | stating |
Token ID | 12316 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
lvl | +0.051 |
Shadow | +0.050 |
zie | +0.045 |
ンジ | +0.045 |
Cargo | +0.044 |
Neg logit contributions | |
bent | -0.027 |
pleas | -0.026 |
Bac | -0.026 |
Hath | -0.025 |
Nib | -0.024 |
Token | how |
Token ID | 703 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
relig | +0.006 |
Neg logit contributions | |
lvl | -0.012 |
Shadow | -0.012 |
zie | -0.011 |
ンジ | -0.011 |
filename | -0.010 |
Token | disgusting |
Token ID | 23374 |
Feature activation | +6.81e-03 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.019 |
Bac | +0.018 |
Hath | +0.018 |
relig | +0.017 |
Neg logit contributions | |
lvl | -0.030 |
Shadow | -0.029 |
zie | -0.026 |
ンジ | -0.026 |
filename | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
relig | +0.004 |
Neg logit contributions | |
lvl | -0.007 |
Shadow | -0.007 |
zie | -0.006 |
ンジ | -0.006 |
filename | -0.006 |
Token | abhor |
Token ID | 42934 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
relig | -0.002 |
Token | rent |
Token ID | 1156 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
bent | +0.081 |
pleas | +0.081 |
Bac | +0.080 |
Hath | +0.079 |
Nib | +0.078 |
Neg logit contributions | |
lvl | -0.029 |
Shadow | -0.027 |
zie | -0.021 |
ンジ | -0.020 |
Cargo | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
lvl | +0.323 |
Shadow | +0.313 |
zie | +0.287 |
ンジ | +0.284 |
Cargo | +0.278 |
Neg logit contributions | |
bent | -0.164 |
pleas | -0.161 |
Bac | -0.157 |
Hath | -0.152 |
relig | -0.147 |
Token | apost |
Token ID | 18584 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
relig | +0.007 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.012 |
Cargo | -0.011 |
Token | ate |
Token ID | 378 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
lvl | +0.091 |
Shadow | +0.088 |
zie | +0.081 |
ンジ | +0.080 |
filename | +0.079 |
Neg logit contributions | |
bent | -0.043 |
pleas | -0.043 |
Bac | -0.042 |
Hath | -0.041 |
Nib | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
bent | +0.057 |
pleas | +0.056 |
Bac | +0.054 |
Hath | +0.053 |
relig | +0.052 |
Neg logit contributions | |
lvl | -0.078 |
Shadow | -0.075 |
zie | -0.068 |
ンジ | -0.067 |
filename | -0.065 |
Token | is |
Token ID | 318 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.002 |
relig | +0.002 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.005 |
ンジ | -0.005 |
filename | -0.005 |
Token | next |
Token ID | 1306 |
Feature activation | +4.85e-03 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.020 |
zie | +0.018 |
ンジ | +0.018 |
filename | +0.018 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
zie | -0.004 |
ンジ | -0.004 |
Cargo | -0.004 |
Token | us |
Token ID | 514 |
Feature activation | +1.23e-04 |
Pos logit contributions | |
lvl | +0.077 |
Shadow | +0.075 |
zie | +0.068 |
ンジ | +0.067 |
Cargo | +0.065 |
Neg logit contributions | |
bent | -0.055 |
pleas | -0.054 |
Bac | -0.053 |
Hath | -0.051 |
Nib | -0.050 |
Token | ( |
Token ID | 357 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
bent | +0.000 |
pleas | +0.000 |
Bac | +0.000 |
Hath | +0.000 |
Nib | +0.000 |
Neg logit contributions | |
lvl | -0.000 |
Shadow | -0.000 |
zie | -0.000 |
ンジ | -0.000 |
filename | -0.000 |
Token | Call |
Token ID | 14134 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.021 |
Cargo | +0.020 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.016 |
Nib | -0.016 |
Token | ahan |
Token ID | 19210 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
lvl | +0.022 |
Shadow | +0.021 |
zie | +0.019 |
ンジ | +0.019 |
filename | +0.019 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.015 |
Hath | -0.014 |
Nib | -0.014 |
Token | Run |
Token ID | 5660 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
lvl | +0.289 |
Shadow | +0.278 |
zie | +0.252 |
ンジ | +0.250 |
filename | +0.244 |
Neg logit contributions | |
bent | -0.197 |
pleas | -0.193 |
Bac | -0.189 |
Hath | -0.185 |
Nib | -0.180 |
Token | ). |
Token ID | 737 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | Temperature |
Token ID | 34467 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
lvl | +0.039 |
Shadow | +0.037 |
zie | +0.034 |
ンジ | +0.034 |
filename | +0.033 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.023 |
Bac | -0.023 |
Hath | -0.023 |
Nib | -0.022 |
Token | crept |
Token ID | 47092 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.021 |
filename | +0.020 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.011 |
Token | up |
Token ID | 510 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
lvl | +0.050 |
Shadow | +0.048 |
zie | +0.044 |
ンジ | +0.044 |
filename | +0.043 |
Neg logit contributions | |
bent | -0.028 |
pleas | -0.028 |
Bac | -0.027 |
Hath | -0.026 |
Nib | -0.025 |
Token | � |
Token ID | 228 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.005 |
Hath | +0.005 |
relig | +0.005 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
Cargo | -0.004 |
Token | � |
Token ID | 138 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
lvl | +0.059 |
Shadow | +0.057 |
zie | +0.052 |
ンジ | +0.052 |
Cargo | +0.051 |
Neg logit contributions | |
bent | -0.036 |
pleas | -0.035 |
Bac | -0.034 |
Hath | -0.033 |
relig | -0.032 |
Token | � |
Token ID | 116 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.009 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.009 |
zie | -0.008 |
ンジ | -0.008 |
Cargo | -0.007 |
Token | ε |
Token ID | 30950 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
lvl | +0.050 |
Shadow | +0.048 |
zie | +0.044 |
ンジ | +0.044 |
Cargo | +0.043 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.029 |
Bac | -0.028 |
Hath | -0.027 |
Nib | -0.026 |
Token | � |
Token ID | 45495 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
lvl | +0.048 |
Shadow | +0.046 |
zie | +0.042 |
ンジ | +0.041 |
Cargo | +0.040 |
Neg logit contributions | |
bent | -0.031 |
pleas | -0.030 |
Bac | -0.030 |
Hath | -0.029 |
Nib | -0.028 |
Token | � |
Token ID | 115 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
bent | +0.042 |
pleas | +0.041 |
Bac | +0.041 |
Hath | +0.040 |
Nib | +0.039 |
Neg logit contributions | |
lvl | -0.044 |
Shadow | -0.042 |
zie | -0.037 |
ンジ | -0.037 |
Cargo | -0.036 |
Token | ρ |
Token ID | 33643 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
lvl | +0.313 |
Shadow | +0.303 |
zie | +0.277 |
ンジ | +0.275 |
Cargo | +0.268 |
Neg logit contributions | |
bent | -0.170 |
pleas | -0.167 |
Bac | -0.162 |
Hath | -0.158 |
Nib | -0.153 |
Token | ε |
Token ID | 30950 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.013 |
Neg logit contributions | |
lvl | -0.025 |
Shadow | -0.024 |
zie | -0.022 |
ンジ | -0.022 |
Cargo | -0.022 |
Token | ι |
Token ID | 29945 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
lvl | +0.045 |
Shadow | +0.043 |
zie | +0.039 |
ンジ | +0.039 |
Cargo | +0.038 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.028 |
Bac | -0.028 |
Hath | -0.027 |
Nib | -0.026 |
Token | � |
Token ID | 7377 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
Cargo | -0.004 |
Token | � |
