Token | sand |
Token ID | 6450 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
gol | +0.177 |
David | +0.150 |
aden | +0.149 |
ival | +0.144 |
cheated | +0.143 |
Neg logit contributions | |
Sn | -0.074 |
pap | -0.073 |
elope | -0.072 |
isa | -0.072 |
sn | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
gol | +0.348 |
David | +0.295 |
aden | +0.294 |
ival | +0.281 |
cheated | +0.279 |
Neg logit contributions | |
bing | -0.112 |
mary | -0.108 |
sn | -0.107 |
isa | -0.106 |
elope | -0.105 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gol | +0.079 |
ival | +0.067 |
aden | +0.066 |
David | +0.065 |
cheated | +0.063 |
Neg logit contributions | |
sn | -0.026 |
pap | -0.025 |
bing | -0.024 |
Sn | -0.024 |
Pr | -0.023 |
Token | deep |
Token ID | 2769 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
gol | +0.053 |
aden | +0.044 |
David | +0.044 |
arl | +0.043 |
ival | +0.043 |
Neg logit contributions | |
sn | -0.022 |
pap | -0.021 |
Sn | -0.020 |
Pr | -0.020 |
pur | -0.020 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
gol | +0.107 |
David | +0.091 |
aden | +0.089 |
ival | +0.088 |
cheated | +0.085 |
Neg logit contributions | |
bing | -0.037 |
isa | -0.036 |
elope | -0.035 |
sn | -0.035 |
pap | -0.035 |
Token | seas |
Token ID | 21547 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
gol | +0.088 |
David | +0.075 |
aden | +0.073 |
ival | +0.072 |
cheated | +0.070 |
Neg logit contributions | |
sn | -0.036 |
eyel | -0.035 |
knees | -0.035 |
pap | -0.034 |
isa | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
gol | +0.195 |
David | +0.124 |
aden | +0.122 |
ival | +0.106 |
cheated | +0.103 |
Neg logit contributions | |
elope | -0.308 |
isa | -0.306 |
cel | -0.306 |
mary | -0.306 |
sn | -0.304 |
Token | |
Token ID | 220 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
gol | +0.032 |
aden | +0.026 |
cheated | +0.026 |
aw | +0.026 |
tant | +0.025 |
Neg logit contributions | |
Sn | -0.017 |
Pr | -0.017 |
Moon | -0.016 |
elope | -0.016 |
Chick | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
elope | +0.008 |
Pr | +0.008 |
Sn | +0.007 |
mary | +0.007 |
Ana | +0.007 |
Neg logit contributions | |
gol | -0.036 |
tant | -0.028 |
liar | -0.028 |
cheated | -0.028 |
trophies | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
gol | +0.004 |
cheated | +0.003 |
aw | +0.003 |
aden | +0.003 |
happened | +0.003 |
Neg logit contributions | |
elope | -0.002 |
Sn | -0.002 |
Pr | -0.002 |
isa | -0.002 |
Ana | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Sn | +0.010 |
elope | +0.010 |
isa | +0.010 |
Pr | +0.010 |
Moon | +0.009 |
Neg logit contributions | |
gol | -0.023 |
aden | -0.019 |
cheated | -0.019 |
aw | -0.019 |
happened | -0.019 |
Token | cakes |
Token ID | 30849 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
gol | +0.019 |
aden | +0.015 |
David | +0.015 |
ival | +0.014 |
arl | +0.014 |
Neg logit contributions | |
pap | -0.010 |
Sn | -0.010 |
sn | -0.010 |
Moon | -0.010 |
Pr | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
mary | +0.002 |
cel | +0.002 |
sn | +0.002 |
Sn | +0.002 |
bing | +0.002 |
Neg logit contributions | |
gol | -0.009 |
aden | -0.007 |
David | -0.007 |
cheated | -0.007 |
tant | -0.007 |
Token | cookies |
Token ID | 14746 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Sn | +0.003 |
cel | +0.003 |
isa | +0.003 |
pap | +0.003 |
elope | +0.003 |
Neg logit contributions | |
gol | -0.004 |
aw | -0.003 |
aden | -0.003 |
David | -0.003 |
cheated | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
mary | +0.003 |
cel | +0.003 |
Sn | +0.003 |
sn | +0.002 |
bing | +0.002 |
Neg logit contributions | |
gol | -0.008 |
aden | -0.007 |
David | -0.007 |
aw | -0.007 |
ival | -0.006 |
Token | ch |
Token ID | 442 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
gol | +0.024 |
aden | +0.019 |
David | +0.019 |
aw | +0.018 |
ival | +0.018 |
Neg logit contributions | |
pap | -0.015 |
sn | -0.015 |
Sn | -0.015 |
roast | -0.014 |
cel | -0.014 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
gol | +0.036 |
David | +0.028 |
aden | +0.027 |
ival | +0.027 |
cheated | +0.026 |
Neg logit contributions | |
isa | -0.038 |
mary | -0.037 |
bing | -0.037 |
Pr | -0.037 |
elope | -0.037 |
Token | ates |
Token ID | 689 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
gol | +0.255 |
aw | +0.205 |
aden | +0.199 |
David | +0.199 |
cheated | +0.191 |
Neg logit contributions | |
Sn | -0.186 |
isa | -0.185 |
cel | -0.185 |
elope | -0.184 |
pap | -0.184 |
Token | and |
Token ID | 290 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
gol | +0.015 |
aden | +0.013 |
David | +0.013 |
ival | +0.012 |
aw | +0.012 |
Neg logit contributions | |
mary | -0.004 |
bing | -0.004 |
Sn | -0.004 |
isa | -0.004 |
sn | -0.004 |
Token | ice |
Token ID | 4771 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
gol | +0.046 |
aden | +0.037 |
David | +0.037 |
ival | +0.035 |
ane | +0.035 |
Neg logit contributions | |
sn | -0.026 |
pap | -0.026 |
roast | -0.026 |
pur | -0.025 |
Sn | -0.025 |
Token | cream |
Token ID | 8566 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
gol | +0.099 |
David | +0.077 |
aden | +0.075 |
cheated | +0.071 |
ival | +0.069 |
Neg logit contributions | |
mary | -0.085 |
isa | -0.084 |
bing | -0.083 |
Sn | -0.082 |
elope | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
gol | +0.149 |
David | +0.128 |
aden | +0.126 |
ival | +0.121 |
cheated | +0.120 |
Neg logit contributions | |
Sn | -0.036 |
mary | -0.035 |
sn | -0.034 |
bing | -0.033 |
cel | -0.033 |
Token | colorful |
Token ID | 20239 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
gol | +0.049 |
aw | +0.039 |
aden | +0.038 |
David | +0.038 |
cheated | +0.036 |
Neg logit contributions | |
Sn | -0.035 |
isa | -0.035 |
elope | -0.035 |
cel | -0.035 |
pap | -0.034 |
Token | cand |
Token ID | 2658 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
gol | +0.080 |
David | +0.065 |
aden | +0.065 |
aw | +0.064 |
cheated | +0.063 |
Neg logit contributions | |
isa | -0.041 |
cel | -0.041 |
Sn | -0.040 |
pap | -0.040 |
elope | -0.040 |
Token | ies |
Token ID | 444 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
gol | +0.080 |
aden | +0.065 |
David | +0.065 |
aw | +0.064 |
cheated | +0.063 |
Neg logit contributions | |
isa | -0.032 |
bing | -0.031 |
cel | -0.031 |
pap | -0.031 |
elope | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
isa | +0.005 |
cel | +0.005 |
Sn | +0.005 |
elope | +0.005 |
pap | +0.005 |
Neg logit contributions | |
gol | -0.013 |
aden | -0.010 |
David | -0.010 |
aw | -0.010 |
cheated | -0.010 |
Token | ch |
Token ID | 442 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
gol | +0.040 |
aw | +0.032 |
aden | +0.032 |
David | +0.032 |
ival | +0.031 |
Neg logit contributions | |
isa | -0.021 |
Sn | -0.021 |
pap | -0.021 |
cel | -0.021 |
elope | -0.021 |
Token | ocol |
Token ID | 4668 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
gol | +0.040 |
David | +0.032 |
cheated | +0.031 |
ival | +0.031 |
aden | +0.029 |
Neg logit contributions | |
isa | -0.037 |
mary | -0.037 |
pap | -0.036 |
bing | -0.035 |
Pr | -0.035 |
Token | ates |
Token ID | 689 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
gol | +0.284 |
aden | +0.226 |
David | +0.223 |
cheated | +0.220 |
aw | +0.219 |
Neg logit contributions | |
isa | -0.150 |
cel | -0.146 |
elope | -0.145 |
bing | -0.144 |
Sn | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
gol | +0.017 |
aden | +0.014 |
David | +0.014 |
aw | +0.014 |
ival | +0.014 |
Neg logit contributions | |
mary | -0.005 |
bing | -0.005 |
isa | -0.005 |
Sn | -0.004 |
pap | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
gol | +0.012 |
aw | +0.010 |
aden | +0.010 |
David | +0.010 |
cheated | +0.010 |
Neg logit contributions | |
Sn | -0.005 |
Pr | -0.005 |
Chick | -0.005 |
pap | -0.005 |
mary | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
cel | +0.023 |
Sn | +0.023 |
isa | +0.023 |
bing | +0.022 |
elope | +0.022 |
Neg logit contributions | |
gol | -0.032 |
aw | -0.026 |
David | -0.026 |
aden | -0.025 |
cheated | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
pap | +0.004 |
Sn | +0.004 |
Pr | +0.004 |
Flower | +0.004 |
sn | +0.004 |
Neg logit contributions | |
gol | -0.014 |
aden | -0.012 |
David | -0.012 |
aw | -0.011 |
cheated | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
Sn | +0.002 |
isa | +0.002 |
bing | +0.002 |
pap | +0.002 |
cel | +0.002 |
Neg logit contributions | |
gol | -0.006 |
David | -0.005 |
aden | -0.005 |
aw | -0.005 |
cheated | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
gol | +0.036 |
aden | +0.029 |
aw | +0.029 |
David | +0.029 |
ival | +0.028 |
Neg logit contributions | |
Sn | -0.021 |
pap | -0.021 |
cel | -0.020 |
isa | -0.020 |
elope | -0.020 |
Token | favourite |
Token ID | 12507 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
gol | +0.071 |
aw | +0.058 |
aden | +0.058 |
David | +0.057 |
cheated | +0.056 |
Neg logit contributions | |
isa | -0.035 |
cel | -0.035 |
elope | -0.034 |
Sn | -0.034 |
pap | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
gol | +0.052 |
aw | +0.041 |
aden | +0.040 |
David | +0.040 |
cheated | +0.039 |
Neg logit contributions | |
isa | -0.038 |
cel | -0.038 |
elope | -0.037 |
bing | -0.037 |
pap | -0.037 |
Token | ch |
Token ID | 442 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
gol | +0.078 |
aden | +0.063 |
David | +0.062 |
aw | +0.061 |
cheated | +0.060 |
Neg logit contributions | |
Sn | -0.040 |
sn | -0.039 |
pap | -0.038 |
cel | -0.038 |
Pr | -0.037 |
Token | ocol |
Token ID | 4668 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
gol | +0.028 |
cheated | +0.021 |
David | +0.021 |
aden | +0.019 |
happened | +0.019 |
Neg logit contributions | |
isa | -0.033 |
pap | -0.031 |
cel | -0.030 |
mary | -0.030 |
Pr | -0.030 |
Token | ates |
Token ID | 689 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
gol | +0.268 |
aden | +0.213 |
David | +0.211 |
aw | +0.210 |
cheated | +0.206 |
Neg logit contributions | |
isa | -0.155 |
cel | -0.152 |
elope | -0.152 |
Sn | -0.150 |
pap | -0.149 |
Token | ! |
Token ID | 0 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
isa | +0.004 |
Sn | +0.004 |
pap | +0.004 |
elope | +0.004 |
cel | +0.004 |
Neg logit contributions | |
gol | -0.012 |
David | -0.010 |
aden | -0.010 |
aw | -0.010 |
cheated | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
gol | +0.052 |
aw | +0.040 |
David | +0.040 |
aden | +0.040 |
ax | +0.038 |
Neg logit contributions | |
cel | -0.043 |
bing | -0.043 |
isa | -0.042 |
elope | -0.041 |
cup | -0.041 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
bing | +0.007 |
cel | +0.007 |
Sn | +0.007 |
elope | +0.007 |
isa | +0.007 |
Neg logit contributions | |
gol | -0.011 |
aw | -0.009 |
aden | -0.008 |
David | -0.008 |
cheated | -0.008 |
Token | mummy |
Token ID | 38567 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
gol | +0.002 |
trophies | +0.002 |
aden | +0.002 |
Tommy | +0.002 |
David | +0.002 |
Neg logit contributions | |
elope | -0.002 |
cel | -0.002 |
bes | -0.002 |
cup | -0.002 |
mary | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
gol | +0.029 |
aden | +0.023 |
David | +0.023 |
aw | +0.023 |
ival | +0.022 |
Neg logit contributions | |
Sn | -0.016 |
isa | -0.016 |
cel | -0.016 |
pap | -0.016 |
elope | -0.016 |
Token | fish |
Token ID | 5916 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
gol | +0.026 |
David | +0.021 |
aden | +0.021 |
he | +0.020 |
ival | +0.020 |
Neg logit contributions | |
sn | -0.016 |
pap | -0.015 |
Sn | -0.015 |
Pr | -0.015 |
roast | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
gol | +0.002 |
David | +0.002 |
aden | +0.002 |
aw | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Sn | -0.001 |
elope | -0.001 |
pap | -0.001 |
cel | -0.001 |
isa | -0.001 |
Token | shells |
Token ID | 19679 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
gol | +0.039 |
David | +0.031 |
aden | +0.031 |
aw | +0.031 |
ival | +0.030 |
Neg logit contributions | |
pap | -0.028 |
Sn | -0.028 |
isa | -0.027 |
cel | -0.027 |
elope | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
gol | +0.190 |
David | +0.164 |
aden | +0.160 |
ival | +0.157 |
aw | +0.153 |
Neg logit contributions | |
mary | -0.039 |
sn | -0.038 |
Sn | -0.037 |
bing | -0.035 |
Pr | -0.035 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
gol | +0.065 |
David | +0.053 |
aden | +0.052 |
ival | +0.051 |
aw | +0.050 |
Neg logit contributions | |
pap | -0.047 |
sn | -0.046 |
roast | -0.045 |
Sn | -0.045 |
Pr | -0.044 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
gol | +0.204 |
aden | +0.151 |
David | +0.151 |
aw | +0.150 |
cheated | +0.143 |
Neg logit contributions | |
cel | -0.212 |
isa | -0.211 |
Sn | -0.210 |
elope | -0.209 |
pap | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
gol | +0.090 |
David | +0.076 |
aden | +0.075 |
aw | +0.073 |
ival | +0.072 |
Neg logit contributions | |
Sn | -0.023 |
mary | -0.023 |
isa | -0.023 |
pap | -0.022 |
cel | -0.022 |
Token | But |
Token ID | 887 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
gol | +0.019 |
aden | +0.015 |
aw | +0.015 |
David | +0.015 |
cheated | +0.015 |
Neg logit contributions | |
Sn | -0.011 |
elope | -0.010 |
pap | -0.010 |
isa | -0.010 |
cel | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
cel | +0.016 |
isa | +0.015 |
elope | +0.015 |
Sn | +0.014 |
bing | +0.014 |
Neg logit contributions | |
gol | -0.037 |
aw | -0.030 |
David | -0.030 |
aden | -0.029 |
cheated | -0.029 |
Token | did |
Token ID | 750 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
pap | +0.010 |
sn | +0.010 |
elope | +0.010 |
isa | +0.010 |
mary | +0.009 |
Neg logit contributions | |
gol | -0.018 |
aden | -0.014 |
ival | -0.014 |
aw | -0.014 |
David | -0.014 |
Token | them |
Token ID | 606 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Sn | +0.013 |
pap | +0.012 |
isa | +0.012 |
Pr | +0.012 |
cel | +0.012 |
Neg logit contributions | |
gol | -0.022 |
David | -0.018 |
aden | -0.017 |
aw | -0.017 |
cheated | -0.017 |
Token | tw |
Token ID | 665 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
gol | +0.057 |
David | +0.048 |
aw | +0.047 |
aden | +0.047 |
ival | +0.046 |
Neg logit contributions | |
Sn | -0.020 |
bing | -0.019 |
cel | -0.019 |
elope | -0.019 |
isa | -0.019 |
Token | irl |
Token ID | 1901 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
gol | +0.003 |