Token ID | 112 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.003 |
ンジ | +0.003 |
Cargo | +0.003 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | Related |
Token ID | 9819 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.010 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.016 |
Shadow | -0.016 |
zie | -0.014 |
ンジ | -0.014 |
filename | -0.014 |
Token | : |
Token ID | 25 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | FCC |
Token ID | 15915 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
lvl | +0.035 |
Shadow | +0.034 |
zie | +0.031 |
ンジ | +0.030 |
filename | +0.030 |
Neg logit contributions | |
bent | -0.023 |
pleas | -0.023 |
Bac | -0.022 |
Hath | -0.022 |
Nib | -0.021 |
Token | expands |
Token ID | 27513 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
bent | +0.027 |
pleas | +0.027 |
Bac | +0.026 |
Hath | +0.026 |
Nib | +0.025 |
Neg logit contributions | |
lvl | -0.045 |
Shadow | -0.043 |
zie | -0.040 |
ンジ | -0.039 |
filename | -0.038 |
Token | Lif |
Token ID | 21073 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.004 |
zie | +0.004 |
ンジ | +0.004 |
filename | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.002 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.012 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
ンジ | -0.002 |
zie | -0.002 |
Cargo | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
lvl | +0.282 |
Shadow | +0.271 |
zie | +0.245 |
ンジ | +0.245 |
filename | +0.237 |
Neg logit contributions | |
bent | -0.202 |
pleas | -0.201 |
Bac | -0.194 |
Hath | -0.190 |
Nib | -0.185 |
Token | help |
Token ID | 1037 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.010 |
Bac | +0.009 |
Hath | +0.009 |
relig | +0.009 |
Neg logit contributions | |
lvl | -0.015 |
Shadow | -0.015 |
zie | -0.013 |
ンジ | -0.013 |
filename | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.019 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.028 |
Shadow | -0.027 |
zie | -0.024 |
ンジ | -0.024 |
filename | -0.024 |
Token | poor |
Token ID | 3595 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.007 |
Nib | -0.007 |
Token | pay |
Token ID | 1414 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
lvl | +0.043 |
Shadow | +0.042 |
zie | +0.038 |
ンジ | +0.038 |
Cargo | +0.037 |
Neg logit contributions | |
bent | -0.031 |
pleas | -0.030 |
Bac | -0.029 |
Hath | -0.029 |
Nib | -0.028 |
Token | would |
Token ID | 561 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
relig | -0.003 |
Token | accused |
Token ID | 5371 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
lvl | +0.022 |
Shadow | +0.021 |
zie | +0.019 |
ンジ | +0.019 |
filename | +0.019 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.012 |
Nib | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | obfusc |
Token ID | 44080 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.010 |
Hath | -0.010 |
relig | -0.010 |
Token | ating |
Token ID | 803 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
lvl | +0.059 |
Shadow | +0.057 |
zie | +0.052 |
ンジ | +0.052 |
Cargo | +0.051 |
Neg logit contributions | |
bent | -0.026 |
pleas | -0.026 |
Bac | -0.025 |
Hath | -0.024 |
Nib | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
bent | +0.128 |
pleas | +0.127 |
Bac | +0.122 |
Hath | +0.120 |
Nib | +0.117 |
Neg logit contributions | |
lvl | -0.194 |
Shadow | -0.188 |
zie | -0.170 |
ンジ | -0.169 |
filename | -0.164 |
Token | purely |
Token ID | 14177 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
relig | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
velt | -0.003 |
Token | political |
Token ID | 1964 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
relig | -0.010 |
Token | reasons |
Token ID | 3840 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
lvl | +0.019 |
Shadow | +0.018 |
zie | +0.017 |
ンジ | +0.017 |
Cargo | +0.016 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.007 |
Nib | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
bent | +0.050 |
pleas | +0.049 |
Bac | +0.048 |
Hath | +0.047 |
Nib | +0.045 |
Neg logit contributions | |
lvl | -0.089 |
Shadow | -0.086 |
zie | -0.078 |
ンジ | -0.078 |
Cargo | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.007 |
Shadow | -0.006 |
zie | -0.006 |
ンジ | -0.006 |
Cargo | -0.006 |
Token | Love |
Token ID | 5896 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.025 |
ンジ | +0.025 |
filename | +0.024 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.020 |
Nib | -0.019 |
Token | conveyed |
Token ID | 33348 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | through |
Token ID | 832 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.019 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.032 |
Shadow | -0.031 |
zie | -0.028 |
ンジ | -0.028 |
filename | -0.027 |
Token | lyr |
Token ID | 47188 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.017 |
Bac | +0.016 |
Hath | +0.016 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.023 |
Shadow | -0.023 |
zie | -0.020 |
ンジ | -0.020 |
filename | -0.020 |
Token | ical |
Token ID | 605 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.011 |
zie | -0.010 |
ンジ | -0.010 |
Cargo | -0.010 |
Token | themes |
Token ID | 13460 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
bent | +0.180 |
pleas | +0.177 |
Bac | +0.171 |
Hath | +0.168 |
relig | +0.164 |
Neg logit contributions | |
lvl | -0.238 |
Shadow | -0.229 |
zie | -0.207 |
ンジ | -0.206 |
filename | -0.199 |
Token | of |
Token ID | 286 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.015 |
Bac | +0.015 |
Hath | +0.014 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.030 |
Shadow | -0.029 |
zie | -0.026 |
ンジ | -0.026 |
Cargo | -0.025 |
Token | pregnancy |
Token ID | 10241 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.012 |
relig | +0.012 |
Neg logit contributions | |
lvl | -0.021 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
filename | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
lvl | +0.030 |
Shadow | +0.029 |
zie | +0.026 |
ンジ | +0.026 |
Cargo | +0.026 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.014 |
Hath | -0.014 |
Nib | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.019 |
relig | +0.018 |
Neg logit contributions | |
lvl | -0.032 |
Shadow | -0.031 |
zie | -0.028 |
ンジ | -0.028 |
filename | -0.027 |
Token | AS |
Token ID | 1921 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
bent | +0.031 |
pleas | +0.030 |
Bac | +0.030 |
Hath | +0.029 |
Nib | +0.028 |
Neg logit contributions | |
lvl | -0.041 |
Shadow | -0.040 |
zie | -0.036 |
ンジ | -0.036 |
velt | -0.035 |
Token | camera |
Token ID | 4676 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
lvl | +0.054 |
Shadow | +0.051 |
zie | +0.046 |
ンジ | +0.046 |
filename | +0.045 |
Neg logit contributions | |
bent | -0.042 |
pleas | -0.042 |
Bac | -0.041 |
Hath | -0.040 |
Nib | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
lvl | +0.046 |
Shadow | +0.045 |
zie | +0.041 |
ンジ | +0.041 |
filename | +0.039 |
Neg logit contributions | |
bent | -0.027 |
pleas | -0.026 |
Bac | -0.026 |
Hath | -0.025 |
Nib | -0.024 |
Token | rep |
Token ID | 1128 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
lvl | +0.018 |
Shadow | +0.018 |
zie | +0.016 |
ンジ | +0.016 |
filename | +0.016 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | rogram |
Token ID | 39529 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.011 |
zie | +0.009 |
ンジ | +0.009 |
Cargo | +0.009 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.012 |
Nib | -0.012 |
Token | med |
Token ID | 1150 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.005 |
ンジ | -0.005 |
Cargo | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
bent | +0.139 |
pleas | +0.136 |
Bac | +0.133 |
Hath | +0.129 |
Nib | +0.125 |
Neg logit contributions | |
lvl | -0.233 |
Shadow | -0.225 |
zie | -0.205 |
ンジ | -0.204 |
filename | -0.198 |
Token | substitute |
Token ID | 15373 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.021 |
filename | +0.020 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.016 |
Bac | -0.016 |
Hath | -0.016 |
Nib | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.021 |
filename | +0.020 |
Neg logit contributions | |
bent | -0.016 |
pleas | -0.016 |
Bac | -0.016 |
Hath | -0.015 |
Nib | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
lvl | +0.031 |
Shadow | +0.030 |
zie | +0.027 |
ンジ | +0.027 |
filename | +0.026 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.023 |
Hath | -0.023 |
Nib | -0.022 |
Token | star |
Token ID | 3491 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.008 |
ンジ | -0.008 |
filename | -0.008 |
Token | until |
Token ID | 1566 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.008 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | my |
Token ID | 616 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
bent | +0.054 |
pleas | +0.053 |
Bac | +0.052 |
Hath | +0.051 |
Nib | +0.049 |
Neg logit contributions | |
lvl | -0.079 |
Shadow | -0.076 |
zie | -0.069 |
ンジ | -0.068 |
filename | -0.066 |
Token | dad |
Token ID | 9955 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
ンジ | +0.015 |
zie | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
Nib | -0.010 |
Token | cou |
Token ID | 2284 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.007 |
zie | +0.006 |
ンジ | +0.006 |
Cargo | +0.006 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | g |
Token ID | 70 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
lvl | +0.004 |
Shadow | +0.003 |
ンジ | +0.003 |
zie | +0.003 |
Cargo | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | hed |
Token ID | 704 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
bent | +0.165 |
pleas | +0.162 |
Bac | +0.158 |
Hath | +0.154 |
Nib | +0.149 |
Neg logit contributions | |
lvl | -0.288 |
Shadow | -0.278 |
zie | -0.253 |
ンジ | -0.251 |
Cargo | -0.245 |
Token | break |
Token ID | 2270 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.005 |
Nib | +0.005 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
filename | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.013 |
zie | +0.012 |
ンジ | +0.012 |
filename | +0.011 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.009 |
Token | tension |
Token ID | 12097 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
ンジ | +0.005 |
zie | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
Nib | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
lvl | +0.062 |
Shadow | +0.060 |
zie | +0.055 |
ンジ | +0.054 |
Cargo | +0.053 |
Neg logit contributions | |
bent | -0.037 |
pleas | -0.037 |
Bac | -0.036 |
Hath | -0.035 |
Nib | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
lvl | +0.114 |
Shadow | +0.111 |
zie | +0.102 |
ンジ | +0.101 |
Cargo | +0.099 |
Neg logit contributions | |
bent | -0.055 |
pleas | -0.054 |
Bac | -0.053 |
Hath | -0.051 |
relig | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
bent | +0.040 |
pleas | +0.039 |
Bac | +0.038 |
Hath | +0.037 |
Nib | +0.036 |
Neg logit contributions | |
lvl | -0.052 |
Shadow | -0.050 |
zie | -0.045 |
ンジ | -0.045 |
filename | -0.044 |
Token | crazy |
Token ID | 7165 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
bent | +0.036 |
pleas | +0.036 |
Bac | +0.035 |
Hath | +0.034 |
Nib | +0.033 |
Neg logit contributions | |
lvl | -0.049 |
Shadow | -0.047 |
zie | -0.042 |
ンジ | -0.042 |
filename | -0.041 |
Token | ac |
Token ID | 936 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.004 |
Nib | +0.004 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.006 |
ンジ | -0.006 |
filename | -0.005 |
Token | robat |
Token ID | 40655 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
bent | +0.042 |
pleas | +0.041 |
Bac | +0.041 |
Hath | +0.040 |
Nib | +0.039 |
Neg logit contributions | |
lvl | -0.041 |
Shadow | -0.040 |
zie | -0.035 |
ンジ | -0.035 |
Cargo | -0.034 |
Token | ics |
Token ID | 873 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.031 |
zie | +0.029 |
ンジ | +0.028 |
Cargo | +0.028 |
Neg logit contributions | |
bent | -0.016 |
pleas | -0.016 |
Bac | -0.016 |
Hath | -0.015 |
Nib | -0.015 |
Token | – |
Token ID | 784 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
bent | +0.121 |
pleas | +0.119 |
Bac | +0.116 |
Hath | +0.113 |
Nib | +0.108 |
Neg logit contributions | |
lvl | -0.241 |
Shadow | -0.233 |
zie | -0.213 |
ンジ | -0.212 |
filename | -0.207 |
Token | and |
Token ID | 290 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
bent | +0.029 |
pleas | +0.028 |
Bac | +0.027 |
Hath | +0.027 |
Nib | +0.026 |
Neg logit contributions | |
lvl | -0.045 |
Shadow | -0.044 |
zie | -0.040 |
ンジ | -0.039 |
filename | -0.038 |
Token | you |
Token ID | 345 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
bent | +0.033 |
pleas | +0.032 |
Bac | +0.032 |
Hath | +0.031 |
Nib | +0.030 |
Neg logit contributions | |
lvl | -0.051 |
Shadow | -0.049 |
ンジ | -0.044 |
zie | -0.044 |
filename | -0.043 |
Token | get |
Token ID | 651 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
bent | +0.021 |
pleas | +0.020 |
Bac | +0.020 |
Hath | +0.019 |
Nib | +0.019 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
ンジ | -0.030 |
zie | -0.030 |
filename | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.023 |
Bac | +0.023 |
Hath | +0.022 |
Nib | +0.021 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.032 |
zie | -0.029 |
ンジ | -0.029 |
filename | -0.028 |
Token | Special |
Token ID | 6093 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.025 |
Bac | +0.024 |
Hath | +0.024 |
Nib | +0.023 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
filename | -0.026 |
Token | Concert |
Token ID | 39220 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.007 |
zie | +0.006 |
ンジ | +0.006 |
filename | +0.006 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
bent | +0.035 |
pleas | +0.035 |
Bac | +0.034 |
Hath | +0.033 |
Nib | +0.032 |
Neg logit contributions | |
lvl | -0.060 |
Shadow | -0.058 |
zie | -0.053 |
ンジ | -0.052 |
filename | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
bent | +0.052 |
pleas | +0.051 |
Bac | +0.049 |
Hath | +0.048 |
Nib | +0.046 |
Neg logit contributions | |
lvl | -0.103 |
Shadow | -0.100 |
zie | -0.091 |
ンジ | -0.091 |
Cargo | -0.089 |
Token | new |