aw | +0.002 |
aden | +0.002 |
David | +0.002 |
cheated | +0.002 |
Neg logit contributions | |
elope | -0.002 |
isa | -0.002 |
cel | -0.002 |
pap | -0.002 |
Sn | -0.002 |
Token | around |
Token ID | 1088 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
mary | +0.015 |
Sn | +0.015 |
bing | +0.015 |
sn | +0.013 |
bed | +0.012 |
Neg logit contributions | |
gol | -0.077 |
David | -0.069 |
aden | -0.066 |
ival | -0.063 |
cheated | -0.063 |
Token | each |
Token ID | 1123 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
cel | +0.004 |
isa | +0.004 |
pap | +0.004 |
elope | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
gol | -0.011 |
aw | -0.009 |
aden | -0.009 |
David | -0.009 |
cheated | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
gol | +0.072 |
aw | +0.058 |
aden | +0.057 |
David | +0.056 |
cheated | +0.054 |
Neg logit contributions | |
cel | -0.051 |
elope | -0.050 |
pap | -0.050 |
Sn | -0.050 |
isa | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
gol | +0.287 |
aw | +0.241 |
aden | +0.235 |
David | +0.230 |
cheated | +0.226 |
Neg logit contributions | |
cel | -0.127 |
isa | -0.124 |
pap | -0.122 |
Sn | -0.121 |
elope | -0.121 |
Token | Annie |
Token ID | 25860 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
gol | +0.008 |
aden | +0.006 |
aw | +0.006 |
David | +0.006 |
ival | +0.006 |
Neg logit contributions | |
bing | -0.007 |
cel | -0.007 |
isa | -0.007 |
pap | -0.007 |
elope | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
isa | +0.043 |
elope | +0.042 |
cel | +0.042 |
Sn | +0.042 |
pap | +0.042 |
Neg logit contributions | |
gol | -0.089 |
aden | -0.072 |
David | -0.072 |
aw | -0.072 |
ival | -0.069 |
Token | mother |
Token ID | 2802 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
pap | +0.001 |
Sn | +0.001 |
Pr | +0.001 |
cel | +0.001 |
sn | +0.001 |
Neg logit contributions | |
gol | -0.002 |
David | -0.002 |
aw | -0.002 |
aden | -0.002 |
ival | -0.002 |
Token | called |
Token ID | 1444 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
isa | +0.019 |
cel | +0.019 |
sn | +0.019 |
pap | +0.019 |
elope | +0.019 |
Neg logit contributions | |
gol | -0.042 |
David | -0.033 |
aden | -0.033 |
aw | -0.033 |
arl | -0.032 |
Token | added |
Token ID | 2087 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
sn | +0.023 |
roast | +0.022 |
isa | +0.022 |
Sn | +0.021 |
cel | +0.021 |
Neg logit contributions | |
gol | -0.049 |
David | -0.041 |
aw | -0.041 |
aden | -0.041 |
arl | -0.041 |
Token | shells |
Token ID | 19679 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
sn | +0.031 |
one | +0.029 |
making | +0.027 |
next | +0.027 |
roast | +0.027 |
Neg logit contributions | |
gol | -0.113 |
David | -0.098 |
aden | -0.095 |
ival | -0.091 |
ody | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
gol | +0.126 |
David | +0.111 |
aden | +0.109 |
cheated | +0.105 |
Goal | +0.105 |
Neg logit contributions | |
mary | -0.019 |
sn | -0.017 |
Pr | -0.016 |
pap | -0.016 |
bing | -0.016 |
Token | stones |
Token ID | 14966 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
pap | +0.002 |
sn | +0.002 |
roast | +0.002 |
Pr | +0.002 |
knees | +0.002 |
Neg logit contributions | |
gol | -0.002 |
aden | -0.002 |
ival | -0.002 |
David | -0.002 |
he | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gol | +0.179 |
David | +0.160 |
aden | +0.158 |
ival | +0.150 |
Goal | +0.148 |
Neg logit contributions | |
mary | -0.030 |
sn | -0.028 |
bing | -0.025 |
soon | -0.025 |
before | -0.024 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
gol | +0.046 |
aden | +0.038 |
arl | +0.038 |
David | +0.038 |
ival | +0.038 |
Neg logit contributions | |
sn | -0.028 |
roast | -0.026 |
pap | -0.026 |
knees | -0.025 |
pur | -0.025 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
gol | +0.227 |
David | +0.176 |
aden | +0.170 |
cheated | +0.168 |
happened | +0.161 |
Neg logit contributions | |
cel | -0.190 |
pap | -0.182 |
isa | -0.180 |
bing | -0.179 |
Sn | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
gol | +0.077 |
David | +0.067 |
aden | +0.066 |
ival | +0.063 |
cheated | +0.062 |
Neg logit contributions | |
mary | -0.017 |
sn | -0.016 |
bing | -0.015 |
Sn | -0.015 |
pap | -0.015 |
Token | make |
Token ID | 787 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
gol | +0.086 |
aden | +0.074 |
ival | +0.074 |
David | +0.074 |
ane | +0.072 |
Neg logit contributions | |
roast | -0.022 |
sn | -0.021 |
make | -0.020 |
side | -0.019 |
search | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
sn | +0.054 |
pur | +0.049 |
pap | +0.049 |
we | +0.048 |
Ana | +0.048 |
Neg logit contributions | |
gol | -0.118 |
arl | -0.098 |
David | -0.097 |
aden | -0.095 |
ival | -0.094 |
Token | look |
Token ID | 804 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Sn | +0.020 |
elope | +0.020 |
pap | +0.020 |
cel | +0.020 |
isa | +0.020 |
Neg logit contributions | |
gol | -0.041 |
David | -0.033 |
aden | -0.033 |
aw | -0.033 |
ival | -0.031 |
Token | some |
Token ID | 617 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
gol | +0.127 |
David | +0.105 |
ival | +0.103 |
aden | +0.103 |
arl | +0.102 |
Neg logit contributions | |
Bee | -0.038 |
pap | -0.038 |
sn | -0.037 |
Luna | -0.036 |
Pr | -0.036 |
Token | shells |
Token ID | 19679 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
sn | +0.025 |
pap | +0.025 |
buzzing | +0.023 |
Moon | +0.023 |
roast | +0.022 |
Neg logit contributions | |
gol | -0.056 |
David | -0.046 |
aden | -0.045 |
ival | -0.044 |
ax | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gol | +0.128 |
David | +0.109 |
aden | +0.106 |
ival | +0.104 |
aw | +0.103 |
Neg logit contributions | |
sn | -0.034 |
bing | -0.033 |
following | -0.031 |
mary | -0.030 |
Sn | -0.030 |
Token | rocks |
Token ID | 12586 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
gol | +0.044 |
aden | +0.035 |
David | +0.035 |
aw | +0.034 |
ival | +0.034 |
Neg logit contributions | |
pap | -0.028 |
isa | -0.028 |
Sn | -0.028 |
elope | -0.027 |
cel | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
gol | +0.159 |
David | +0.141 |
aden | +0.134 |
ival | +0.133 |
Goal | +0.131 |
Neg logit contributions | |
sn | -0.036 |
bing | -0.036 |
following | -0.033 |
mary | -0.033 |
making | -0.031 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
gol | +0.068 |
David | +0.055 |
aden | +0.055 |
ival | +0.054 |
aw | +0.053 |
Neg logit contributions | |
pap | -0.042 |
sn | -0.041 |
isa | -0.039 |
Pr | -0.039 |
roast | -0.039 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
gol | +0.203 |
aden | +0.149 |
David | +0.149 |
aw | +0.148 |
cheated | +0.142 |
Neg logit contributions | |
cel | -0.211 |
isa | -0.210 |
Sn | -0.209 |
pap | -0.208 |
elope | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
gol | +0.080 |
David | +0.069 |
aden | +0.067 |
ival | +0.065 |
aw | +0.064 |
Neg logit contributions | |
sn | -0.018 |
bing | -0.018 |
mary | -0.017 |
Sn | -0.017 |
pap | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
gol | +0.014 |
aden | +0.012 |
ival | +0.011 |
David | +0.011 |
cheated | +0.011 |
Neg logit contributions | |
Pr | -0.010 |
Bee | -0.010 |
Luna | -0.009 |
Chick | -0.009 |
Milo | -0.009 |
Token | picked |
Token ID | 6497 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
gol | +0.026 |
aden | +0.021 |
aw | +0.021 |
David | +0.021 |
ival | +0.020 |
Neg logit contributions | |
isa | -0.015 |
pap | -0.015 |
Sn | -0.015 |
elope | -0.015 |
cel | -0.015 |
Token | them |
Token ID | 606 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
gol | +0.034 |
David | +0.030 |
aden | +0.028 |
ival | +0.028 |
arl | +0.028 |
Neg logit contributions | |
sn | -0.008 |
Pr | -0.008 |
Sn | -0.008 |
mary | -0.008 |
Flower | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
gol | +0.043 |
David | +0.034 |
aden | +0.033 |
aw | +0.032 |
cheated | +0.032 |
Neg logit contributions | |
bing | -0.032 |
isa | -0.031 |
Sn | -0.031 |
cel | -0.030 |
Pr | -0.030 |
Token | shells |
Token ID | 19679 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
gol | +0.072 |
arl | +0.059 |
David | +0.059 |
ane | +0.058 |
ival | +0.055 |
Neg logit contributions | |
sn | -0.034 |
bing | -0.031 |
isa | -0.031 |
following | -0.030 |
Ana | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
gol | +0.168 |
David | +0.141 |
aden | +0.137 |
aw | +0.134 |
cheated | +0.133 |
Neg logit contributions | |
mary | -0.048 |
bing | -0.047 |
sn | -0.047 |
cel | -0.045 |
isa | -0.044 |
Token | rocks |
Token ID | 12586 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
gol | +0.066 |
David | +0.052 |
aden | +0.052 |
ival | +0.051 |
arl | +0.050 |
Neg logit contributions | |
sn | -0.040 |
pap | -0.040 |
cel | -0.039 |
Sn | -0.039 |
Pr | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
gol | +0.138 |
David | +0.118 |
aden | +0.116 |
Goal | +0.113 |
aw | +0.113 |
Neg logit contributions | |
bing | -0.037 |
mary | -0.036 |
sn | -0.033 |
Sn | -0.033 |
cel | -0.033 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
gol | +0.067 |
David | +0.054 |
aden | +0.053 |
aw | +0.053 |
arl | +0.052 |
Neg logit contributions | |
pap | -0.038 |
sn | -0.037 |
isa | -0.036 |
Sn | -0.036 |
Pr | -0.036 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
gol | +0.219 |
David | +0.165 |
aden | +0.163 |
cheated | +0.161 |
aw | +0.156 |
Neg logit contributions | |
cel | -0.196 |
isa | -0.190 |
pap | -0.189 |
bing | -0.187 |
mary | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
gol | +0.081 |
David | +0.068 |
aden | +0.067 |
aw | +0.065 |
ival | +0.065 |
Neg logit contributions | |
mary | -0.023 |
bing | -0.022 |
Sn | -0.022 |
isa | -0.021 |
pap | -0.021 |
Token | but |
Token ID | 475 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
gol | +0.112 |
aden | +0.093 |
David | +0.093 |
aw | +0.091 |
ival | +0.091 |
Neg logit contributions | |
pap | -0.035 |
sn | -0.035 |
Sn | -0.034 |
cel | -0.034 |
bing | -0.033 |
Token | Jane |
Token ID | 12091 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
elope | +0.009 |
isa | +0.009 |
pap | +0.009 |
Sn | +0.009 |
Pr | +0.009 |
Neg logit contributions | |
gol | -0.021 |
aden | -0.018 |
aw | -0.017 |
David | -0.017 |
ival | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
gol | +0.019 |
David | +0.015 |
aden | +0.015 |
aw | +0.015 |
ival | +0.015 |
Neg logit contributions | |
isa | -0.009 |
elope | -0.009 |
cel | -0.009 |
pap | -0.009 |
Sn | -0.009 |
Token | like |
Token ID | 588 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
gol | +0.032 |
aden | +0.026 |
David | +0.026 |
aw | +0.026 |
ival | +0.025 |
Neg logit contributions | |
Sn | -0.015 |
pap | -0.015 |
sn | -0.015 |
cel | -0.015 |
isa | -0.015 |
Token | fish |
Token ID | 5916 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
gol | +0.029 |
David | +0.024 |
he | +0.023 |
aden | +0.023 |
ival | +0.023 |
Neg logit contributions | |
sn | -0.017 |
pap | -0.016 |
Sn | -0.016 |
Pr | -0.015 |
roast | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
gol | +0.003 |
David | +0.003 |
aden | +0.003 |
aw | +0.003 |
ival | +0.003 |
Neg logit contributions | |
Sn | -0.001 |
pap | -0.001 |
elope | -0.001 |
isa | -0.001 |
cel | -0.001 |
Token | shells |
Token ID | 19679 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
gol | +0.040 |
David | +0.032 |
aden | +0.032 |
aw | +0.031 |
ival | +0.031 |
Neg logit contributions | |
pap | -0.025 |
sn | -0.024 |
roast | -0.024 |
Sn | -0.024 |
Pr | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gol | +0.195 |
David | +0.169 |
aden | +0.165 |
ival | +0.162 |
Goal | +0.156 |
Neg logit contributions | |
mary | -0.038 |
sn | -0.038 |
Sn | -0.036 |
bing | -0.034 |
Pr | -0.033 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
gol | +0.066 |
David | +0.054 |
aden | +0.053 |
ival | +0.053 |
aw | +0.052 |
Neg logit contributions | |
pap | -0.043 |
sn | -0.043 |
roast | -0.042 |
Sn | -0.040 |
Pr | -0.040 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
gol | +0.209 |
David | +0.156 |
aden | +0.155 |
aw | +0.151 |
cheated | +0.148 |
Neg logit contributions | |
cel | -0.203 |
isa | -0.202 |
pap | -0.201 |
elope | -0.199 |
Sn | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
gol | +0.092 |
David | +0.079 |
aden | +0.077 |
aw | +0.075 |
ival | +0.075 |
Neg logit contributions | |
mary | -0.023 |
Sn | -0.023 |
isa | -0.023 |
pap | -0.023 |
bing | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
gol | +0.017 |
aw | +0.014 |
aden | +0.014 |
David | +0.014 |
cheated | +0.014 |
Neg logit contributions | |
Sn | -0.009 |
Pr | -0.009 |
elope | -0.009 |
Chick | -0.008 |
pap | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
gol | +0.011 |
aw | +0.009 |
aden | +0.009 |
cheated | +0.009 |
David | +0.009 |
Neg logit contributions | |
Sn | -0.006 |
elope | -0.006 |
isa | -0.005 |
Pr | -0.005 |
Chick | -0.005 |
Token | One |
Token ID | 3198 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
cel | +0.007 |
pap | +0.007 |
isa | +0.007 |
elope | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
gol | -0.015 |
aw | -0.013 |
David | -0.013 |
aden | -0.012 |
ival | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
gol | +0.088 |
David | +0.073 |
aden | +0.073 |
aw | +0.071 |
ival | +0.070 |
Neg logit contributions | |
Sn | -0.034 |
elope | -0.034 |
pap | -0.034 |
bing | -0.034 |
isa | -0.033 |
Token | different |
Token ID | 1180 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
gol | +0.015 |
aden | +0.012 |
aw | +0.012 |
David | +0.012 |
cheated | +0.011 |
Neg logit contributions | |
isa | -0.012 |
elope | -0.011 |
Sn | -0.011 |
cel | -0.011 |
pap | -0.011 |
Token | fish |
Token ID | 5916 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
gol | +0.036 |
aw | +0.029 |
aden | +0.029 |
David | +0.029 |
cheated | +0.028 |
Neg logit contributions | |
cel | -0.020 |
isa | -0.020 |
Sn | -0.020 |
elope | -0.020 |
pap | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
gol | +0.040 |
aw | +0.033 |
aden | +0.033 |
David | +0.033 |
cheated | +0.032 |
Neg logit contributions | |
cel | -0.017 |
Sn | -0.017 |
isa | -0.017 |
pap | -0.017 |
elope | -0.017 |
Token | colorful |
Token ID | 20239 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
gol | +0.032 |
aw | +0.026 |
aden | +0.026 |
David | +0.026 |
cheated | +0.025 |
Neg logit contributions | |
cel | -0.015 |
Sn | -0.015 |
isa | -0.015 |
elope | -0.014 |
pap | -0.014 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