Token ID | 649 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.026 |
Hath | +0.025 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.038 |
Shadow | -0.036 |
zie | -0.033 |
ンジ | -0.033 |
filename | -0.032 |
Token | songs |
Token ID | 7259 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
ンジ | -0.009 |
zie | -0.009 |
filename | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.023 |
filename | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.006 |
zie | +0.006 |
ンジ | +0.006 |
Cargo | +0.006 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.004 |
Nib | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.011 |
zie | +0.010 |
ンジ | +0.010 |
filename | +0.010 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.007 |
Token | fourth |
Token ID | 5544 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.016 |
Shadow | -0.015 |
zie | -0.014 |
ンジ | -0.014 |
Cargo | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
lvl | +0.043 |
Shadow | +0.041 |
zie | +0.037 |
ンジ | +0.036 |
Cargo | +0.035 |
Neg logit contributions | |
bent | -0.032 |
pleas | -0.031 |
Bac | -0.031 |
Hath | -0.030 |
Nib | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
lvl | +0.063 |
Shadow | +0.061 |
zie | +0.056 |
ンジ | +0.055 |
filename | +0.054 |
Neg logit contributions | |
bent | -0.034 |
pleas | -0.033 |
Bac | -0.033 |
Hath | -0.032 |
Nib | -0.031 |
Token | original |
Token ID | 2656 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
relig | +0.004 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.005 |
ンジ | -0.005 |
zie | -0.005 |
velt | -0.005 |
Token | screenplay |
Token ID | 39769 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.002 |
ンジ | +0.002 |
velt | +0.002 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
relig | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.024 |
ンジ | +0.024 |
velt | +0.023 |
Neg logit contributions | |
bent | -0.018 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.017 |
relig | -0.016 |
Token | Of |
Token ID | 3226 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.007 |
zie | +0.006 |
ンジ | +0.006 |
velt | +0.006 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.004 |
Token | course |
Token ID | 1781 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.025 |
Bac | +0.025 |
Hath | +0.024 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.030 |
Shadow | -0.029 |
zie | -0.026 |
ンジ | -0.026 |
Cargo | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.042 |
Shadow | -0.041 |
zie | -0.038 |
ンジ | -0.037 |
Cargo | -0.037 |
Token | it |
Token ID | 340 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.014 |
zie | +0.013 |
ンジ | +0.013 |
velt | +0.013 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.009 |
Token | might |
Token ID | 1244 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | seem |
Token ID | 1283 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
zie | +0.007 |
ンジ | +0.007 |
velt | +0.007 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | way |
Token ID | 835 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
lvl | +0.035 |
Shadow | +0.034 |
zie | +0.031 |
ンジ | +0.031 |
filename | +0.030 |
Neg logit contributions | |
bent | -0.018 |
pleas | -0.017 |
Bac | -0.017 |
Hath | -0.016 |
relig | -0.016 |
Token | ested |
Token ID | 7287 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
bent | +0.045 |
pleas | +0.045 |
Bac | +0.044 |
Hath | +0.043 |
Nib | +0.041 |
Neg logit contributions | |
lvl | -0.067 |
Shadow | -0.065 |
zie | -0.059 |
ンジ | -0.058 |
Cargo | -0.057 |
Token | it |
Token ID | 340 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
bent | +0.027 |
pleas | +0.027 |
Bac | +0.026 |
Hath | +0.026 |
Nib | +0.025 |
Neg logit contributions | |
lvl | -0.039 |
Shadow | -0.038 |
zie | -0.034 |
ンジ | -0.034 |
filename | -0.033 |
Token | yet |
Token ID | 1865 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.040 |
Shadow | -0.038 |
ンジ | -0.035 |
zie | -0.035 |
filename | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.024 |
ンジ | +0.023 |
Cargo | +0.023 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.013 |
Nib | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
bent | +0.019 |
pleas | +0.019 |
Bac | +0.018 |
Hath | +0.018 |
Nib | +0.017 |
Neg logit contributions | |
lvl | -0.034 |
Shadow | -0.033 |
zie | -0.030 |
ンジ | -0.030 |
filename | -0.029 |
Token | enough |
Token ID | 1576 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.019 |
Shadow | -0.019 |
zie | -0.017 |
ンジ | -0.017 |
filename | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
bent | +0.027 |
pleas | +0.026 |
Bac | +0.026 |
Hath | +0.025 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.039 |
Shadow | -0.038 |
zie | -0.034 |
ンジ | -0.034 |
filename | -0.033 |
Token | sum |
Token ID | 2160 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
ンジ | +0.001 |
zie | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
bent | +0.055 |
pleas | +0.054 |
Bac | +0.053 |
Hath | +0.051 |
Nib | +0.050 |
Neg logit contributions | |
lvl | -0.088 |
Shadow | -0.085 |
zie | -0.077 |
ンジ | -0.077 |
filename | -0.075 |
Token | up |
Token ID | 510 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
bent | +0.018 |
pleas | +0.018 |
Bac | +0.017 |
Hath | +0.017 |
Nib | +0.016 |
Neg logit contributions | |
lvl | -0.030 |
Shadow | -0.029 |
zie | -0.026 |
ンジ | -0.026 |
filename | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
ンジ | +0.002 |
zie | +0.002 |
velt | +0.002 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | Ram |
Token ID | 7431 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.026 |
ンジ | +0.025 |
Cargo | +0.025 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.020 |
relig | -0.019 |
Token | on |
Token ID | 261 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
bent | +0.023 |
pleas | +0.022 |
Bac | +0.022 |
Hath | +0.021 |
relig | +0.021 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.026 |
Cargo | -0.026 |
Token | Guerrero |
Token ID | 49002 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
Cargo | +0.017 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.013 |
Bac | -0.013 |
Hath | -0.012 |
relig | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.014 |
Hath | +0.013 |
Nib | +0.013 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.023 |
filename | -0.022 |
Token | 22 |
Token ID | 2534 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.041 |
Shadow | -0.039 |
zie | -0.036 |
ンジ | -0.036 |
filename | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.026 |
Shadow | -0.025 |
zie | -0.023 |
ンジ | -0.022 |
Cargo | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.017 |
zie | -0.016 |
ンジ | -0.016 |
Cargo | -0.015 |
Token | Gu |
Token ID | 8205 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | er |
Token ID | 263 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.011 |
ンジ | +0.010 |
zie | +0.010 |
Cargo | +0.010 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | rero |
Token ID | 34785 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
bent | +0.061 |
pleas | +0.060 |
Bac | +0.059 |
Hath | +0.058 |