gol | +0.097 |
David | +0.078 |
aden | +0.078 |
aw | +0.076 |
cheated | +0.074 |
Neg logit contributions | |
isa | -0.061 |
pap | -0.060 |
Sn | -0.060 |
cel | -0.059 |
elope | -0.059 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
gol | +0.190 |
aw | +0.140 |
aden | +0.137 |
David | +0.136 |
cheated | +0.128 |
Neg logit contributions | |
Sn | -0.219 |
isa | -0.218 |
elope | -0.217 |
cel | -0.217 |
pap | -0.216 |
Token | below |
Token ID | 2174 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
gol | +0.076 |
aw | +0.063 |
aden | +0.063 |
David | +0.063 |
cheated | +0.061 |
Neg logit contributions | |
isa | -0.027 |
Sn | -0.027 |
cel | -0.027 |
elope | -0.027 |
pap | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
gol | +0.101 |
aden | +0.084 |
David | +0.084 |
ival | +0.082 |
cheated | +0.081 |
Neg logit contributions | |
elope | -0.028 |
Pr | -0.028 |
Sn | -0.028 |
sn | -0.027 |
isa | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
gol | +0.022 |
aden | +0.018 |
aw | +0.018 |
David | +0.018 |
cheated | +0.018 |
Neg logit contributions | |
elope | -0.011 |
Pr | -0.011 |
Sn | -0.011 |
Flower | -0.010 |
isa | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.007 |
aden | +0.007 |
cheated | +0.007 |
David | +0.006 |
Neg logit contributions | |
elope | -0.004 |
Sn | -0.004 |
isa | -0.004 |
Pr | -0.004 |
Chick | -0.003 |
Token | shore |
Token ID | 15191 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
gol | +0.052 |
aw | +0.041 |
aden | +0.041 |
David | +0.041 |
cheated | +0.039 |
Neg logit contributions | |
isa | -0.035 |
Sn | -0.035 |
cel | -0.035 |
elope | -0.035 |
pap | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
gol | +0.047 |
aden | +0.039 |
David | +0.039 |
aw | +0.038 |
cheated | +0.038 |
Neg logit contributions | |
isa | -0.016 |
elope | -0.016 |
bing | -0.016 |
Sn | -0.015 |
pap | -0.015 |
Token | collecting |
Token ID | 13157 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
gol | +0.060 |
aw | +0.050 |
aden | +0.050 |
David | +0.050 |
cheated | +0.048 |
Neg logit contributions | |
isa | -0.022 |
cel | -0.021 |
elope | -0.021 |
Sn | -0.021 |
pap | -0.021 |
Token | shells |
Token ID | 19679 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
gol | +0.016 |
David | +0.013 |
aden | +0.013 |
cheated | +0.012 |
ival | +0.012 |
Neg logit contributions | |
sn | -0.010 |
pap | -0.009 |
Pr | -0.009 |
Sn | -0.009 |
bing | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
gol | +0.158 |
David | +0.133 |
aden | +0.130 |
cheated | +0.129 |
ival | +0.127 |
Neg logit contributions | |
bing | -0.043 |
sn | -0.041 |
mary | -0.040 |
Sn | -0.040 |
pap | -0.040 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
gol | +0.026 |
aden | +0.021 |
aw | +0.021 |
David | +0.021 |
ival | +0.021 |
Neg logit contributions | |
pap | -0.013 |
sn | -0.013 |
isa | -0.012 |
Sn | -0.012 |
bing | -0.012 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
gol | +0.211 |
David | +0.157 |
aden | +0.157 |
cheated | +0.154 |
aw | +0.151 |
Neg logit contributions | |
cel | -0.196 |
isa | -0.194 |
pap | -0.192 |
bing | -0.191 |
elope | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
gol | +0.080 |
David | +0.068 |
aden | +0.066 |
aw | +0.064 |
ival | +0.064 |
Neg logit contributions | |
bing | -0.022 |
Sn | -0.021 |
mary | -0.021 |
isa | -0.021 |
sn | -0.020 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
gol | +0.016 |
aw | +0.014 |
David | +0.013 |
aden | +0.013 |
cheated | +0.013 |
Neg logit contributions | |
Sn | -0.009 |
Pr | -0.008 |
Ana | -0.008 |
elope | -0.008 |
Moon | -0.007 |
Token | took |
Token ID | 1718 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
gol | +0.041 |
aw | +0.034 |
aden | +0.033 |
David | +0.033 |
cheated | +0.032 |
Neg logit contributions | |
cel | -0.021 |
Sn | -0.021 |
isa | -0.021 |
elope | -0.021 |
pap | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
sn | +0.003 |
Pr | +0.003 |
Sn | +0.003 |
one | +0.003 |
Moon | +0.002 |
Neg logit contributions | |
gol | -0.009 |
arl | -0.007 |
David | -0.007 |
ane | -0.007 |
aden | -0.007 |
Token | cast |
Token ID | 2701 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
gol | +0.126 |
David | +0.100 |
aden | +0.097 |
cheated | +0.095 |
ival | +0.092 |
Neg logit contributions | |
bing | -0.088 |
sn | -0.086 |
Sn | -0.084 |
mary | -0.083 |
we | -0.083 |
Token | les |
Token ID | 829 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
gol | +0.080 |
David | +0.066 |
liar | +0.064 |
cheated | +0.063 |
fault | +0.063 |
Neg logit contributions | |
ches | -0.034 |
isa | -0.030 |
bing | -0.028 |
mary | -0.028 |
every | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
gol | +0.034 |
David | +0.029 |
aden | +0.029 |
cheated | +0.027 |
ival | +0.027 |
Neg logit contributions | |
bing | -0.009 |
mary | -0.009 |
isa | -0.009 |
sn | -0.009 |
Sn | -0.008 |
Token | collect |
Token ID | 2824 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
gol | +0.007 |
aw | +0.006 |
arl | +0.006 |
David | +0.005 |
aden | +0.005 |
Neg logit contributions | |
sn | -0.003 |
roast | -0.003 |
isa | -0.003 |
pap | -0.003 |
Sn | -0.003 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
gol | +0.046 |
David | +0.038 |
arl | +0.035 |
ane | +0.034 |
aden | +0.034 |
Neg logit contributions | |
sn | -0.028 |
one | -0.025 |
n | -0.024 |
Ana | -0.024 |
Pr | -0.023 |
Token | seas |
Token ID | 21547 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
gol | +0.054 |
David | +0.042 |
cheated | +0.041 |
aden | +0.040 |
ival | +0.039 |
Neg logit contributions | |
sn | -0.043 |
bing | -0.042 |
pap | -0.042 |
isa | -0.042 |
cel | -0.042 |
Token | hell |
Token ID | 12758 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
gol | +0.149 |
David | +0.093 |
aden | +0.089 |
cheated | +0.087 |
aw | +0.073 |
Neg logit contributions | |
mary | -0.265 |
cel | -0.262 |
isa | -0.261 |
elope | -0.256 |
bing | -0.254 |
Token | s |
Token ID | 82 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
gol | +0.139 |
David | +0.121 |
aden | +0.116 |
cheated | +0.111 |
aw | +0.110 |
Neg logit contributions | |
mary | -0.042 |
bing | -0.040 |
Sn | -0.038 |
isa | -0.038 |
sn | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
gol | +0.026 |
David | +0.022 |
aden | +0.022 |
ival | +0.021 |
cheated | +0.021 |
Neg logit contributions | |
bing | -0.005 |
sn | -0.005 |
mary | -0.005 |
elope | -0.005 |
pap | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
gol | +0.027 |
cheated | +0.022 |
aw | +0.022 |
aden | +0.022 |
David | +0.022 |
Neg logit contributions | |
Sn | -0.012 |
elope | -0.012 |
Pr | -0.012 |
Chick | -0.011 |
Moon | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
isa | +0.031 |
pap | +0.030 |
Pr | +0.030 |
sn | +0.029 |
elope | +0.029 |
Neg logit contributions | |
gol | -0.069 |
aden | -0.058 |
David | -0.058 |
cheated | -0.057 |
ival | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
gol | +0.013 |
David | +0.011 |
aden | +0.011 |
aw | +0.011 |
tant | +0.011 |
Neg logit contributions | |
bing | -0.004 |
Sn | -0.003 |
sn | -0.003 |
pap | -0.003 |
isa | -0.003 |
Token | cup |
Token ID | 6508 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
gol | +0.059 |
aden | +0.049 |
aw | +0.048 |
David | +0.048 |
ival | +0.048 |
Neg logit contributions | |
Sn | -0.026 |
pap | -0.024 |
sn | -0.024 |
cel | -0.024 |
Pr | -0.023 |
Token | cakes |
Token ID | 37263 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Sn | +0.008 |
mary | +0.008 |
sn | +0.008 |
cel | +0.008 |
pap | +0.008 |
Neg logit contributions | |
gol | -0.017 |
David | -0.014 |
aden | -0.014 |
cheated | -0.013 |
Kyle | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Sn | +0.022 |
cel | +0.022 |
isa | +0.022 |
elope | +0.021 |
pap | +0.021 |
Neg logit contributions | |
gol | -0.055 |
aden | -0.045 |
David | -0.045 |
aw | -0.045 |
cheated | -0.043 |
Token | ch |
Token ID | 442 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
gol | +0.027 |
aden | +0.021 |
David | +0.021 |
aw | +0.021 |
ival | +0.021 |
Neg logit contributions | |
Sn | -0.016 |
sn | -0.016 |
pap | -0.016 |
Pr | -0.015 |
cel | -0.015 |
Token | ocol |
Token ID | 4668 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
gol | +0.037 |
David | +0.030 |
cheated | +0.029 |
ival | +0.028 |
happened | +0.027 |
Neg logit contributions | |
bing | -0.033 |
mary | -0.032 |
isa | -0.032 |
Pr | -0.031 |
Sn | -0.031 |
Token | ates |
Token ID | 689 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
gol | +0.287 |
aden | +0.231 |
David | +0.228 |
cheated | +0.227 |
ival | +0.223 |
Neg logit contributions | |
isa | -0.128 |
bing | -0.124 |
cup | -0.123 |
we | -0.122 |
cel | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
gol | +0.012 |
David | +0.010 |
aden | +0.010 |
aw | +0.010 |
ival | +0.010 |
Neg logit contributions | |
Sn | -0.003 |
bing | -0.003 |
isa | -0.003 |
mary | -0.003 |
sn | -0.003 |
Token | |
Token ID | 220 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
gol | +0.026 |
aw | +0.021 |
happened | +0.021 |
ival | +0.021 |
aden | +0.020 |
Neg logit contributions | |
Sn | -0.016 |
Pr | -0.014 |
Chick | -0.012 |
Fl | -0.012 |
elope | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Sn | +0.011 |
Pr | +0.009 |
elope | +0.009 |
Chick | +0.008 |
mary | +0.008 |
Neg logit contributions | |
gol | -0.042 |
aw | -0.033 |
tant | -0.033 |
liar | -0.033 |
aden | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
gol | +0.014 |
happened | +0.012 |
aw | +0.012 |
cheated | +0.011 |
aden | +0.011 |
Neg logit contributions | |
Sn | -0.005 |
Pr | -0.004 |
elope | -0.004 |
mary | -0.003 |
Flower | -0.003 |
Token | sky |
Token ID | 6766 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
gol | +0.037 |
David | +0.030 |
aden | +0.030 |
aw | +0.029 |
ival | +0.029 |
Neg logit contributions | |
Sn | -0.019 |
elope | -0.019 |
cel | -0.019 |
isa | -0.019 |
sn | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
isa | +0.008 |
cel | +0.008 |
Sn | +0.008 |
elope | +0.008 |
pap | +0.008 |
Neg logit contributions | |
gol | -0.020 |
aw | -0.017 |
aden | -0.016 |
David | -0.016 |
cheated | -0.016 |
Token | Round |
Token ID | 10485 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
gol | +0.005 |
aden | +0.004 |
David | +0.004 |
aw | +0.004 |
cheated | +0.004 |
Neg logit contributions | |
Sn | -0.003 |
isa | -0.003 |
cel | -0.003 |
elope | -0.003 |
pap | -0.003 |
Token | shapes |
Token ID | 15268 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
isa | +0.007 |
Moon | +0.007 |
Sn | +0.007 |
sn | +0.007 |
elope | +0.007 |
Neg logit contributions | |
gol | -0.028 |
David | -0.025 |
aden | -0.025 |
arl | -0.023 |
cheated | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
gol | +0.119 |
David | +0.100 |
aden | +0.099 |
aw | +0.094 |
ival | +0.093 |
Neg logit contributions | |
sn | -0.060 |
bing | -0.058 |
isa | -0.058 |
mary | -0.057 |
pap | -0.057 |
Token | other |
Token ID | 584 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
gol | +0.034 |
aw | +0.028 |
aden | +0.027 |
David | +0.027 |
cheated | +0.026 |
Neg logit contributions | |
isa | -0.018 |
cel | -0.018 |
Sn | -0.018 |
elope | -0.018 |
pap | -0.018 |
Token | shapes |
Token ID | 15268 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
gol | +0.284 |
David | +0.235 |
arl | +0.233 |
aden | +0.225 |
ax | +0.221 |
Neg logit contributions | |
isa | -0.127 |
sn | -0.123 |
Moon | -0.120 |
pap | -0.119 |
elope | -0.118 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
gol | +0.128 |
David | +0.109 |
aden | +0.107 |
aw | +0.103 |
ival | +0.102 |
Neg logit contributions | |
sn | -0.050 |
bing | -0.048 |
mary | -0.048 |
pap | -0.047 |
pur | -0.047 |
Token | changed |
Token ID | 3421 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
gol | +0.057 |
David | +0.049 |
aden | +0.048 |
aw | +0.047 |
arl | +0.047 |
Neg logit contributions | |
sn | -0.024 |
pap | -0.024 |
Pr | -0.024 |
Moon | -0.024 |
elope | -0.024 |
Token | each |
Token ID | 1123 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
bing | +0.017 |
pap | +0.016 |
Pr | +0.016 |
isa | +0.016 |
elope | +0.016 |
Neg logit contributions | |
gol | -0.050 |
David | -0.042 |
aden | -0.042 |
ival | -0.042 |
aw | -0.040 |
Token | day |
Token ID | 1110 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
gol | +0.046 |
aw | +0.037 |
aden | +0.037 |
David | +0.037 |
cheated | +0.035 |
Neg logit contributions | |
isa | -0.027 |
Sn | -0.027 |
elope | -0.027 |
cel | -0.027 |
pap | -0.027 |
Token | sand |
Token ID | 6450 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
gol | +0.015 |
David | +0.012 |
aden | +0.012 |
aw | +0.012 |
cheated | +0.012 |
Neg logit contributions | |
Sn | -0.009 |
cel | -0.009 |
isa | -0.009 |
bing | -0.009 |
pap | -0.009 |
Token | cast |
Token ID | 2701 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
gol | +0.184 |
David | +0.151 |
aden | +0.148 |
cheated | +0.143 |
ival | +0.141 |
Neg logit contributions | |
bing | -0.091 |
mary | -0.086 |
isa | -0.085 |
Sn | -0.084 |
cel | -0.084 |
Token | les |
Token ID | 829 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
gol | +0.090 |
David | +0.073 |
aden | +0.069 |
liar | +0.069 |
cheated | +0.068 |
Neg logit contributions | |
isa | -0.042 |
ches | -0.042 |
mary | -0.040 |
bing | -0.040 |
sn | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
gol | +0.044 |
David | +0.037 |
aden | +0.037 |
ival | +0.035 |
cheated | +0.035 |
Neg logit contributions | |
bing | -0.014 |
isa | -0.013 |
Sn | -0.013 |
mary | -0.013 |
cel | -0.013 |
Token | collecting |
Token ID | 13157 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
gol | +0.019 |
aw | +0.016 |
David | +0.016 |
aden | +0.016 |
ival | +0.015 |
Neg logit contributions | |
isa | -0.008 |
pap | -0.008 |
Sn | -0.008 |
sn | -0.008 |
cel | -0.008 |
Token | seas |
Token ID | 21547 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
gol | +0.028 |
David | +0.023 |
aden | +0.021 |
cheated | +0.021 |
ane | +0.020 |
Neg logit contributions | |
sn | -0.020 |
Ana | -0.018 |
mary | -0.018 |
Pr | -0.018 |
knees | -0.018 |
Token | hell |
Token ID | 12758 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
gol | +0.151 |
David | +0.093 |
aden | +0.089 |
cheated | +0.084 |
ival | +0.074 |
Neg logit contributions | |
mary | -0.261 |
cel | -0.256 |
isa | -0.256 |
elope | -0.252 |
we | -0.251 |
Token | s |
Token ID | 82 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
gol | +0.133 |
David | +0.114 |
aden | +0.111 |
cheated | +0.106 |
aw | +0.106 |
Neg logit contributions | |
mary | -0.039 |
bing | -0.038 |
Sn | -0.037 |
isa | -0.037 |
elope | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
bing | +0.002 |
mary | +0.002 |
sn | +0.002 |
Sn | +0.002 |
elope | +0.002 |
Neg logit contributions | |
gol | -0.008 |
David | -0.007 |
aden | -0.007 |
ival | -0.007 |
cheated | -0.007 |
Token | |
Token ID | 220 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
gol | +0.022 |
aw | +0.018 |
aden | +0.018 |
cheated | +0.018 |
David | +0.018 |
Neg logit contributions | |
Sn | -0.011 |
Pr | -0.011 |
elope | -0.011 |
isa | -0.010 |
Chick | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
Sn | +0.017 |
Pr | +0.017 |
elope | +0.016 |
Chick | +0.016 |
mary | +0.015 |
Neg logit contributions | |
gol | -0.057 |
tant | -0.045 |
cheated | -0.044 |
aden | -0.044 |
aw | -0.044 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
bing | +0.024 |
isa | +0.019 |
mary | +0.018 |
we | +0.017 |
Sn | +0.016 |
Neg logit contributions | |
gol | -0.085 |
David | -0.074 |
aden | -0.072 |
cheated | -0.071 |
ival | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
isa | +0.040 |
cel | +0.040 |
Sn | +0.039 |
elope | +0.039 |
pap | +0.039 |
Neg logit contributions | |
gol | -0.081 |
aw | -0.067 |
aden | -0.065 |
David | -0.065 |
cheated | -0.064 |
Token | tick |
Token ID | 4378 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
gol | +0.017 |
cheated | +0.013 |
aden | +0.013 |
David | +0.013 |
aw | +0.013 |
Neg logit contributions | |
isa | -0.008 |
elope | -0.008 |
cel | -0.008 |
pap | -0.007 |
Chick | -0.007 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
isa | +0.045 |
cel | +0.045 |
Sn | +0.045 |
elope | +0.045 |
pap | +0.045 |
Neg logit contributions | |
gol | -0.062 |
aw | -0.049 |
aden | -0.048 |
David | -0.048 |
cheated | -0.046 |
Token | each |
Token ID | 1123 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
isa | +0.033 |
cel | +0.033 |
Sn | +0.032 |
elope | +0.032 |
pap | +0.032 |
Neg logit contributions | |
gol | -0.069 |
aw | -0.057 |
aden | -0.056 |
David | -0.056 |
cheated | -0.055 |
Token | other |
Token ID | 584 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
gol | +0.085 |
David | +0.068 |
aden | +0.068 |
aw | +0.067 |
cheated | +0.065 |
Neg logit contributions | |
isa | -0.047 |
elope | -0.046 |
Sn | -0.046 |
Pr | -0.045 |
cel | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
gol | +0.251 |
aw | +0.212 |
aden | +0.205 |
cheated | +0.201 |
ax | +0.196 |
Neg logit contributions | |
pap | -0.134 |
cel | -0.133 |
isa | -0.131 |
roast | -0.126 |
Chick | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
gol | +0.007 |
aden | +0.005 |
aw | +0.005 |
David | +0.005 |
cheated | +0.005 |
Neg logit contributions | |
Sn | -0.004 |
elope | -0.004 |
Pr | -0.003 |
isa | -0.003 |
cel | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.006 |
aden | +0.006 |
cheated | +0.006 |
David | +0.006 |
Neg logit contributions | |
elope | -0.004 |
Sn | -0.004 |
isa | -0.004 |
Pr | -0.003 |
Chick | -0.003 |
Token | Finally |
Token ID | 11158 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Sn | +0.008 |
isa | +0.008 |
elope | +0.008 |
cel | +0.008 |
bing | +0.007 |
Neg logit contributions | |
gol | -0.016 |
aden | -0.013 |
aw | -0.013 |
David | -0.013 |
cheated | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
gol | +0.015 |
aw | +0.012 |
David | +0.012 |
aden | +0.012 |
cheated | +0.011 |
Neg logit contributions | |
isa | -0.007 |
cel | -0.007 |
elope | -0.007 |
Sn | -0.007 |
pap | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
gol | +0.060 |
ival | +0.046 |
aden | +0.045 |
David | +0.044 |
aw | +0.043 |
Neg logit contributions | |
Pr | -0.041 |
Sn | -0.041 |
sn | -0.039 |
isa | -0.039 |
pap | -0.038 |
Token | feet |
Token ID | 3625 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
gol | +0.069 |
aw | +0.058 |
David | +0.058 |
aden | +0.058 |
ival | +0.057 |
Neg logit contributions | |
pap | -0.016 |
elope | -0.016 |
isa | -0.016 |
Sn | -0.016 |
cel | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
gol | +0.046 |
David | +0.038 |
aden | +0.038 |
aw | +0.037 |
ival | +0.037 |
Neg logit contributions | |
Sn | -0.015 |
bing | -0.015 |
sn | -0.014 |
isa | -0.014 |
Pr | -0.014 |
Token | threw |
Token ID | 9617 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
gol | +0.022 |
aw | +0.018 |
aden | +0.018 |
David | +0.017 |
cheated | +0.017 |
Neg logit contributions | |
isa | -0.012 |
cel | -0.012 |
elope | -0.012 |
Sn | -0.012 |
pap | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
gol | +0.028 |
David | +0.024 |
ival | +0.024 |
aden | +0.023 |
ane | +0.023 |
Neg logit contributions | |
Sn | -0.011 |
sn | -0.010 |
one | -0.010 |
Pr | -0.009 |
side | -0.009 |
Token | tant |
Token ID | 24246 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
bit | +0.010 |
sn | +0.008 |
b | +0.008 |
pur | +0.007 |
pose | +0.007 |
Neg logit contributions | |
gol | -0.015 |
David | -0.014 |
aden | -0.014 |
aw | -0.013 |
ateful | -0.013 |
Token | rum |
Token ID | 6582 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
gol | +0.196 |
aw | +0.150 |
aden | +0.149 |
David | +0.147 |
cheated | +0.142 |
Neg logit contributions | |
Sn | -0.202 |
cel | -0.198 |
pap | -0.195 |
elope | -0.194 |
roast | -0.192 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
bing | +0.007 |
Sn | +0.007 |
elope | +0.007 |
isa | +0.007 |
we | +0.007 |
Neg logit contributions | |
gol | -0.027 |
David | -0.023 |
aden | -0.023 |
ival | -0.022 |
aw | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
gol | +0.019 |
aden | +0.016 |
ival | +0.015 |
aw | +0.015 |
ane | +0.015 |
Neg logit contributions | |
Sn | -0.008 |
Pr | -0.008 |
Luna | -0.008 |
Milo | -0.008 |
Bee | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
gol | +0.008 |
aden | +0.007 |
aw | +0.007 |
trophies | +0.006 |
cheated | +0.006 |
Neg logit contributions | |
Sn | -0.003 |
Pr | -0.003 |
elope | -0.003 |
Chick | -0.003 |
Luna | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Sn | +0.007 |
elope | +0.007 |
isa | +0.007 |
Pr | +0.007 |
pap | +0.007 |
Neg logit contributions | |
gol | -0.016 |
aden | -0.013 |
aw | -0.012 |
cheated | -0.012 |
ival | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Sn | +0.014 |
isa | +0.013 |
elope | +0.013 |
cel | +0.013 |
pap | +0.013 |
Neg logit contributions | |
gol | -0.034 |
aden | -0.028 |
David | -0.027 |
aw | -0.027 |
ival | -0.026 |
Token | sail |
Token ID | 14936 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
gol | +0.064 |
aw | +0.053 |
aden | +0.053 |
David | +0.053 |
cheated | +0.052 |
Neg logit contributions | |
isa | -0.022 |
cel | -0.021 |
bing | -0.021 |
elope | -0.020 |
pap | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
gol | +0.067 |
David | +0.059 |
aden | +0.058 |
cheated | +0.055 |
ax | +0.054 |
Neg logit contributions | |
Sn | -0.019 |
mary | -0.019 |
sn | -0.017 |
bing | -0.016 |
Ruby | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
gol | +0.011 |
aden | +0.009 |
David | +0.009 |
cheated | +0.009 |
aw | +0.009 |
Neg logit contributions | |
Sn | -0.004 |
isa | -0.004 |
elope | -0.004 |
cel | -0.004 |
mary | -0.004 |
Token | high |
Token ID | 1029 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
gol | +0.045 |
aw | +0.036 |
David | +0.036 |
aden | +0.036 |
cheated | +0.034 |
Neg logit contributions | |
Sn | -0.028 |
cel | -0.028 |
isa | -0.028 |
pap | -0.028 |
elope | -0.028 |
Token | seas |
Token ID | 21547 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
gol | +0.071 |
David | +0.057 |
aden | +0.057 |
aw | +0.057 |
cheated | +0.055 |
Neg logit contributions | |
isa | -0.041 |
Sn | -0.041 |
elope | -0.041 |
cel | -0.040 |
pap | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
gol | +0.220 |
David | +0.170 |
aden | +0.169 |
aw | +0.167 |
cheated | +0.163 |
Neg logit contributions | |
isa | -0.173 |
cel | -0.171 |
elope | -0.171 |
Sn | -0.171 |
bing | -0.167 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
gol | +0.005 |
aw | +0.004 |
aden | +0.004 |
David | +0.004 |
cheated | +0.004 |
Neg logit contributions | |
Sn | -0.003 |
cel | -0.003 |
Pr | -0.003 |
Chick | -0.003 |
elope | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
gol | +0.021 |
aw | +0.017 |
aden | +0.017 |
David | +0.017 |
cheated | +0.017 |
Neg logit contributions | |
Sn | -0.011 |
cel | -0.011 |
isa | -0.011 |
elope | -0.011 |
pap | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
gol | +0.033 |
aw | +0.026 |
cheated | +0.026 |
David | +0.026 |
aden | +0.026 |
Neg logit contributions | |
isa | -0.018 |
cel | -0.018 |
elope | -0.018 |
mary | -0.017 |
bing | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
cel | +0.007 |
isa | +0.006 |
elope | +0.006 |
Sn | +0.006 |
mary | +0.006 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
David | -0.007 |
aden | -0.007 |
happened | -0.007 |
Token | decorated |
Token ID | 24789 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
gol | +0.033 |
aden | +0.028 |
David | +0.028 |
aw | +0.027 |
ival | +0.027 |
Neg logit contributions | |
sn | -0.014 |
roast | -0.014 |
pap | -0.014 |
elope | -0.013 |
knees | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
gol | +0.023 |
aden | +0.018 |
David | +0.018 |
aw | +0.018 |
cheated | +0.018 |
Neg logit contributions | |
Sn | -0.014 |
isa | -0.014 |
elope | -0.014 |
pap | -0.014 |
bing | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +9.78e-02 |
Pos logit contributions | |
gol | +0.010 |
aw | +0.009 |
cheated | +0.009 |
trophies | +0.008 |
he | +0.008 |
Neg logit contributions | |
cel | -0.006 |
isa | -0.006 |
pap | -0.006 |
elope | -0.005 |
Sn | -0.005 |
Token | shells |
Token ID | 19679 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
gol | +0.005 |
ival | +0.004 |
aden | +0.004 |
David | +0.004 |
ane | +0.004 |
Neg logit contributions | |
sn | -0.002 |
pap | -0.002 |
roast | -0.002 |
Pr | -0.002 |
pur | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
gol | +0.165 |
David | +0.144 |
aden | +0.140 |
ival | +0.137 |
Goal | +0.135 |
Neg logit contributions | |
mary | -0.032 |
sn | -0.030 |
Sn | -0.029 |
bing | -0.028 |
Pr | -0.028 |
Token | seaw |
Token ID | 32085 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
gol | +0.045 |
David | +0.037 |
aden | +0.036 |
ival | +0.036 |
he | +0.035 |
Neg logit contributions | |
pap | -0.031 |
sn | -0.030 |
roast | -0.029 |
knees | -0.029 |
Moon | -0.028 |
Token | eed |
Token ID | 2308 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
gol | +0.204 |
David | +0.154 |
aden | +0.153 |
cheated | +0.148 |
aw | +0.146 |
Neg logit contributions | |
cel | -0.188 |
isa | -0.185 |
pap | -0.184 |
elope | -0.181 |
bing | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
gol | +0.094 |
David | +0.082 |
aden | +0.080 |
ival | +0.077 |
aw | +0.076 |
Neg logit contributions | |
mary | -0.020 |
Sn | -0.019 |
bing | -0.019 |
pap | -0.019 |
sn | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
gol | +0.014 |
aden | +0.012 |
aw | +0.012 |
David | +0.011 |
ival | +0.011 |
Neg logit contributions | |
Sn | -0.006 |
Pr | -0.005 |
elope | -0.005 |
Chick | -0.005 |
pap | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
sn | +0.017 |
isa | +0.016 |
pap | +0.016 |
roast | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
gol | -0.036 |
David | -0.030 |
aw | -0.030 |
aden | -0.029 |
arl | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
gol | +0.041 |
aden | +0.031 |
aw | +0.031 |
David | +0.031 |
ival | +0.029 |
Neg logit contributions | |
Sn | -0.036 |
isa | -0.036 |
elope | -0.036 |
pap | -0.036 |
cel | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
gol | +0.005 |
aw | +0.004 |
David | +0.004 |
cheated | +0.004 |
happened | +0.004 |
Neg logit contributions | |
isa | -0.004 |
elope | -0.004 |
cel | -0.004 |
bing | -0.004 |
Sn | -0.004 |
Token | Hi |
Token ID | 17250 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
cel | +0.032 |
isa | +0.032 |
Sn | +0.032 |
pap | +0.032 |
elope | +0.032 |
Neg logit contributions | |
gol | -0.031 |
aw | -0.024 |
David | -0.023 |
aden | -0.022 |
cheated | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
gol | +0.003 |
aw | +0.002 |
aden | +0.002 |
David | +0.002 |
cheated | +0.002 |
Neg logit contributions | |
isa | -0.001 |
cel | -0.001 |
elope | -0.001 |
Sn | -0.001 |
bing | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
isa | +0.034 |
cel | +0.034 |
elope | +0.034 |
Sn | +0.034 |
pap | +0.033 |
Neg logit contributions | |
gol | -0.055 |
aw | -0.044 |
aden | -0.044 |
David | -0.044 |
cheated | -0.042 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
gol | +0.017 |
aden | +0.014 |
David | +0.014 |
aw | +0.014 |
ival | +0.013 |
Neg logit contributions | |
elope | -0.010 |
cel | -0.010 |
Sn | -0.010 |
sn | -0.010 |
isa | -0.010 |
Token | Bee |
Token ID | 24719 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
isa | +0.089 |
cel | +0.089 |
elope | +0.088 |
Sn | +0.088 |
pap | +0.087 |
Neg logit contributions | |
gol | -0.108 |
aw | -0.084 |
aden | -0.082 |
David | -0.082 |
cheated | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
cel | +0.167 |
bing | +0.160 |
roast | +0.151 |
isa | +0.150 |
knees | +0.150 |
Neg logit contributions | |
gol | -0.249 |
aw | -0.212 |
ax | -0.192 |
aden | -0.188 |
cheated | -0.187 |
Token | Do |
Token ID | 2141 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
bing | +0.032 |
isa | +0.031 |
pap | +0.030 |
cel | +0.030 |
elope | +0.030 |
Neg logit contributions | |
gol | -0.033 |
aw | -0.024 |
aden | -0.023 |
cheated | -0.023 |
David | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
gol | +0.042 |
aw | +0.034 |
David | +0.033 |
aden | +0.033 |
cheated | +0.032 |
Neg logit contributions | |
isa | -0.028 |
cel | -0.027 |
Sn | -0.027 |
elope | -0.027 |
bing | -0.027 |
Token | want |
Token ID | 765 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
gol | +0.048 |
David | +0.039 |
aw | +0.038 |
aden | +0.038 |
ival | +0.037 |
Neg logit contributions | |
sn | -0.031 |
isa | -0.030 |
elope | -0.030 |
cel | -0.030 |
pap | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
gol | +0.061 |
aw | +0.050 |
chalk | +0.048 |
happened | +0.047 |
cheated | +0.046 |
Neg logit contributions | |
isa | -0.062 |
elope | -0.062 |
bing | -0.062 |