relig | +0.056 |
Neg logit contributions | |
lvl | -0.065 |
Shadow | -0.063 |
ンジ | -0.055 |
zie | -0.055 |
Cargo | -0.053 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
bent | +0.034 |
pleas | +0.033 |
Bac | +0.032 |
Hath | +0.032 |
Nib | +0.031 |
Neg logit contributions | |
lvl | -0.068 |
Shadow | -0.065 |
zie | -0.060 |
ンジ | -0.059 |
Cargo | -0.058 |
Token | time |
Token ID | 640 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
bent | +0.009 |
pleas | +0.009 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.013 |
zie | -0.012 |
ンジ | -0.011 |
filename | -0.011 |
Token | because |
Token ID | 780 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.007 |
Shadow | -0.007 |
zie | -0.006 |
ンジ | -0.006 |
filename | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.019 |
relig | +0.018 |
Neg logit contributions | |
lvl | -0.035 |
Shadow | -0.034 |
zie | -0.031 |
ンジ | -0.031 |
Cargo | -0.030 |
Token | � |
Token ID | 564 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.012 |
zie | +0.011 |
ンジ | +0.011 |
filename | +0.011 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.008 |
Nib | -0.008 |
Token | � |
Token ID | 250 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
bent | +0.014 |
pleas | +0.014 |
Bac | +0.013 |
Hath | +0.013 |
relig | +0.013 |
Neg logit contributions | |
lvl | -0.015 |
Shadow | -0.014 |
zie | -0.013 |
ンジ | -0.013 |
filename | -0.012 |
Token | a |
Token ID | 64 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
bent | +0.026 |
pleas | +0.026 |
Bac | +0.025 |
Hath | +0.025 |
Nib | +0.024 |
Neg logit contributions | |
lvl | -0.036 |
Shadow | -0.035 |
zie | -0.032 |
ンジ | -0.032 |
velt | -0.031 |
Token | different |
Token ID | 1180 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.019 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.024 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
velt | -0.020 |
Token | issue |
Token ID | 2071 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
bent | +0.029 |
pleas | +0.028 |
Bac | +0.028 |
Hath | +0.027 |
Nib | +0.026 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.032 |
ンジ | -0.028 |
zie | -0.028 |
velt | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.020 |
Bac | +0.019 |
Hath | +0.019 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.037 |
Shadow | -0.036 |
zie | -0.033 |
ンジ | -0.033 |
Cargo | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
bent | +0.037 |
pleas | +0.037 |
Bac | +0.036 |
Hath | +0.035 |
Nib | +0.034 |
Neg logit contributions | |
lvl | -0.048 |
Shadow | -0.046 |
zie | -0.041 |
ンジ | -0.041 |
filename | -0.040 |
Token | booster |
Token ID | 30430 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
bent | +0.010 |
pleas | +0.009 |
Bac | +0.009 |
Hath | +0.009 |
Nib | +0.009 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
velt | -0.009 |
Token | release |
Token ID | 2650 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
zie | +0.015 |
ンジ | +0.015 |
Cargo | +0.014 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.009 |
Nib | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
lvl | +0.035 |
Shadow | +0.034 |
zie | +0.031 |
ンジ | +0.030 |
filename | +0.030 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.019 |
Bac | -0.018 |
Hath | -0.018 |
Nib | -0.017 |
Token | Bow |
Token ID | 9740 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
lvl | +0.042 |
Shadow | +0.040 |
zie | +0.036 |
ンジ | +0.036 |
velt | +0.035 |
Neg logit contributions | |
bent | -0.030 |
pleas | -0.030 |
Bac | -0.029 |
Hath | -0.028 |
Nib | -0.028 |
Token | e |
Token ID | 68 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Hath | +0.013 |
Bac | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.023 |
Shadow | -0.022 |
ンジ | -0.020 |
zie | -0.020 |
velt | -0.020 |
Token | Ber |
Token ID | 4312 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
relig | +0.002 |
Neg logit contributions | |
lvl | -0.009 |
Shadow | -0.009 |
zie | -0.008 |
ンジ | -0.008 |
Cargo | -0.008 |
Token | gd |
Token ID | 21287 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.014 |
zie | +0.012 |
ンジ | +0.012 |
Cargo | +0.012 |
Neg logit contributions | |
bent | -0.019 |
pleas | -0.019 |
Bac | -0.019 |
Hath | -0.019 |
Nib | -0.018 |
Token | ahl |
Token ID | 15668 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
lvl | +0.098 |
Shadow | +0.093 |
ンジ | +0.084 |
zie | +0.083 |
Cargo | +0.080 |
Neg logit contributions | |
bent | -0.088 |
pleas | -0.087 |
Bac | -0.084 |
Hath | -0.084 |
relig | -0.081 |
Token | had |
Token ID | 550 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
lvl | +0.077 |
Shadow | +0.074 |
zie | +0.067 |
ンジ | +0.067 |
Cargo | +0.065 |
Neg logit contributions | |
bent | -0.045 |
pleas | -0.045 |
Bac | -0.043 |
Hath | -0.043 |
Nib | -0.041 |
Token | more |
Token ID | 517 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.003 |
Shadow | -0.003 |
zie | -0.003 |
ンジ | -0.003 |
Cargo | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.014 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.012 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.008 |
Nib | -0.008 |
Token | do |
Token ID | 466 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
Cargo | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | reductions |
Token ID | 20691 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
lvl | +0.029 |
Shadow | +0.028 |
zie | +0.025 |
ンジ | +0.025 |
Cargo | +0.024 |
Neg logit contributions | |
bent | -0.022 |
pleas | -0.022 |
Bac | -0.021 |
Hath | -0.021 |
Nib | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.012 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.024 |
Shadow | -0.023 |
zie | -0.021 |
ンジ | -0.021 |
Cargo | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
lvl | +0.005 |
Shadow | +0.005 |
zie | +0.004 |
ンジ | +0.004 |
filename | +0.004 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.014 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.012 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
Nib | -0.010 |
Token | As |
Token ID | 1722 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
Cargo | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | physicians |
Token ID | 17206 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
lvl | +0.007 |
Shadow | +0.006 |
zie | +0.006 |
ンジ | +0.006 |
filename | +0.006 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | today |
Token ID | 1909 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.003 |
ンジ | +0.003 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | execute |
Token ID | 12260 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
bent | +0.004 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
relig | +0.003 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.006 |
ンジ | -0.005 |
filename | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.003 |
ンジ | +0.003 |
filename | +0.003 |
Neg logit contributions | |
bent | -0.002 |
pleas | -0.002 |
Bac | -0.002 |
Hath | -0.002 |
Nib | -0.002 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
lvl | +0.014 |
Shadow | +0.014 |
zie | +0.012 |
ンジ | +0.012 |
filename | +0.012 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
relig | -0.010 |
Token | shift |
Token ID | 6482 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
filename | +0.009 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
relig | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
lvl | +0.008 |
Shadow | +0.008 |
ンジ | +0.007 |
zie | +0.007 |
filename | +0.007 |
Neg logit contributions | |
bent | -0.005 |
pleas | -0.005 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | song |
Token ID | 3496 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
lvl | +0.002 |
Shadow | +0.002 |
zie | +0.002 |
ンジ | +0.002 |
filename | +0.002 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
relig | -0.001 |
Token | about |
Token ID | 546 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
lvl | +0.032 |
Shadow | +0.031 |
zie | +0.028 |
ンジ | +0.028 |
Cargo | +0.028 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.014 |
Hath | -0.014 |
relig | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
zie | +0.017 |
ンジ | +0.017 |
filename | +0.017 |
Neg logit contributions | |
bent | -0.013 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.012 |
Nib | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.006 |
Shadow | -0.006 |
zie | -0.005 |
ンジ | -0.005 |
Cargo | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.002 |
ンジ | -0.002 |
filename | -0.002 |
Token | � |
Token ID | 251 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
lvl | +0.012 |
Shadow | +0.012 |
zie | +0.011 |
ンジ | +0.010 |
Cargo | +0.010 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.009 |
Token | Violent |
Token ID | 35615 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.010 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.019 |
Shadow | -0.018 |
zie | -0.017 |
ンジ | -0.017 |
Cargo | -0.016 |
Token | J |
Token ID | 449 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
lvl | +0.042 |
Shadow | +0.040 |
zie | +0.037 |
ンジ | +0.036 |
Cargo | +0.036 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.024 |
Hath | -0.023 |
relig | -0.022 |
Token | explains |
Token ID | 6688 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
lvl | +0.018 |
Shadow | +0.017 |
zie | +0.016 |
ンジ | +0.016 |
Cargo | +0.015 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.011 |
Nib | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
bent | +0.006 |
pleas | +0.006 |
Bac | +0.006 |
Hath | +0.006 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.011 |
zie | -0.010 |
ンジ | -0.010 |
Cargo | -0.010 |
Token | � |
Token ID | 247 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.005 |
Bac | +0.005 |
Hath | +0.004 |
relig | +0.004 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
zie | -0.004 |
ンジ | -0.004 |
Cargo | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | -2.16e-04 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.009 |
Token | actually |
Token ID | 1682 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
lvl | +0.000 |
Shadow | +0.000 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
Nib | -0.000 |
Token | another |
Token ID | 1194 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.010 |
pleas | -0.010 |
Bac | -0.010 |
Hath | -0.010 |
Nib | -0.010 |
Token | � |
Token ID | 564 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
lvl | +0.019 |
Shadow | +0.018 |
zie | +0.017 |
ンジ | +0.016 |
filename | +0.016 |
Neg logit contributions | |
bent | -0.016 |
pleas | -0.016 |
Bac | -0.015 |
Hath | -0.015 |
relig | -0.015 |
Token | � |
Token ID | 250 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
lvl | +0.011 |
Shadow | +0.010 |
zie | +0.009 |
ンジ | +0.009 |
Cargo | +0.009 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.014 |
Bac | -0.014 |
Hath | -0.014 |
Nib | -0.014 |
Token | shock |
Token ID | 39563 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
relig | +0.006 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.009 |
zie | -0.009 |
ンジ | -0.008 |
Cargo | -0.008 |
Token | doctrine |
Token ID | 13115 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
lvl | +0.058 |
Shadow | +0.056 |
zie | +0.051 |
ンジ | +0.050 |
filename | +0.049 |
Neg logit contributions | |
bent | -0.039 |
pleas | -0.039 |
Bac | -0.038 |
Hath | -0.037 |
Nib | -0.036 |
Token | � |
Token ID | 447 |
Feature activation | -7.15e-04 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
relig | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
Cargo | -0.001 |
Token | � |
Token ID | 251 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.000 |
zie | +0.000 |
ンジ | +0.000 |
filename | +0.000 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | experiment |
Token ID | 6306 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
lvl | +0.015 |
Shadow | +0.015 |
zie | +0.013 |
ンジ | +0.013 |
Cargo | +0.013 |
Neg logit contributions | |
bent | -0.008 |
pleas | -0.008 |
Bac | -0.008 |
Hath | -0.008 |
relig | -0.008 |
Token | í |
Token ID | 8836 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
bent | +0.001 |
pleas | +0.001 |
Bac | +0.001 |
Hath | +0.001 |
Nib | +0.001 |
Neg logit contributions | |
lvl | -0.001 |
Shadow | -0.001 |
zie | -0.001 |
ンジ | -0.001 |
Cargo | -0.001 |
Token | k |
Token ID | 74 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
lvl | +0.040 |
Shadow | +0.039 |
ンジ | +0.035 |
zie | +0.035 |
filename | +0.033 |
Neg logit contributions | |
bent | -0.036 |
pleas | -0.035 |
Bac | -0.035 |
Hath | -0.034 |
Nib | -0.033 |
Token | 41 |
Token ID | 6073 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
bent | +0.028 |
pleas | +0.028 |
Bac | +0.027 |
Hath | +0.027 |
Nib | +0.026 |
Neg logit contributions | |
lvl | -0.041 |
Shadow | -0.040 |
ンジ | -0.036 |
zie | -0.035 |
filename | -0.035 |
Token | ), |
Token ID | 828 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
lvl | +0.010 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
Cargo | +0.008 |
Neg logit contributions | |
bent | -0.007 |
pleas | -0.007 |
Bac | -0.007 |
Hath | -0.007 |
Nib | -0.006 |
Token | Kr |
Token ID | 13685 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.004 |
pleas | -0.004 |
Bac | -0.004 |
Hath | -0.004 |
Nib | -0.004 |
Token | ?, |
Token ID | 21747 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
lvl | +0.037 |
Shadow | +0.035 |
ンジ | +0.032 |
zie | +0.031 |
Cargo | +0.030 |
Neg logit contributions | |
bent | -0.034 |
pleas | -0.033 |
Bac | -0.033 |
Hath | -0.032 |
Nib | -0.031 |
Token | Kur |
Token ID | 18132 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
lvl | +0.016 |
Shadow | +0.016 |
zie | +0.014 |
ンジ | +0.014 |
filename | +0.014 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
Nib | -0.010 |
Token | ? |
Token ID | 30 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
lvl | +0.025 |
Shadow | +0.024 |
ンジ | +0.021 |
zie | +0.021 |
Cargo | +0.021 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.020 |
Nib | -0.019 |
Token | í |
Token ID | 8836 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
lvl | +0.039 |
Shadow | +0.038 |
zie | +0.034 |
ンジ | +0.033 |
filename | +0.032 |