cel | -0.061 |
Sn | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
cel | +0.019 |
pap | +0.019 |
Sn | +0.019 |
isa | +0.018 |
elope | +0.018 |
Neg logit contributions | |
gol | -0.040 |
aw | -0.034 |
David | -0.032 |
aden | -0.032 |
cheated | -0.032 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
gol | +0.012 |
aw | +0.009 |
David | +0.009 |
aden | +0.009 |
cheated | +0.009 |
Neg logit contributions | |
bing | -0.009 |
isa | -0.009 |
pap | -0.009 |
cel | -0.009 |
Sn | -0.009 |
Token | name |
Token ID | 1438 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
isa | +0.046 |
Sn | +0.046 |
cel | +0.045 |
elope | +0.045 |
pap | +0.045 |
Neg logit contributions | |
gol | -0.063 |
aw | -0.049 |
aden | -0.049 |
David | -0.049 |
cheated | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
gol | +0.061 |
aw | +0.051 |
aden | +0.050 |
David | +0.050 |
cheated | +0.049 |
Neg logit contributions | |
isa | -0.026 |
cel | -0.026 |
Sn | -0.026 |
elope | -0.026 |
pap | -0.026 |
Token | El |
Token ID | 2574 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
gol | +0.020 |
aw | +0.016 |
aden | +0.015 |
David | +0.015 |
cheated | +0.015 |
Neg logit contributions | |
isa | -0.014 |
cel | -0.014 |
Sn | -0.014 |
elope | -0.014 |
pap | -0.014 |
Token | isa |
Token ID | 9160 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
Sn | +0.109 |
cel | +0.109 |
pap | +0.107 |
bing | +0.105 |
elope | +0.104 |
Neg logit contributions | |
gol | -0.217 |
aw | -0.184 |
aden | -0.177 |
David | -0.171 |
ax | -0.170 |
Token | and |
Token ID | 290 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
bing | +0.181 |
convince | +0.167 |
Sn | +0.166 |
cel | +0.164 |
roast | +0.163 |
Neg logit contributions | |
gol | -0.205 |
aw | -0.200 |
aden | -0.164 |
happened | -0.164 |
Tommy | -0.162 |
Token | she |
Token ID | 673 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
gol | +0.028 |
aw | +0.022 |
aden | +0.022 |
David | +0.022 |
cheated | +0.022 |
Neg logit contributions | |
cel | -0.016 |
isa | -0.016 |
elope | -0.016 |
Sn | -0.016 |
bing | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
gol | +0.012 |
cheated | +0.009 |
aw | +0.009 |
happened | +0.009 |
aden | +0.008 |
Neg logit contributions | |
bing | -0.013 |
isa | -0.013 |
pap | -0.013 |
Pr | -0.013 |
cel | -0.013 |
Token | three |
Token ID | 1115 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
gol | +0.024 |
cheated | +0.019 |
aw | +0.018 |
Tommy | +0.017 |
aden | +0.017 |
Neg logit contributions | |
bing | -0.016 |
isa | -0.016 |
cel | -0.016 |
we | -0.015 |
elope | -0.015 |
Token | years |
Token ID | 812 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
roast | +0.038 |
Sn | +0.038 |
Stacy | +0.037 |
pap | +0.037 |
cup | +0.037 |
Neg logit contributions | |
aw | -0.063 |
gol | -0.060 |
tant | -0.052 |
aden | -0.052 |
trophies | -0.051 |
Token | friendly |
Token ID | 8030 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
isa | +0.007 |
cel | +0.007 |
bing | +0.007 |
elope | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.007 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
gol | +0.074 |
aw | +0.059 |
aden | +0.055 |
David | +0.055 |
cheated | +0.054 |
Neg logit contributions | |
isa | -0.055 |
cel | -0.055 |
bing | -0.054 |
Sn | -0.053 |
elope | -0.053 |
Token | offered |
Token ID | 4438 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
cel | +0.026 |
Sn | +0.026 |
bing | +0.026 |
isa | +0.026 |
pap | +0.025 |
Neg logit contributions | |
gol | -0.037 |
aw | -0.030 |
aden | -0.029 |
cheated | -0.029 |
David | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
cel | +0.013 |
bing | +0.013 |
isa | +0.013 |
elope | +0.012 |
roast | +0.012 |
Neg logit contributions | |
gol | -0.015 |
aw | -0.013 |
happened | -0.012 |
ax | -0.012 |
cheated | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
isa | +0.020 |
cel | +0.019 |
bing | +0.019 |
elope | +0.018 |
mary | +0.018 |
Neg logit contributions | |
gol | -0.036 |
aden | -0.029 |
David | -0.029 |
Tommy | -0.029 |
cheated | -0.028 |
Token | Honey |
Token ID | 21788 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
cel | +0.028 |
isa | +0.027 |
bing | +0.027 |
Sn | +0.026 |
mary | +0.026 |
Neg logit contributions | |
gol | -0.037 |
aw | -0.032 |
David | -0.030 |
aden | -0.029 |
cheated | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
cel | +0.166 |
eyel | +0.150 |
isa | +0.149 |
we | +0.147 |
bing | +0.143 |
Neg logit contributions | |
gol | -0.222 |
aw | -0.188 |
ax | -0.181 |
aden | -0.174 |
he | -0.172 |
Token | guide |
Token ID | 5698 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
cel | +0.081 |
isa | +0.080 |
bing | +0.077 |
Chick | +0.075 |
Sn | +0.074 |
Neg logit contributions | |
gol | -0.110 |
aw | -0.087 |
aden | -0.086 |
David | -0.084 |
cheated | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
cel | +0.009 |
isa | +0.008 |
Sn | +0.008 |
bing | +0.008 |
elope | +0.008 |
Neg logit contributions | |
gol | -0.017 |
aw | -0.015 |
aden | -0.014 |
David | -0.014 |
ax | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
we | +0.003 |
isa | +0.003 |
bing | +0.003 |
cel | +0.003 |
elope | +0.003 |
Neg logit contributions | |
gol | -0.004 |
aw | -0.004 |
Tommy | -0.003 |
ax | -0.003 |
arl | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
bing | +0.025 |
cel | +0.025 |
isa | +0.024 |
Sn | +0.024 |
Pr | +0.023 |
Neg logit contributions | |
gol | -0.034 |
aw | -0.027 |
aden | -0.026 |
David | -0.026 |
cheated | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
cel | +0.012 |
bing | +0.012 |
we | +0.012 |
roast | +0.011 |
mary | +0.011 |
Neg logit contributions | |
gol | -0.012 |
aw | -0.011 |
happened | -0.011 |
cheated | -0.011 |
ival | -0.010 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
gol | +0.049 |
aden | +0.042 |
David | +0.041 |
aw | +0.040 |
ax | +0.040 |
Neg logit contributions | |
pap | -0.025 |
elope | -0.024 |
sn | -0.024 |
Pr | -0.024 |
Flower | -0.024 |
Token | began |
Token ID | 2540 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Sn | +0.030 |
isa | +0.029 |
cel | +0.029 |
pap | +0.029 |
elope | +0.028 |
Neg logit contributions | |
gol | -0.042 |
aw | -0.035 |
aden | -0.033 |
David | -0.033 |
cheated | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
cel | +0.019 |
isa | +0.019 |
Sn | +0.019 |
elope | +0.019 |
bing | +0.018 |
Neg logit contributions | |
gol | -0.024 |
aw | -0.019 |
David | -0.019 |
happened | -0.018 |
aden | -0.018 |
Token | tell |
Token ID | 1560 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
isa | +0.020 |
cel | +0.020 |
Sn | +0.019 |
bing | +0.019 |
we | +0.019 |
Neg logit contributions | |
gol | -0.046 |
David | -0.037 |
aden | -0.037 |
cheated | -0.037 |
aw | -0.037 |
Token | Pen |
Token ID | 7507 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
cel | +0.044 |
bing | +0.042 |
roast | +0.039 |
mary | +0.039 |
we | +0.039 |
Neg logit contributions | |
gol | -0.051 |
aw | -0.050 |
cheated | -0.043 |
happened | -0.043 |
he | -0.043 |
Token | elope |
Token ID | 47329 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
bing | +0.088 |
cel | +0.085 |
roast | +0.083 |
Sn | +0.078 |
bed | +0.070 |
Neg logit contributions | |
aw | -0.270 |
gol | -0.258 |
ax | -0.240 |
David | -0.239 |
happened | -0.237 |
Token | it |
Token ID | 340 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
cel | +0.152 |
isa | +0.148 |
Sn | +0.146 |
bing | +0.146 |
elope | +0.140 |
Neg logit contributions | |
gol | -0.238 |
aw | -0.203 |
aden | -0.194 |
cheated | -0.192 |
David | -0.191 |
Token | 's |
Token ID | 338 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
cel | +0.010 |
isa | +0.010 |
Sn | +0.010 |
bing | +0.010 |
pap | +0.010 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.016 |
happened | -0.015 |
cheated | -0.015 |
aden | -0.015 |
Token | story |
Token ID | 1621 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
cel | +0.053 |
isa | +0.053 |
Sn | +0.053 |
bing | +0.052 |
elope | +0.050 |
Neg logit contributions | |
gol | -0.070 |
aw | -0.053 |
aden | -0.053 |
David | -0.053 |
cheated | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
elope | +0.030 |
isa | +0.030 |
cel | +0.030 |
Sn | +0.030 |
sn | +0.029 |
Neg logit contributions | |
gol | -0.083 |
aden | -0.068 |
David | -0.067 |
aw | -0.066 |
cheated | -0.064 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
gol | +0.044 |
ival | +0.039 |
David | +0.039 |
aden | +0.038 |
cheated | +0.037 |
Neg logit contributions | |
pap | -0.015 |
Pr | -0.014 |
elope | -0.013 |
sn | -0.013 |
isa | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
gol | +0.024 |
aden | +0.020 |
aw | +0.020 |
David | +0.020 |
ival | +0.019 |
Neg logit contributions | |
isa | -0.010 |
elope | -0.010 |
cel | -0.010 |
Sn | -0.010 |
pap | -0.010 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.007 |
aden | +0.007 |
ival | +0.007 |
cheated | +0.007 |
Neg logit contributions | |
Sn | -0.004 |
Pr | -0.004 |
elope | -0.004 |
Moon | -0.003 |
pap | -0.003 |
Token | name |
Token ID | 1438 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
pap | +0.037 |
elope | +0.034 |
Sn | +0.033 |
Flower | +0.032 |
Moon | +0.032 |
Neg logit contributions | |
gol | -0.089 |
David | -0.077 |
aden | -0.077 |
aw | -0.076 |
ax | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -7.07e-04 |
Pos logit contributions | |
gol | +0.061 |
aden | +0.050 |
David | +0.050 |
aw | +0.048 |
ax | +0.048 |
Neg logit contributions | |
Sn | -0.020 |
cel | -0.019 |
elope | -0.019 |
sn | -0.019 |
pap | -0.019 |
Token | Cat |
Token ID | 5181 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
Sn | +0.000 |
pap | +0.000 |
Pr | +0.000 |
Chick | +0.000 |
elope | +0.000 |
Neg logit contributions | |
gol | -0.000 |
ival | -0.000 |
aden | -0.000 |
aw | -0.000 |
cheated | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
roast | +0.136 |
cel | +0.135 |
pap | +0.135 |
bing | +0.134 |
isa | +0.133 |
Neg logit contributions | |
gol | -0.238 |
aw | -0.214 |
aden | -0.197 |
ax | -0.191 |
David | -0.191 |
Token | Cat |
Token ID | 5181 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
bing | +0.001 |
cel | +0.001 |
isa | +0.001 |
pap | +0.001 |
we | +0.001 |
Neg logit contributions | |
gol | -0.002 |
aw | -0.002 |
David | -0.002 |
aden | -0.002 |
cheated | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
pap | +0.081 |
cel | +0.080 |
Sn | +0.080 |
bing | +0.079 |
isa | +0.079 |
Neg logit contributions | |
gol | -0.141 |
aw | -0.121 |
aden | -0.115 |
cheated | -0.114 |
David | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
gol | +0.042 |
aden | +0.034 |
David | +0.033 |
ival | +0.033 |
aw | +0.033 |
Neg logit contributions | |
pap | -0.017 |
sn | -0.017 |
Pr | -0.017 |
Sn | -0.017 |
elope | -0.017 |
Token | special |
Token ID | 2041 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
pap | +0.005 |
elope | +0.005 |
isa | +0.005 |
Sn | +0.005 |
cel | +0.005 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.007 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
gol | +0.049 |
aden | +0.042 |
David | +0.041 |
aw | +0.040 |
ax | +0.040 |
Neg logit contributions | |
pap | -0.025 |
elope | -0.024 |
sn | -0.024 |
Pr | -0.024 |
Flower | -0.024 |
Token | began |
Token ID | 2540 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Sn | +0.030 |
isa | +0.029 |
cel | +0.029 |
pap | +0.029 |
elope | +0.028 |
Neg logit contributions | |
gol | -0.042 |
aw | -0.035 |
aden | -0.033 |
David | -0.033 |
cheated | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
cel | +0.019 |
isa | +0.019 |
Sn | +0.019 |
elope | +0.019 |
bing | +0.018 |
Neg logit contributions | |
gol | -0.024 |
aw | -0.019 |
David | -0.019 |
happened | -0.018 |
aden | -0.018 |
Token | tell |
Token ID | 1560 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
isa | +0.020 |
cel | +0.020 |
Sn | +0.019 |
bing | +0.019 |
we | +0.019 |
Neg logit contributions | |
gol | -0.046 |
David | -0.037 |
aden | -0.037 |
cheated | -0.037 |
aw | -0.037 |
Token | Pen |
Token ID | 7507 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
cel | +0.044 |
bing | +0.042 |
roast | +0.039 |
mary | +0.039 |
we | +0.039 |
Neg logit contributions | |
gol | -0.051 |
aw | -0.050 |
cheated | -0.043 |
happened | -0.043 |
he | -0.043 |
Token | elope |
Token ID | 47329 |
Feature activation | -5.67e+00 |
Pos logit contributions | |
bing | +0.088 |
cel | +0.085 |
roast | +0.083 |
Sn | +0.078 |
bed | +0.070 |
Neg logit contributions | |
aw | -0.270 |
gol | -0.258 |
ax | -0.240 |
David | -0.239 |
happened | -0.237 |
Token | it |
Token ID | 340 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
cel | +0.152 |
isa | +0.148 |
Sn | +0.146 |
bing | +0.146 |
elope | +0.140 |
Neg logit contributions | |
gol | -0.238 |
aw | -0.203 |
aden | -0.194 |
cheated | -0.192 |
David | -0.191 |
Token | 's |
Token ID | 338 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
cel | +0.010 |
isa | +0.010 |
Sn | +0.010 |
bing | +0.010 |
pap | +0.010 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.016 |
happened | -0.015 |
cheated | -0.015 |
aden | -0.015 |
Token | story |
Token ID | 1621 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
cel | +0.053 |
isa | +0.053 |
Sn | +0.053 |
bing | +0.052 |
elope | +0.050 |
Neg logit contributions | |
gol | -0.070 |
aw | -0.053 |
aden | -0.053 |
David | -0.053 |
cheated | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
elope | +0.030 |
isa | +0.030 |
cel | +0.030 |
Sn | +0.030 |
sn | +0.029 |
Neg logit contributions | |
gol | -0.083 |
aden | -0.068 |
David | -0.067 |
aw | -0.066 |
cheated | -0.064 |
Token | |
Token ID | 220 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
aw | +0.013 |
gol | +0.013 |
Tommy | +0.012 |
he | +0.012 |
ival | +0.012 |
Neg logit contributions | |
bing | -0.024 |
we | -0.023 |
cel | -0.023 |
ci | -0.023 |
isa | -0.021 |
Token | YOU |
Token ID | 36981 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
gol | +0.009 |
aw | +0.008 |
aden | +0.008 |
ival | +0.007 |
David | +0.007 |
Neg logit contributions | |
Sn | -0.005 |
isa | -0.005 |
bing | -0.005 |
we | -0.005 |
cel | -0.005 |
Token | ARE |
Token ID | 15986 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
cel | +0.057 |
isa | +0.056 |
Sn | +0.055 |
elope | +0.055 |
sn | +0.053 |
Neg logit contributions | |
gol | -0.062 |
aden | -0.047 |
David | -0.046 |
aw | -0.045 |
cheated | -0.043 |
Token | MA |
Token ID | 8779 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Sn | +0.054 |
isa | +0.053 |
cel | +0.053 |
pap | +0.053 |
elope | +0.052 |
Neg logit contributions | |
gol | -0.084 |
David | -0.066 |
aden | -0.066 |
aw | -0.066 |
cheated | -0.064 |
Token | KING |
Token ID | 37286 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
pap | +0.066 |
isa | +0.066 |
Sn | +0.066 |
elope | +0.066 |
cel | +0.066 |
Neg logit contributions | |
gol | -0.080 |
aw | -0.063 |
David | -0.060 |
aden | -0.060 |
ival | -0.058 |
Token | A |
Token ID | 317 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Sn | +0.058 |
cel | +0.058 |
elope | +0.056 |
isa | +0.056 |
pap | +0.055 |
Neg logit contributions | |
gol | -0.106 |
aden | -0.087 |
aw | -0.086 |
David | -0.086 |
cheated | -0.083 |
Token | M |
Token ID | 337 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
Sn | +0.045 |
sn | +0.045 |
cel | +0.045 |
isa | +0.044 |
Pr | +0.044 |
Neg logit contributions | |
gol | -0.078 |
David | -0.064 |
aden | -0.064 |
aw | -0.063 |
ax | -0.060 |
Token | ESS |
Token ID | 7597 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
isa | +0.176 |
Sn | +0.170 |
cel | +0.170 |
pap | +0.168 |
elope | +0.168 |
Neg logit contributions | |
gol | -0.230 |
David | -0.178 |
cheated | -0.177 |
aw | -0.176 |
aden | -0.175 |
Token | ! |
Token ID | 0 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
cel | +0.013 |
isa | +0.013 |
Sn | +0.013 |
elope | +0.013 |
pap | +0.013 |
Neg logit contributions | |
gol | -0.029 |
David | -0.024 |
aden | -0.024 |
aw | -0.024 |
cheated | -0.023 |
Token | AND |
Token ID | 5357 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
isa | +0.001 |
cel | +0.001 |
Sn | +0.001 |
elope | +0.001 |
pap | +0.001 |
Neg logit contributions | |
gol | -0.002 |
aw | -0.002 |
aden | -0.002 |
David | -0.002 |
cheated | -0.002 |
Token | YOU |
Token ID | 7013 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Sn | +0.010 |
cel | +0.010 |
isa | +0.010 |
elope | +0.010 |
pap | +0.010 |
Neg logit contributions | |
gol | -0.016 |
aw | -0.012 |
aden | -0.012 |
David | -0.012 |
cheated | -0.012 |
Token | ARE |
Token ID | 15986 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
gol | +0.082 |
aw | +0.069 |
aden | +0.066 |
David | +0.065 |
cheated | +0.065 |
Neg logit contributions | |
pap | -0.051 |
isa | -0.050 |
bing | -0.050 |
Sn | -0.050 |
elope | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
Sn | +0.023 |
pap | +0.022 |
sn | +0.022 |
Pr | +0.022 |
Moon | +0.021 |
Neg logit contributions | |
gol | -0.053 |
aden | -0.043 |
aw | -0.043 |
ival | -0.043 |
cheated | -0.042 |
Token | bee |
Token ID | 20697 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
pap | +0.013 |
sn | +0.012 |
Moon | +0.012 |
Sn | +0.012 |
elope | +0.011 |
Neg logit contributions | |
gol | -0.022 |
aden | -0.019 |
aw | -0.019 |
David | -0.018 |
ax | -0.018 |
Token | came |
Token ID | 1625 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
Sn | +0.101 |
pap | +0.098 |
isa | +0.097 |
cel | +0.096 |
Pr | +0.095 |
Neg logit contributions | |
gol | -0.141 |
aw | -0.120 |
aden | -0.109 |
cheated | -0.108 |
David | -0.108 |
Token | flying |
Token ID | 7348 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
gol | +0.000 |
aw | +0.000 |
aden | +0.000 |
David | +0.000 |
ax | +0.000 |
Neg logit contributions | |
cel | -0.000 |
Sn | -0.000 |
isa | -0.000 |
elope | -0.000 |
pap | -0.000 |
Token | into |
Token ID | 656 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
isa | +0.023 |
Sn | +0.023 |
elope | +0.023 |
bing | +0.023 |
mary | +0.022 |
Neg logit contributions | |
gol | -0.061 |
aden | -0.051 |
David | -0.051 |
aw | -0.049 |
cheated | -0.049 |
Token | Honey |
Token ID | 21788 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Pr | +0.011 |
pap | +0.011 |
Sn | +0.010 |
isa | +0.010 |
Moon | +0.010 |
Neg logit contributions | |
gol | -0.031 |
aden | -0.026 |
ival | -0.026 |
David | -0.026 |
aw | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Sn | +0.131 |
cel | +0.130 |
eyel | +0.117 |
pap | +0.116 |
Ana | +0.116 |
Neg logit contributions | |
gol | -0.245 |
aw | -0.217 |
he | -0.192 |
ax | -0.189 |
aden | -0.187 |
Token | room |
Token ID | 2119 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
cel | +0.054 |
isa | +0.054 |
Sn | +0.054 |
elope | +0.052 |
pap | +0.052 |
Neg logit contributions | |
gol | -0.105 |
aw | -0.086 |
aden | -0.085 |
David | -0.084 |
cheated | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
isa | +0.011 |
Sn | +0.011 |
cel | +0.011 |
elope | +0.011 |
pap | +0.011 |
Neg logit contributions | |
gol | -0.028 |
aw | -0.024 |
aden | -0.023 |
David | -0.023 |
cheated | -0.023 |
Token | Honey |
Token ID | 21788 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
gol | +0.007 |
aw | +0.006 |
David | +0.006 |
aden | +0.006 |
Tommy | +0.006 |
Neg logit contributions | |
bing | -0.005 |
isa | -0.005 |
we | -0.004 |
cel | -0.004 |
elope | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Sn | +0.106 |
cel | +0.104 |
Pr | +0.100 |
pap | +0.099 |
isa | +0.099 |
Neg logit contributions | |
gol | -0.153 |
aw | -0.131 |
cheated | -0.121 |
David | -0.121 |
happened | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Sn | +0.019 |
cel | +0.019 |
isa | +0.018 |
bing | +0.018 |
elope | +0.018 |
Neg logit contributions | |
gol | -0.050 |
David | -0.042 |
aden | -0.042 |
aw | -0.041 |
ival | -0.040 |
Token | I |
Token ID | 314 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
isa | +0.028 |
bing | +0.027 |
elope | +0.027 |
pap | +0.026 |
we | +0.026 |
Neg logit contributions | |
gol | -0.031 |
aw | -0.024 |
aden | -0.024 |
cheated | -0.023 |
David | -0.023 |
Token | want |
Token ID | 765 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
gol | +0.053 |
David | +0.043 |
aw | +0.043 |
aden | +0.042 |
ival | +0.040 |
Neg logit contributions | |
cel | -0.039 |
elope | -0.039 |
Sn | -0.038 |
isa | -0.038 |
sn | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
gol | +0.070 |
aw | +0.055 |
chalk | +0.055 |
cheated | +0.055 |
Tommy | +0.055 |
Neg logit contributions | |
elope | -0.071 |
isa | -0.069 |
cel | -0.068 |
bing | -0.067 |
mary | -0.061 |
Token | prevent |
Token ID | 2948 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
isa | +0.019 |
elope | +0.018 |
bing | +0.017 |
cel | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
gol | -0.034 |
aden | -0.027 |
cheated | -0.027 |
David | -0.027 |
aw | -0.027 |
Token | Fl |
Token ID | 1610 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
isa | +0.071 |
elope | +0.071 |
cel | +0.070 |
pap | +0.067 |
mary | +0.067 |
Neg logit contributions | |
gol | -0.106 |
aw | -0.085 |
aden | -0.083 |
cheated | -0.083 |
David | -0.080 |
Token | uffy |
Token ID | 15352 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
pap | +0.225 |
cel | +0.218 |
isa | +0.218 |
Moon | +0.218 |
Pr | +0.216 |
Neg logit contributions | |
gol | -0.168 |
aw | -0.129 |
arl | -0.126 |
ane | -0.116 |
he | -0.114 |
Token | from |
Token ID | 422 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
isa | +0.138 |
elope | +0.133 |
pap | +0.132 |
cel | +0.131 |
Moon | +0.125 |
Neg logit contributions | |
gol | -0.250 |
aw | -0.205 |
cheated | -0.198 |
aden | -0.196 |
he | -0.193 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
isa | +0.036 |
elope | +0.036 |
cel | +0.035 |
mary | +0.033 |
Sn | +0.033 |
Neg logit contributions | |
gol | -0.074 |
aden | -0.059 |
aw | -0.059 |
cheated | -0.059 |
David | -0.059 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
isa | +0.069 |
elope | +0.069 |
cel | +0.068 |
Sn | +0.066 |
pap | +0.066 |
Neg logit contributions | |
gol | -0.117 |
aw | -0.093 |
aden | -0.093 |
David | -0.092 |
cheated | -0.090 |
Token | ." |
Token ID | 526 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
isa | +0.029 |
cel | +0.029 |
elope | +0.029 |
pap | +0.029 |
Sn | +0.028 |
Neg logit contributions | |
gol | -0.079 |
aw | -0.066 |
aden | -0.065 |
David | -0.064 |
cheated | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
gol | +0.029 |
aden | +0.023 |
aw | +0.022 |
David | +0.022 |
cheated | +0.022 |
Neg logit contributions | |
elope | -0.018 |
isa | -0.018 |
Sn | -0.017 |
cel | -0.017 |
pap | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
gol | +0.004 |
aw | +0.003 |
David | +0.003 |
aden | +0.003 |
ival | +0.003 |
Neg logit contributions | |
Sn | -0.003 |
cel | -0.003 |
pap | -0.003 |
isa | -0.003 |
elope | -0.003 |
Token | special |
Token ID | 2041 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
elope | +0.021 |
bing | +0.021 |
Chick | +0.020 |
cel | +0.020 |
isa | +0.020 |
Neg logit contributions | |
gol | -0.022 |
David | -0.017 |
aden | -0.017 |
aw | -0.017 |
ival | -0.017 |
Token | menu |
Token ID | 6859 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
gol | +0.036 |
David | +0.026 |
aw | +0.026 |
aden | +0.026 |
ival | +0.026 |
Neg logit contributions | |
elope | -0.039 |
Chick | -0.038 |
bing | -0.038 |
cel | -0.038 |
isa | -0.037 |
Token | prevented |
Token ID | 13351 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
gol | +0.051 |
aden | +0.043 |
arl | +0.042 |
David | +0.042 |
aw | +0.041 |
Neg logit contributions | |
sn | -0.017 |
isa | -0.017 |
elope | -0.017 |
Sn | -0.016 |
pap | -0.016 |
Token | Laura |
Token ID | 16753 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
cel | +0.033 |
isa | +0.033 |
Sn | +0.033 |
pap | +0.033 |
elope | +0.033 |
Neg logit contributions | |
gol | -0.054 |
aw | -0.044 |
aden | -0.043 |
David | -0.043 |
cheated | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
cel | +0.124 |
isa | +0.124 |
Sn | +0.120 |
elope | +0.119 |
pap | +0.119 |
Neg logit contributions | |
gol | -0.266 |
aw | -0.219 |
aden | -0.216 |
David | -0.214 |
cheated | -0.212 |
Token | Alice |
Token ID | 14862 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
pap | +0.039 |
isa | +0.039 |
elope | +0.039 |
Sn | +0.038 |
sn | +0.037 |
Neg logit contributions | |
gol | -0.082 |
aden | -0.067 |
aw | -0.067 |
David | -0.066 |
ival | -0.063 |
Token | from |
Token ID | 422 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
cel | +0.055 |
isa | +0.055 |
Sn | +0.054 |
elope | +0.053 |
pap | +0.053 |
Neg logit contributions | |
gol | -0.106 |
aw | -0.088 |
aden | -0.086 |
David | -0.086 |
cheated | -0.085 |
Token | having |
Token ID | 1719 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
gol | +0.012 |
aden | +0.010 |
aw | +0.010 |
David | +0.010 |
ival | +0.010 |
Neg logit contributions | |
isa | -0.004 |
Sn | -0.004 |
elope | -0.004 |
pap | -0.004 |
bing | -0.004 |
Token | an |
Token ID | 281 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Sn | +0.035 |
sn | +0.035 |
pap | +0.034 |
elope | +0.034 |
Pr | +0.033 |
Neg logit contributions | |
gol | -0.080 |
aden | -0.064 |
arl | -0.063 |
aw | -0.062 |
David | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Sn | +0.011 |
cel | +0.011 |
elope | +0.010 |
mary | +0.010 |
bing | +0.010 |
Neg logit contributions | |
gol | -0.045 |
David | -0.039 |
aden | -0.038 |
aw | -0.037 |
ival | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
gol | +0.012 |
aw | +0.010 |
Tommy | +0.010 |
cheated | +0.009 |
Tom | +0.009 |
Neg logit contributions | |
isa | -0.020 |
we | -0.019 |
bing | -0.019 |
elope | -0.018 |
cel | -0.018 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
gol | +0.017 |
cheated | +0.014 |
aw | +0.014 |
happened | +0.013 |
Tom | +0.012 |
Neg logit contributions | |
bing | -0.019 |
isa | -0.019 |
Sn | -0.019 |
cel | -0.019 |
Moon | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
gol | +0.075 |
Tommy | +0.066 |
cheated | +0.060 |
chalk | +0.060 |
happened | +0.058 |
Neg logit contributions | |
bing | -0.098 |
elope | -0.096 |
isa | -0.096 |
cel | -0.093 |
we | -0.089 |
Token | prevent |
Token ID | 2948 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
isa | +0.020 |
elope | +0.018 |
bing | +0.018 |
cel | +0.018 |
we | +0.017 |
Neg logit contributions | |
gol | -0.036 |
aden | -0.028 |
cheated | -0.028 |
chalk | -0.028 |
David | -0.028 |
Token | Fl |
Token ID | 1610 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
cel | +0.064 |
isa | +0.064 |
elope | +0.062 |
roast | +0.059 |
pap | +0.059 |
Neg logit contributions | |
gol | -0.101 |
aw | -0.085 |
cheated | -0.082 |
Tommy | -0.081 |
aden | -0.081 |
Token | uffy |
Token ID | 15352 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
pap | +0.221 |
cel | +0.218 |
Moon | +0.216 |
Pr | +0.214 |
isa | +0.214 |
Neg logit contributions | |
gol | -0.161 |
aw | -0.125 |
arl | -0.120 |
he | -0.111 |
ane | -0.111 |
Token | from |
Token ID | 422 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
isa | +0.127 |
cel | +0.122 |
elope | +0.122 |
pap | +0.121 |
Sn | +0.116 |
Neg logit contributions | |
gol | -0.255 |
aw | -0.207 |
aden | -0.205 |
cheated | -0.202 |
David | -0.198 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
isa | +0.032 |
elope | +0.032 |
cel | +0.032 |
Sn | +0.030 |
pap | +0.030 |
Neg logit contributions | |
gol | -0.072 |
aden | -0.058 |
David | -0.057 |
aw | -0.057 |
cheated | -0.057 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Sn | +0.062 |
pap | +0.061 |
Pr | +0.060 |
cel | +0.060 |
bing | +0.059 |
Neg logit contributions | |
gol | -0.118 |
aw | -0.096 |
David | -0.096 |
aden | -0.095 |
ival | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Sn | +0.024 |
isa | +0.024 |
cel | +0.024 |
elope | +0.024 |
pap | +0.024 |
Neg logit contributions | |
gol | -0.068 |
aw | -0.057 |
aden | -0.056 |
David | -0.056 |
cheated | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
isa | +0.014 |
cel | +0.014 |
Sn | +0.013 |
elope | +0.013 |
pap | +0.013 |
Neg logit contributions | |
gol | -0.034 |
aw | -0.028 |
aden | -0.028 |
David | -0.028 |
cheated | -0.027 |
Token | The |
Token ID | 383 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
bing | +0.005 |
we | +0.005 |
cel | +0.005 |
isa | +0.005 |
roast | +0.005 |
Neg logit contributions | |
gol | -0.005 |
aw | -0.004 |
Tommy | -0.004 |
ax | -0.004 |
aden | -0.004 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
isa | +0.024 |
cel | +0.024 |
bing | +0.023 |
Sn | +0.023 |
elope | +0.023 |
Neg logit contributions | |
gol | -0.035 |
aw | -0.028 |
aden | -0.027 |
David | -0.027 |
cheated | -0.026 |
Token | waved |
Token ID | 26834 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
cel | +0.039 |