Neg logit contributions | |
bent | -0.031 |
pleas | -0.031 |
Bac | -0.030 |
Hath | -0.029 |
relig | -0.029 |
Token | k |
Token ID | 74 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
lvl | +0.042 |
Shadow | +0.040 |
zie | +0.036 |
ンジ | +0.036 |
Cargo | +0.035 |
Neg logit contributions | |
bent | -0.028 |
pleas | -0.027 |
Bac | -0.027 |
Hath | -0.026 |
Nib | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
bent | +0.017 |
pleas | +0.016 |
Bac | +0.016 |
Hath | +0.016 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.031 |
Shadow | -0.030 |
zie | -0.027 |
ンジ | -0.027 |
Cargo | -0.027 |
Token | Ring |
Token ID | 12569 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.002 |
Shadow | -0.002 |
zie | -0.001 |
ンジ | -0.001 |
filename | -0.001 |
Token | – |
Token ID | 784 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
lvl | +0.026 |
Shadow | +0.025 |
zie | +0.023 |
ンジ | +0.023 |
Cargo | +0.022 |
Neg logit contributions | |
bent | -0.016 |
pleas | -0.016 |
Bac | -0.016 |
Hath | -0.015 |
Nib | -0.015 |
Token | bet |
Token ID | 731 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
bent | +0.011 |
pleas | +0.011 |
Bac | +0.011 |
Hath | +0.010 |
Nib | +0.010 |
Neg logit contributions | |
lvl | -0.021 |
Shadow | -0.021 |
zie | -0.019 |
ンジ | -0.019 |
filename | -0.018 |
Token | rays |
Token ID | 20477 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
bent | +0.041 |
pleas | +0.040 |
Bac | +0.040 |
Hath | +0.039 |
Nib | +0.038 |
Neg logit contributions | |
lvl | -0.022 |
Shadow | -0.020 |
zie | -0.017 |
ンジ | -0.017 |
Cargo | -0.016 |
Token | Fro |
Token ID | 9734 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
lvl | +0.062 |
Shadow | +0.060 |
zie | +0.055 |
ンジ | +0.054 |
filename | +0.053 |
Neg logit contributions | |
bent | -0.038 |
pleas | -0.037 |
Bac | -0.037 |
Hath | -0.036 |
Nib | -0.035 |
Token | do |
Token ID | 4598 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
lvl | +0.020 |
Shadow | +0.019 |
ンジ | +0.017 |
zie | +0.017 |
Cargo | +0.016 |
Neg logit contributions | |
bent | -0.021 |
pleas | -0.021 |
Bac | -0.020 |
Hath | -0.020 |
Nib | -0.019 |
Token | by |
Token ID | 416 |
Feature activation | -9.09e-03 |
Pos logit contributions | |
lvl | +0.176 |
Shadow | +0.170 |
zie | +0.156 |
ンジ | +0.154 |
Cargo | +0.151 |
Neg logit contributions | |
bent | -0.092 |
pleas | -0.091 |
Bac | -0.088 |
Hath | -0.086 |
Nib | -0.083 |
Token | leading |
Token ID | 3756 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
filename | +0.008 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.006 |
Hath | -0.006 |
Nib | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.006 |
Neg logit contributions | |
lvl | -0.010 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
filename | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
bent | +0.032 |
pleas | +0.032 |
Bac | +0.031 |
Hath | +0.030 |
Nib | +0.029 |
Neg logit contributions | |
lvl | -0.050 |
Shadow | -0.048 |
zie | -0.044 |
ンジ | -0.044 |
filename | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
bent | +0.028 |
pleas | +0.027 |
Bac | +0.027 |
Hath | +0.026 |
Nib | +0.025 |
Neg logit contributions | |
lvl | -0.038 |
Shadow | -0.037 |
zie | -0.034 |
ンジ | -0.033 |
filename | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
bent | +0.003 |
pleas | +0.003 |
Bac | +0.003 |
Hath | +0.003 |
Nib | +0.003 |
Neg logit contributions | |
lvl | -0.005 |
Shadow | -0.005 |
zie | -0.004 |
ンジ | -0.004 |
velt | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
bent | +0.013 |
pleas | +0.013 |
Bac | +0.013 |
Hath | +0.013 |
Nib | +0.012 |
Neg logit contributions | |
lvl | -0.018 |
Shadow | -0.017 |
zie | -0.016 |
ンジ | -0.015 |
Cargo | -0.015 |
Token | � |
Token ID | 447 |
Feature activation | -7.07e-04 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.012 |
Shadow | -0.011 |
zie | -0.010 |
ンジ | -0.010 |
Cargo | -0.010 |
Token | � |
Token ID | 250 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.001 |
pleas | -0.001 |
Bac | -0.001 |
Hath | -0.001 |
Nib | -0.001 |
Token | Tel |
Token ID | 33317 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.011 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.017 |
Shadow | -0.017 |
zie | -0.015 |
ンジ | -0.015 |
Cargo | -0.015 |
Token | stra |
Token ID | 12044 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
lvl | +0.013 |
Shadow | +0.012 |
ンジ | +0.008 |
zie | +0.008 |
velt | +0.007 |
Neg logit contributions | |
bent | -0.052 |
pleas | -0.052 |
Bac | -0.051 |
Hath | -0.050 |
relig | -0.049 |
Token | is |
Token ID | 318 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
lvl | +0.211 |
Shadow | +0.203 |
zie | +0.186 |
ンジ | +0.185 |
filename | +0.180 |
Neg logit contributions | |
bent | -0.116 |
pleas | -0.114 |
Bac | -0.111 |
Hath | -0.108 |
Nib | -0.104 |
Token | working |
Token ID | 1762 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
lvl | +0.021 |
Shadow | +0.021 |
zie | +0.019 |
ンジ | +0.019 |
velt | +0.018 |
Neg logit contributions | |
bent | -0.012 |
pleas | -0.012 |
Bac | -0.012 |
Hath | -0.011 |
Nib | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -4.98e-04 |
Pos logit contributions | |
lvl | +0.028 |
Shadow | +0.027 |
zie | +0.025 |
ンジ | +0.025 |
filename | +0.024 |
Neg logit contributions | |
bent | -0.015 |
pleas | -0.015 |
Bac | -0.014 |
Hath | -0.014 |
Nib | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
lvl | +0.000 |
Shadow | +0.000 |
zie | +0.000 |
ンジ | +0.000 |
velt | +0.000 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
Nib | -0.000 |
Token | Australian |
Token ID | 6638 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
lvl | +0.017 |
Shadow | +0.016 |
zie | +0.015 |
ンジ | +0.014 |
velt | +0.014 |
Neg logit contributions | |
bent | -0.009 |
pleas | -0.009 |
Bac | -0.009 |
Hath | -0.009 |
Nib | -0.008 |
Token | attacked |
Token ID | 7384 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
bent | +0.020 |
pleas | +0.019 |
Bac | +0.019 |
Hath | +0.018 |
Nib | +0.018 |
Neg logit contributions | |
lvl | -0.032 |
Shadow | -0.031 |
zie | -0.028 |
ンジ | -0.028 |
filename | -0.028 |
Token | by |
Token ID | 416 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
bent | +0.012 |
pleas | +0.012 |
Bac | +0.012 |
Hath | +0.011 |
Nib | +0.011 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.019 |
zie | -0.018 |
ンジ | -0.017 |
Cargo | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
lvl | +0.027 |
Shadow | +0.026 |
zie | +0.023 |
ンジ | +0.023 |
velt | +0.022 |
Neg logit contributions | |
bent | -0.018 |
pleas | -0.018 |
Bac | -0.017 |
Hath | -0.017 |
Nib | -0.016 |
Token | cursed |
Token ID | 25155 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.015 |
Bac | +0.015 |
Hath | +0.015 |
Nib | +0.014 |
Neg logit contributions | |
lvl | -0.019 |
Shadow | -0.018 |
zie | -0.016 |
ンジ | -0.016 |
filename | -0.016 |
Token | nut |
Token ID | 6701 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
bent | +0.016 |
pleas | +0.016 |
Bac | +0.015 |
Hath | +0.015 |
Nib | +0.015 |
Neg logit contributions | |
lvl | -0.020 |
Shadow | -0.019 |
zie | -0.017 |
ンジ | -0.017 |