bing | +0.038 |
Sn | +0.038 |
isa | +0.038 |
pap | +0.037 |
Neg logit contributions | |
gol | -0.060 |
aw | -0.051 |
cheated | -0.048 |
aden | -0.048 |
David | -0.047 |
Token | at |
Token ID | 379 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Sn | +0.010 |
pap | +0.010 |
Pr | +0.010 |
sn | +0.009 |
isa | +0.009 |
Neg logit contributions | |
gol | -0.019 |
David | -0.016 |
aden | -0.016 |
ival | -0.015 |
aw | -0.015 |
Token | Honey |
Token ID | 21788 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
cel | +0.008 |
elope | +0.007 |
isa | +0.007 |
roast | +0.007 |
bing | +0.007 |
Neg logit contributions | |
gol | -0.014 |
aw | -0.012 |
Tommy | -0.011 |
aden | -0.011 |
David | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
cel | +0.166 |
isa | +0.153 |
Sn | +0.152 |
eyel | +0.150 |
elope | +0.148 |
Neg logit contributions | |
gol | -0.210 |
aw | -0.178 |
ax | -0.162 |
aden | -0.161 |
cheated | -0.156 |
Token | said |
Token ID | 531 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
gol | +0.004 |
aw | +0.004 |
cheated | +0.003 |
happened | +0.003 |
David | +0.003 |
Neg logit contributions | |
cel | -0.003 |
isa | -0.003 |
bing | -0.003 |
we | -0.003 |
elope | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
Sn | +0.008 |
isa | +0.008 |
cel | +0.008 |
pap | +0.008 |
elope | +0.008 |
Neg logit contributions | |
gol | -0.018 |
aden | -0.015 |
aw | -0.014 |
David | -0.014 |
cheated | -0.014 |
Token | Hi |
Token ID | 17250 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
isa | +0.025 |
cel | +0.025 |
Sn | +0.025 |
elope | +0.025 |
pap | +0.025 |
Neg logit contributions | |
gol | -0.032 |
aw | -0.025 |
aden | -0.024 |
David | -0.024 |
cheated | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
isa | +0.002 |
elope | +0.002 |
roast | +0.002 |
cel | +0.001 |
bing | +0.001 |
Neg logit contributions | |
gol | -0.002 |
aw | -0.002 |
ax | -0.002 |
Tommy | -0.002 |
ival | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
isa | +0.034 |
cel | +0.034 |
Sn | +0.033 |
elope | +0.033 |
pap | +0.033 |
Neg logit contributions | |
gol | -0.091 |
aw | -0.075 |
aden | -0.075 |
David | -0.074 |
cheated | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
gol | +0.003 |
aw | +0.002 |
aden | +0.002 |
cheated | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Sn | -0.001 |
Pr | -0.001 |
Chick | -0.001 |
pap | -0.001 |
Ana | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
elope | +0.004 |
Sn | +0.003 |
Pr | +0.003 |
isa | +0.003 |
Chick | +0.003 |
Neg logit contributions | |
gol | -0.010 |
cheated | -0.008 |
aden | -0.008 |
aw | -0.008 |
tant | -0.007 |
Token | They |
Token ID | 2990 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
isa | +0.012 |
Sn | +0.012 |
elope | +0.012 |
Pr | +0.011 |
bing | +0.011 |
Neg logit contributions | |
gol | -0.030 |
aden | -0.025 |
aw | -0.024 |
cheated | -0.024 |
happened | -0.024 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
isa | +0.017 |
sn | +0.017 |
pap | +0.017 |
cel | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
gol | -0.044 |
David | -0.037 |
aden | -0.036 |
aw | -0.036 |
ival | -0.035 |
Token | Mama |
Token ID | 40084 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
cel | +0.030 |
isa | +0.030 |
elope | +0.030 |
Sn | +0.030 |
pap | +0.029 |
Neg logit contributions | |
gol | -0.047 |
aw | -0.038 |
aden | -0.038 |
David | -0.037 |
cheated | -0.036 |
Token | if |
Token ID | 611 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
isa | +0.119 |
Sn | +0.118 |
cel | +0.117 |
pap | +0.117 |
elope | +0.117 |
Neg logit contributions | |
gol | -0.270 |
aw | -0.221 |
aden | -0.219 |
David | -0.219 |
cheated | -0.212 |
Token | they |
Token ID | 484 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
isa | +0.018 |
cel | +0.018 |
Sn | +0.018 |
elope | +0.018 |
pap | +0.018 |
Neg logit contributions | |
gol | -0.038 |
aw | -0.031 |
aden | -0.031 |
David | -0.031 |
cheated | -0.030 |
Token | can |
Token ID | 460 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
isa | +0.007 |
pap | +0.007 |
sn | +0.006 |
Sn | +0.006 |
roast | +0.006 |
Neg logit contributions | |
gol | -0.010 |
David | -0.008 |
aden | -0.008 |
aw | -0.008 |
ival | -0.007 |
Token | bake |
Token ID | 28450 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
gol | +0.064 |
he | +0.052 |
aden | +0.051 |
cheated | +0.051 |
David | +0.051 |
Neg logit contributions | |
elope | -0.038 |
isa | -0.037 |
cel | -0.037 |
pap | -0.035 |
bing | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
isa | +0.063 |
elope | +0.063 |
cel | +0.063 |
Sn | +0.062 |
pap | +0.062 |
Neg logit contributions | |
gol | -0.130 |
aw | -0.107 |
aden | -0.105 |
David | -0.105 |
cheated | -0.102 |
Token | there |
Token ID | 612 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Pr | +0.013 |
Ana | +0.013 |
elope | +0.013 |
isa | +0.013 |
Sn | +0.013 |
Neg logit contributions | |
gol | -0.021 |
aw | -0.018 |
David | -0.016 |
aden | -0.016 |
ival | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
gol | +0.068 |
arl | +0.059 |
aw | +0.058 |
David | +0.057 |
aden | +0.057 |
Neg logit contributions | |
Sn | -0.012 |
elope | -0.012 |
sn | -0.010 |
Ana | -0.009 |
M | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
gol | +0.026 |
aden | +0.022 |
David | +0.022 |
ival | +0.022 |
arl | +0.022 |
Neg logit contributions | |
sn | -0.006 |
elope | -0.006 |
Chick | -0.006 |
Sn | -0.006 |
roast | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
isa | +0.028 |
Sn | +0.028 |
cel | +0.028 |
elope | +0.028 |
pap | +0.028 |
Neg logit contributions | |
gol | -0.040 |
aw | -0.031 |
aden | -0.031 |
David | -0.031 |
cheated | -0.030 |
Token | called |
Token ID | 1444 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
hips | +0.067 |
bing | +0.066 |
balls | +0.065 |
Sn | +0.065 |
forehead | +0.064 |
Neg logit contributions | |
gol | -0.052 |
aw | -0.046 |
chalk | -0.038 |
Tom | -0.036 |
car | -0.035 |
Token | Moon |
Token ID | 6869 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
gol | +0.026 |
aw | +0.020 |
David | +0.020 |
aden | +0.020 |
Tommy | +0.019 |
Neg logit contributions | |
bing | -0.023 |
isa | -0.022 |
cel | -0.022 |
pap | -0.022 |
elope | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
cel | +0.157 |
bing | +0.152 |
Sn | +0.148 |
convince | +0.145 |
eyel | +0.143 |
Neg logit contributions | |
gol | -0.202 |
aw | -0.186 |
aden | -0.165 |
ax | -0.165 |
ane | -0.162 |
Token | She |
Token ID | 1375 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
he | +0.009 |
aw | +0.009 |
happened | +0.009 |
See | +0.009 |
ane | +0.008 |
Neg logit contributions | |
bing | -0.017 |
convince | -0.016 |
we | -0.016 |
ci | -0.015 |
bes | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
bing | +0.027 |
pap | +0.026 |
isa | +0.026 |
Sn | +0.026 |
Pr | +0.026 |
Neg logit contributions | |
gol | -0.026 |
aw | -0.021 |
happened | -0.020 |
cheated | -0.020 |
David | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
gol | +0.011 |
aw | +0.008 |
cheated | +0.008 |
aden | +0.008 |
David | +0.008 |
Neg logit contributions | |
cel | -0.007 |
isa | -0.007 |
bing | -0.007 |
elope | -0.007 |
we | -0.007 |
Token | years |
Token ID | 812 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
Sn | +0.042 |
roast | +0.041 |
cup | +0.039 |
Stacy | +0.039 |
cel | +0.039 |
Neg logit contributions | |
aw | -0.067 |
gol | -0.060 |
aden | -0.053 |
tant | -0.053 |
trophies | -0.051 |
Token | We |
Token ID | 1135 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
gol | +0.001 |
aden | +0.001 |
aw | +0.001 |
ival | +0.001 |
David | +0.001 |
Neg logit contributions | |
Sn | -0.000 |
isa | -0.000 |
elope | -0.000 |
we | -0.000 |
mary | -0.000 |
Token | 're |
Token ID | 821 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
gol | +0.015 |
David | +0.014 |
aw | +0.013 |
ival | +0.013 |
aden | +0.012 |
Neg logit contributions | |
sn | -0.008 |
roast | -0.008 |
Sn | -0.008 |
bit | -0.008 |
cel | -0.008 |
Token | going |
Token ID | 1016 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Sn | +0.050 |
pap | +0.048 |
cel | +0.048 |
isa | +0.048 |
elope | +0.048 |
Neg logit contributions | |
gol | -0.103 |
aw | -0.085 |
David | -0.084 |
aden | -0.084 |
ival | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Sn | +0.020 |
cel | +0.020 |
pap | +0.019 |
isa | +0.019 |
bing | +0.019 |
Neg logit contributions | |
gol | -0.048 |
aw | -0.040 |
aden | -0.040 |
David | -0.040 |
cheated | -0.038 |
Token | see |
Token ID | 766 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Sn | +0.048 |
roast | +0.047 |
sn | +0.045 |
pap | +0.045 |
Moon | +0.043 |
Neg logit contributions | |
gol | -0.127 |
aw | -0.115 |
ival | -0.108 |
aden | -0.108 |
David | -0.108 |
Token | Sun |
Token ID | 3825 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
Sn | +0.014 |
isa | +0.013 |
Moon | +0.013 |
pap | +0.013 |
Pr | +0.013 |
Neg logit contributions | |
gol | -0.033 |
David | -0.026 |
aden | -0.026 |
cheated | -0.025 |
aw | -0.025 |
Token | flower |
Token ID | 25547 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
cel | +0.133 |
pap | +0.126 |
Sn | +0.126 |
eyel | +0.124 |
isa | +0.123 |
Neg logit contributions | |
gol | -0.235 |
aw | -0.203 |
aden | -0.190 |
ane | -0.190 |
he | -0.187 |
Token | ," |
Token ID | 553 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
isa | +0.078 |
elope | +0.077 |
Sn | +0.077 |
cel | +0.076 |
pap | +0.076 |
Neg logit contributions | |
gol | -0.179 |
David | -0.147 |
aden | -0.146 |
aw | -0.144 |
cheated | -0.140 |
Token | he |
Token ID | 339 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
gol | +0.044 |
aw | +0.035 |
David | +0.034 |
aden | +0.034 |
cheated | +0.033 |
Neg logit contributions | |
cel | -0.032 |
bing | -0.031 |
isa | -0.031 |
Sn | -0.031 |
elope | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
gol | +0.098 |
aw | +0.078 |
David | +0.075 |
aden | +0.074 |
cheated | +0.074 |
Neg logit contributions | |
cel | -0.103 |
bing | -0.102 |
Sn | -0.101 |
isa | -0.100 |
elope | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
gol | +0.061 |
cheated | +0.049 |
aw | +0.049 |
aden | +0.048 |
David | +0.048 |
Neg logit contributions | |
isa | -0.034 |
cel | -0.034 |
elope | -0.033 |
Sn | -0.032 |
pap | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
cel | +0.044 |
Sn | +0.044 |
isa | +0.044 |
bing | +0.044 |
pap | +0.042 |
Neg logit contributions | |
gol | -0.074 |
aw | -0.061 |
aden | -0.058 |
David | -0.058 |
cheated | -0.058 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
gol | +0.006 |
aw | +0.005 |
aden | +0.005 |
David | +0.005 |
ival | +0.005 |
Neg logit contributions | |
Sn | -0.003 |
isa | -0.003 |
elope | -0.003 |
cel | -0.003 |
pap | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
isa | +0.028 |
Sn | +0.028 |
cel | +0.027 |
elope | +0.027 |
pap | +0.027 |
Neg logit contributions | |
gol | -0.067 |
aw | -0.055 |
aden | -0.054 |
David | -0.054 |
cheated | -0.053 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
pap | +0.008 |
Sn | +0.008 |
elope | +0.007 |
isa | +0.007 |
Pr | +0.007 |
Neg logit contributions | |
gol | -0.013 |
aden | -0.011 |
aw | -0.011 |
David | -0.011 |
ival | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
Sn | +0.011 |
Pr | +0.011 |
pap | +0.011 |
sn | +0.010 |
Chick | +0.010 |
Neg logit contributions | |
gol | -0.027 |
aw | -0.022 |
David | -0.022 |
aden | -0.022 |
cheated | -0.021 |
Token | chick |
Token ID | 17943 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
cel | +0.018 |
bing | +0.017 |
isa | +0.016 |
we | +0.016 |
bes | +0.016 |
Neg logit contributions | |
gol | -0.019 |
thief | -0.016 |
Here | -0.016 |
aw | -0.015 |
trouble | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
cel | +0.129 |
isa | +0.129 |
Sn | +0.128 |
elope | +0.126 |
bing | +0.124 |
Neg logit contributions | |
gol | -0.253 |
aw | -0.207 |
aden | -0.205 |
David | -0.204 |
cheated | -0.198 |
Token | � |
Token ID | 6184 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
gol | +0.009 |
aw | +0.007 |
aden | +0.007 |
David | +0.007 |
cheated | +0.007 |
Neg logit contributions | |
isa | -0.004 |
cel | -0.004 |
Sn | -0.004 |
elope | -0.004 |
pap | -0.004 |
Token | � |
Token ID | 95 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
knees | +0.037 |
isa | +0.037 |
sey | +0.036 |
we | +0.036 |
fl | +0.035 |
Neg logit contributions | |
gol | -0.067 |
aw | -0.060 |
ival | -0.050 |
arl | -0.049 |
David | -0.047 |
Token | € |
Token ID | 26391 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
knees | +0.059 |
Ana | +0.051 |
pap | +0.050 |
eyel | +0.048 |
Sn | +0.048 |
Neg logit contributions | |
gol | -0.066 |
aw | -0.063 |
David | -0.053 |
Here | -0.052 |
Tom | -0.048 |
Token | � |
Token ID | 129 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
Sn | +0.064 |
isa | +0.063 |
bing | +0.061 |
eyel | +0.061 |
pap | +0.060 |
Neg logit contributions | |
gol | -0.098 |
aw | -0.086 |
David | -0.084 |
ival | -0.078 |
cheated | -0.078 |
Token | I |
Token ID | 314 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
isa | +0.028 |
bing | +0.027 |
elope | +0.027 |
pap | +0.026 |
we | +0.026 |
Neg logit contributions | |
gol | -0.031 |
aw | -0.024 |
aden | -0.024 |
cheated | -0.023 |
David | -0.023 |
Token | want |
Token ID | 765 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
gol | +0.053 |
David | +0.043 |
aw | +0.043 |
aden | +0.042 |
ival | +0.040 |
Neg logit contributions | |
cel | -0.039 |
elope | -0.039 |
Sn | -0.038 |
isa | -0.038 |
sn | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
gol | +0.070 |
aw | +0.055 |
chalk | +0.055 |
cheated | +0.055 |
Tommy | +0.055 |
Neg logit contributions | |
elope | -0.071 |
isa | -0.069 |
cel | -0.068 |
bing | -0.067 |
mary | -0.061 |
Token | prevent |
Token ID | 2948 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
isa | +0.019 |
elope | +0.018 |
bing | +0.017 |
cel | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
gol | -0.034 |
aden | -0.027 |
cheated | -0.027 |
David | -0.027 |
aw | -0.027 |
Token | Fl |
Token ID | 1610 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
isa | +0.071 |
elope | +0.071 |
cel | +0.070 |
pap | +0.067 |
mary | +0.067 |
Neg logit contributions | |
gol | -0.106 |
aw | -0.085 |
aden | -0.083 |
cheated | -0.083 |
David | -0.080 |
Token | uffy |
Token ID | 15352 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