filename | -0.017 |
Token | cr |
Token ID | 6098 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
bent | +0.039 |
pleas | +0.039 |
Bac | +0.038 |
Hath | +0.037 |
Nib | +0.036 |
Neg logit contributions | |
lvl | -0.047 |
Shadow | -0.045 |
zie | -0.040 |
ンジ | -0.040 |
Cargo | -0.039 |
Token | acker |
Token ID | 10735 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
lvl | +0.097 |
Shadow | +0.091 |
zie | +0.075 |
ンジ | +0.074 |
Cargo | +0.070 |
Neg logit contributions | |
bent | -0.194 |
pleas | -0.192 |
Bac | -0.189 |
Hath | -0.187 |
Nib | -0.183 |
Token | doll |
Token ID | 3654 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
lvl | +0.054 |
Shadow | +0.052 |
zie | +0.048 |
ンジ | +0.047 |
Cargo | +0.046 |
Neg logit contributions | |
bent | -0.033 |
pleas | -0.032 |
Bac | -0.032 |
Hath | -0.031 |
Nib | -0.030 |
Token | named |
Token ID | 3706 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
bent | +0.025 |
pleas | +0.024 |
Bac | +0.024 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.042 |
Shadow | -0.041 |
zie | -0.037 |
ンジ | -0.037 |
Cargo | -0.036 |
Token | Colonel |
Token ID | 21636 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
bent | +0.024 |
pleas | +0.024 |
Bac | +0.023 |
Hath | +0.023 |
Nib | +0.022 |
Neg logit contributions | |
lvl | -0.033 |
Shadow | -0.032 |
zie | -0.029 |
ンジ | -0.029 |
Cargo | -0.028 |
Token | Nut |
Token ID | 11959 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
lvl | +0.023 |
Shadow | +0.022 |
zie | +0.020 |
ンジ | +0.020 |
Cargo | +0.019 |
Neg logit contributions | |
bent | -0.017 |
pleas | -0.017 |
Bac | -0.016 |
Hath | -0.016 |
relig | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
Cargo | -0.009 |
Token | According |
Token ID | 4821 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
bent | +0.008 |
pleas | +0.008 |
Bac | +0.008 |
Hath | +0.008 |
Nib | +0.008 |
Neg logit contributions | |
lvl | -0.013 |
Shadow | -0.012 |
zie | -0.011 |
ンジ | -0.011 |
Cargo | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
bent | +0.007 |
pleas | +0.007 |
Bac | +0.007 |
Hath | +0.007 |
Nib | +0.007 |
Neg logit contributions | |
lvl | -0.011 |
Shadow | -0.010 |
zie | -0.009 |
ンジ | -0.009 |
filename | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
lvl | +0.069 |
Shadow | +0.066 |
zie | +0.060 |
ンジ | +0.060 |
filename | +0.058 |
Neg logit contributions | |
bent | -0.051 |
pleas | -0.050 |
Bac | -0.049 |
Hath | -0.048 |
Nib | -0.047 |
Token | Hills |
Token ID | 14379 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
lvl | +0.025 |
Shadow | +0.024 |
zie | +0.022 |
ンジ | +0.021 |
filename | +0.021 |
Neg logit contributions | |
bent | -0.024 |
pleas | -0.024 |
Bac | -0.023 |
Hath | -0.023 |
Nib | -0.022 |
Token | borough |
Token ID | 17913 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
lvl | +0.006 |
Shadow | +0.006 |
zie | +0.005 |
ンジ | +0.005 |
filename | +0.005 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
Nib | -0.003 |
Token | County |
Token ID | 3418 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
lvl | +0.192 |
Shadow | +0.183 |
zie | +0.165 |
ンジ | +0.163 |
filename | +0.159 |
Neg logit contributions | |
bent | -0.161 |
pleas | -0.159 |
Bac | -0.155 |
Hath | -0.153 |
Nib | -0.148 |
Token | Sheriff |
Token ID | 12874 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
lvl | +0.052 |
Shadow | +0.049 |
zie | +0.043 |
ンジ | +0.043 |
filename | +0.041 |
Neg logit contributions | |
bent | -0.063 |
pleas | -0.062 |
Bac | -0.061 |
Hath | -0.060 |
Nib | -0.059 |
Token | 's |
Token ID | 338 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
bent | +0.005 |
pleas | +0.004 |
Bac | +0.004 |
Hath | +0.004 |
relig | +0.004 |
Neg logit contributions | |
lvl | -0.008 |
Shadow | -0.008 |
zie | -0.007 |
ンジ | -0.007 |
Cargo | -0.007 |
Token | Office |
Token ID | 4452 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
lvl | +0.033 |
Shadow | +0.031 |
zie | +0.028 |
ンジ | +0.028 |
filename | +0.027 |
Neg logit contributions | |
bent | -0.029 |
pleas | -0.029 |
Bac | -0.028 |
Hath | -0.027 |
Nib | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
lvl | +0.131 |
Shadow | +0.128 |
zie | +0.117 |
ンジ | +0.116 |
Cargo | +0.114 |
Neg logit contributions | |
bent | -0.061 |
pleas | -0.060 |
Bac | -0.058 |
Hath | -0.057 |
relig | -0.054 |
Token | is |
Token ID | 318 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
lvl | +0.001 |
Shadow | +0.001 |
zie | +0.001 |
ンジ | +0.001 |
filename | +0.001 |
Neg logit contributions | |
bent | -0.000 |
pleas | -0.000 |
Bac | -0.000 |
Hath | -0.000 |
relig | -0.000 |
Token | temporary |
Token ID | 8584 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
lvl | +0.009 |
Shadow | +0.009 |
zie | +0.008 |
ンジ | +0.008 |
velt | +0.008 |
Neg logit contributions | |
bent | -0.006 |
pleas | -0.006 |
Bac | -0.005 |
Hath | -0.005 |
Nib | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
lvl | +0.034 |
Shadow | +0.033 |
zie | +0.030 |
ンジ | +0.030 |
Cargo | +0.029 |
Neg logit contributions | |
bent | -0.020 |
pleas | -0.020 |
Bac | -0.019 |
Hath | -0.019 |
Nib | -0.018 |
Token | I |
Token ID | 314 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
Nib | +0.002 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
zie | -0.004 |
ンジ | -0.004 |
filename | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
bent | +0.002 |
pleas | +0.002 |
Bac | +0.002 |
Hath | +0.002 |
relig | +0.002 |
Neg logit contributions | |
lvl | -0.004 |
Shadow | -0.004 |
ンジ | -0.004 |
zie | -0.004 |
filename | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
lvl | +0.003 |
Shadow | +0.003 |
zie | +0.003 |
ンジ | +0.003 |
Cargo | +0.003 |
Neg logit contributions | |
bent | -0.003 |
pleas | -0.003 |
Bac | -0.003 |
Hath | -0.003 |
relig | -0.003 |
Token | m |
Token ID | 76 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
lvl | +0.181 |
Shadow | +0.175 |
zie | +0.158 |
ンジ | +0.157 |
Cargo | +0.153 |
Neg logit contributions | |
bent | -0.130 |
pleas | -0.128 |
Bac | -0.125 |
Hath | -0.122 |
Nib | -0.118 |
Token | also |
Token ID | 635 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
lvl | +0.062 |
Shadow | +0.060 |
zie | +0.055 |
ンジ | +0.055 |
filename | +0.053 |
Neg logit contributions | |
bent | -0.036 |
pleas | -0.036 |
Bac | -0.034 |
Hath | -0.034 |
Nib | -0.032 |
Token | going |
Token ID | 1016 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
lvl | +0.023 |
Shadow | +0.023 |
zie | +0.021 |
ンジ | +0.020 |
filename | +0.020 |
Neg logit contributions | |
bent | -0.014 |
pleas | -0.014 |
Bac | -0.014 |
Hath | -0.013 |
Nib | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
lvl | +0.046 |
Shadow | +0.045 |
zie | +0.040 |
ンジ | +0.040 |
Cargo | +0.039 |
Neg logit contributions | |
bent | -0.035 |
pleas | -0.034 |
Bac | -0.033 |
Hath | -0.033 |
Nib | -0.032 |
Token | use |
Token ID | 779 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
lvl | +0.024 |
Shadow | +0.024 |
zie | +0.022 |
ンジ | +0.022 |
filename | +0.021 |
Neg logit contributions | |
bent | -0.011 |
pleas | -0.011 |
Bac | -0.011 |
Hath | -0.010 |
relig | -0.010 |