pap | +0.225 |
cel | +0.218 |
isa | +0.218 |
Moon | +0.218 |
Pr | +0.216 |
Neg logit contributions | |
gol | -0.168 |
aw | -0.129 |
arl | -0.126 |
ane | -0.116 |
he | -0.114 |
Token | from |
Token ID | 422 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
isa | +0.138 |
elope | +0.133 |
pap | +0.132 |
cel | +0.131 |
Moon | +0.125 |
Neg logit contributions | |
gol | -0.250 |
aw | -0.205 |
cheated | -0.198 |
aden | -0.196 |
he | -0.193 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
isa | +0.036 |
elope | +0.036 |
cel | +0.035 |
mary | +0.033 |
Sn | +0.033 |
Neg logit contributions | |
gol | -0.074 |
aden | -0.059 |
aw | -0.059 |
cheated | -0.059 |
David | -0.059 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
isa | +0.069 |
elope | +0.069 |
cel | +0.068 |
Sn | +0.066 |
pap | +0.066 |
Neg logit contributions | |
gol | -0.117 |
aw | -0.093 |
aden | -0.093 |
David | -0.092 |
cheated | -0.090 |
Token | ." |
Token ID | 526 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
isa | +0.029 |
cel | +0.029 |
elope | +0.029 |
pap | +0.029 |
Sn | +0.028 |
Neg logit contributions | |
gol | -0.079 |
aw | -0.066 |
aden | -0.065 |
David | -0.064 |
cheated | -0.064 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
gol | +0.010 |
Tommy | +0.009 |
aw | +0.009 |
happened | +0.008 |
Tom | +0.008 |
Neg logit contributions | |
isa | -0.013 |
cel | -0.012 |
bing | -0.012 |
we | -0.012 |
elope | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Sn | +0.038 |
mary | +0.038 |
sn | +0.038 |
pap | +0.038 |
bing | +0.038 |
Neg logit contributions | |
gol | -0.125 |
aden | -0.104 |
David | -0.102 |
ival | -0.100 |
cheated | -0.099 |
Token | out |
Token ID | 503 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
pap | +0.038 |
Sn | +0.037 |
Pr | +0.036 |
sn | +0.036 |
Chick | +0.036 |
Neg logit contributions | |
gol | -0.086 |
aden | -0.070 |
aw | -0.070 |
David | -0.068 |
ival | -0.066 |
Token | came |
Token ID | 1625 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
gol | +0.024 |
David | +0.019 |
aden | +0.019 |
aw | +0.019 |
ax | +0.018 |
Neg logit contributions | |
Sn | -0.015 |
isa | -0.015 |
sn | -0.015 |
cel | -0.015 |
elope | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.006 |
aden | +0.006 |
David | +0.006 |
ival | +0.006 |
Neg logit contributions | |
Sn | -0.004 |
elope | -0.004 |
isa | -0.004 |
pap | -0.004 |
cel | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
pap | +0.030 |
Sn | +0.029 |
sn | +0.029 |
Moon | +0.029 |
elope | +0.029 |
Neg logit contributions | |
gol | -0.052 |
aden | -0.045 |
aw | -0.045 |
David | -0.043 |
ax | -0.043 |
Token | chick |
Token ID | 17943 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
pap | +0.041 |
Sn | +0.041 |
elope | +0.041 |
isa | +0.041 |
cel | +0.039 |
Neg logit contributions | |
gol | -0.073 |
David | -0.060 |
aden | -0.060 |
aw | -0.059 |
cheated | -0.057 |
Token | ! |
Token ID | 0 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
isa | +0.123 |
Sn | +0.120 |
cel | +0.119 |
pap | +0.118 |
elope | +0.115 |
Neg logit contributions | |
gol | -0.259 |
aw | -0.217 |
aden | -0.206 |
David | -0.204 |
cheated | -0.204 |
Token | Pe |
Token ID | 2631 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
gol | +0.046 |
aw | +0.037 |
aden | +0.037 |
David | +0.037 |
cheated | +0.035 |
Neg logit contributions | |
Sn | -0.025 |
cel | -0.024 |
isa | -0.024 |
elope | -0.024 |
pap | -0.024 |
Token | ep |
Token ID | 538 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
isa | +0.015 |
cel | +0.015 |
elope | +0.015 |
Sn | +0.015 |
pap | +0.014 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.014 |
aden | -0.014 |
David | -0.014 |
cheated | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
gol | +0.009 |
aden | +0.008 |
David | +0.007 |
aw | +0.007 |
ival | +0.007 |
Neg logit contributions | |
elope | -0.004 |
isa | -0.004 |
Sn | -0.004 |
bing | -0.004 |
cel | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
gol | +0.022 |
aw | +0.018 |
aden | +0.018 |
David | +0.018 |
cheated | +0.018 |
Neg logit contributions | |
isa | -0.011 |
cel | -0.011 |
Sn | -0.011 |
elope | -0.011 |
bing | -0.010 |
Token | there |
Token ID | 612 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
gol | +0.043 |
aw | +0.037 |
aden | +0.037 |
David | +0.036 |
ival | +0.035 |
Neg logit contributions | |
Sn | -0.010 |
elope | -0.010 |
pap | -0.009 |
Pr | -0.009 |
Ana | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
gol | +0.046 |
arl | +0.040 |
David | +0.039 |
aden | +0.039 |
aw | +0.039 |
Neg logit contributions | |
elope | -0.007 |
Sn | -0.007 |
sn | -0.007 |
Ana | -0.006 |
isa | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
gol | +0.014 |
aden | +0.012 |
ival | +0.012 |
David | +0.011 |
cheated | +0.011 |
Neg logit contributions | |
Sn | -0.004 |
elope | -0.004 |
Chick | -0.004 |
sn | -0.004 |
Pr | -0.004 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
isa | +0.031 |
cel | +0.031 |
elope | +0.031 |
Sn | +0.031 |
bing | +0.030 |
Neg logit contributions | |
gol | -0.042 |
aw | -0.032 |
David | -0.032 |
aden | -0.032 |
cheated | -0.031 |
Token | called |
Token ID | 1444 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
hips | +0.067 |
iously | +0.065 |
Sn | +0.065 |
bing | +0.065 |
Misty | +0.065 |
Neg logit contributions | |
gol | -0.050 |
aw | -0.043 |
chalk | -0.037 |
Tom | -0.034 |
car | -0.034 |
Token | Honey |
Token ID | 21788 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
gol | +0.025 |
aw | +0.019 |
David | +0.019 |
aden | +0.019 |
cheated | +0.018 |
Neg logit contributions | |
bing | -0.019 |
isa | -0.018 |
cel | -0.018 |
pap | -0.018 |
elope | -0.018 |
Token | who |
Token ID | 508 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
cel | +0.178 |
breaths | +0.176 |
hips | +0.175 |
eyel | +0.172 |
convince | +0.171 |
Neg logit contributions | |
gol | -0.162 |
aw | -0.138 |
he | -0.124 |
ax | -0.122 |
happened | -0.121 |
Token | lived |
Token ID | 5615 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
gol | +0.036 |
aw | +0.029 |
cheated | +0.028 |
happened | +0.027 |
aden | +0.027 |
Neg logit contributions | |
bing | -0.034 |
cel | -0.033 |
isa | -0.033 |
pap | -0.033 |
Sn | -0.032 |
Token | in |
Token ID | 287 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
gol | +0.041 |
aw | +0.034 |
David | +0.033 |
aden | +0.032 |
cheated | +0.032 |
Neg logit contributions | |
cel | -0.022 |
isa | -0.021 |
elope | -0.021 |
pap | -0.021 |
Sn | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
bing | +0.022 |
cel | +0.021 |
isa | +0.021 |
mary | +0.021 |
cup | +0.020 |
Neg logit contributions | |
gol | -0.022 |
David | -0.017 |
Tommy | -0.017 |
aw | -0.017 |
chalk | -0.016 |
Token | small |
Token ID | 1402 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
gol | +0.014 |
aden | +0.011 |
David | +0.011 |
aw | +0.011 |
cheated | +0.011 |
Neg logit contributions | |
Sn | -0.008 |
elope | -0.008 |
pap | -0.008 |
isa | -0.008 |
cel | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
gol | +0.010 |
Tommy | +0.008 |
chalk | +0.007 |
aden | +0.007 |
arl | +0.007 |
Neg logit contributions | |
bing | -0.016 |
isa | -0.016 |
elope | -0.015 |
we | -0.015 |
pap | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Sn | +0.023 |
elope | +0.022 |
Pr | +0.022 |
Chick | +0.022 |
cel | +0.021 |
Neg logit contributions | |
gol | -0.053 |
aw | -0.042 |
aden | -0.041 |
David | -0.041 |
ival | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
gol | +0.020 |
David | +0.015 |
aden | +0.015 |
aw | +0.015 |
he | +0.014 |
Neg logit contributions | |
pap | -0.020 |
bing | -0.020 |
isa | -0.020 |
cel | -0.020 |
elope | -0.020 |
Token | " |
Token ID | 1 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
gol | +0.002 |
Tom | +0.002 |
he | +0.001 |
David | +0.001 |
aw | +0.001 |
Neg logit contributions | |
knees | -0.003 |
pap | -0.003 |
isa | -0.003 |
elope | -0.003 |
bing | -0.003 |
Token | Hi |
Token ID | 17250 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
isa | +0.059 |
elope | +0.058 |
cel | +0.058 |
pap | +0.058 |
Sn | +0.057 |
Neg logit contributions | |
gol | -0.059 |
David | -0.043 |
aw | -0.043 |
aden | -0.043 |
cheated | -0.041 |
Token | Sp |
Token ID | 1338 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
gol | +0.002 |
aw | +0.001 |
aden | +0.001 |
cheated | +0.001 |
Tommy | +0.001 |
Neg logit contributions | |
elope | -0.001 |
isa | -0.001 |
cel | -0.001 |
mary | -0.001 |
bing | -0.001 |
Token | ud |
Token ID | 463 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
pap | +0.196 |
Pr | +0.191 |
elope | +0.189 |
Sn | +0.187 |
cel | +0.187 |
Neg logit contributions | |
gol | -0.188 |
aw | -0.147 |
aden | -0.140 |
David | -0.138 |
he | -0.137 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
pap | +0.029 |
elope | +0.029 |
cel | +0.029 |
isa | +0.029 |
Sn | +0.029 |
Neg logit contributions | |
gol | -0.048 |
aw | -0.038 |
cheated | -0.037 |
aden | -0.036 |
David | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
gol | +0.024 |
aw | +0.017 |
cheated | +0.017 |
chalk | +0.016 |
happened | +0.016 |
Neg logit contributions | |
bing | -0.040 |
isa | -0.038 |
elope | -0.038 |
cel | -0.038 |
we | -0.036 |
Token | Lily |
Token ID | 20037 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
gol | +0.041 |
Tommy | +0.028 |
chalk | +0.027 |
cheated | +0.027 |
happened | +0.026 |
Neg logit contributions | |
bing | -0.052 |
cel | -0.051 |
elope | -0.051 |
isa | -0.050 |
we | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
gol | +0.024 |
cheated | +0.018 |
aw | +0.018 |
ax | +0.017 |
Tommy | +0.017 |
Neg logit contributions | |
roast | -0.020 |
isa | -0.020 |
cel | -0.019 |
carniv | -0.019 |
pap | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
gol | +0.034 |
cheated | +0.028 |
aw | +0.028 |
aden | +0.027 |
happened | +0.027 |
Neg logit contributions | |
isa | -0.023 |
Sn | -0.022 |
bing | -0.022 |
cel | -0.022 |
elope | -0.022 |
Token | ". |
Token ID | 1911 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
gol | +0.034 |
aw | +0.027 |
aden | +0.027 |
cheated | +0.027 |
David | +0.027 |
Neg logit contributions | |
isa | -0.017 |
cel | -0.017 |
elope | -0.016 |
Sn | -0.016 |
bing | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
gol | +0.014 |
aw | +0.012 |
cheated | +0.011 |
ival | +0.011 |
he | +0.010 |
Neg logit contributions | |
cel | -0.014 |
bing | -0.014 |
Sn | -0.014 |
isa | -0.014 |
knees | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
gol | +0.033 |
aw | +0.026 |
David | +0.026 |
ival | +0.025 |
aden | +0.025 |
Neg logit contributions | |
cel | -0.030 |
Sn | -0.030 |
pap | -0.029 |
isa | -0.029 |
bing | -0.029 |
Token | The |
Token ID | 464 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
gol | +0.011 |
aw | +0.009 |
David | +0.009 |
ival | +0.009 |
Tom | +0.008 |
Neg logit contributions | |
cel | -0.010 |
Sn | -0.010 |
knees | -0.010 |
eyel | -0.009 |
hips | -0.009 |
Token | other |
Token ID | 584 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
Sn | +0.018 |
bing | +0.018 |
cel | +0.018 |
Chick | +0.017 |
bed | +0.017 |
Neg logit contributions | |
gol | -0.024 |
aw | -0.020 |
cheated | -0.019 |
ival | -0.019 |
liar | -0.019 |
Token | bees |
Token ID | 17002 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
aw | +0.145 |
gol | +0.135 |
happened | +0.119 |
ival | +0.110 |
ax | +0.108 |
Neg logit contributions | |
Sn | -0.105 |
cel | -0.104 |
bing | -0.101 |
hips | -0.096 |
Chick | -0.094 |
Token | offered |
Token ID | 4438 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
elope | +0.040 |
isa | +0.039 |
cel | +0.038 |
pap | +0.038 |
bing | +0.038 |
Neg logit contributions | |
gol | -0.069 |
aden | -0.056 |
David | -0.056 |
aw | -0.054 |
cheated | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
cel | +0.018 |
Sn | +0.017 |
bing | +0.016 |
isa | +0.016 |
elope | +0.016 |
Neg logit contributions | |
gol | -0.026 |
aw | -0.022 |
David | -0.021 |
aden | -0.021 |
cheated | -0.020 |
Token | tired |
Token ID | 10032 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
bing | +0.024 |
Sn | +0.023 |
cel | +0.023 |
Chick | +0.022 |
bed | +0.021 |
Neg logit contributions | |
gol | -0.036 |
aw | -0.030 |
cheated | -0.028 |
ival | -0.028 |
happened | -0.028 |
Token | bee |
Token ID | 20697 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
cel | +0.024 |
Sn | +0.023 |
bing | +0.022 |
elope | +0.022 |
isa | +0.021 |
Neg logit contributions | |
gol | -0.033 |
aw | -0.028 |
ax | -0.025 |
aden | -0.025 |
David | -0.025 |
Token | just |
Token ID | 655 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
pap | +0.023 |
Sn | +0.023 |
sn | +0.023 |
Pr | +0.022 |
bing | +0.022 |
Neg logit contributions | |
gol | -0.043 |
aden | -0.036 |
David | -0.036 |
aw | -0.035 |
ival | -0.034 |
Token | as |
Token ID | 355 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
gol | +0.010 |
David | +0.009 |
aden | +0.009 |
ival | +0.009 |
aw | +0.008 |
Neg logit contributions | |
sn | -0.004 |
Pr | -0.004 |
pap | -0.004 |
following | -0.004 |
cel | -0.004 |
Token | cheerful |
Token ID | 37999 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
pap | +0.003 |
Pr | +0.002 |
sn | +0.002 |
Chick | +0.002 |
soon | +0.002 |
Neg logit contributions | |
gol | -0.007 |
aden | -0.006 |
David | -0.006 |
aw | -0.006 |
ival | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
gol | +0.039 |
David | +0.033 |
aden | +0.033 |
aw | +0.033 |
ival | +0.032 |
Neg logit contributions | |
Sn | -0.009 |
cel | -0.009 |
bing | -0.009 |
pap | -0.009 |
isa | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gol | +0.022 |
aw | +0.018 |
aden | +0.018 |
David | +0.018 |
ival | +0.018 |
Neg logit contributions | |
Sn | -0.010 |
pap | -0.010 |
isa | -0.010 |
elope | -0.010 |
bing | -0.010 |
Token | new |
Token ID | 649 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
gol | +0.048 |
David | +0.041 |
aden | +0.040 |
aw | +0.039 |
ax | +0.039 |
Neg logit contributions | |
pap | -0.025 |
elope | -0.025 |
cel | -0.024 |
Sn | -0.023 |
isa | -0.023 |
Token | uniform |
Token ID | 8187 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
gol | +0.175 |
David | +0.145 |
aden | +0.145 |
aw | +0.144 |
ival | +0.140 |
Neg logit contributions | |
elope | -0.093 |
pap | -0.092 |
isa | -0.091 |
Sn | -0.091 |
cel | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
gol | +0.195 |
David | +0.168 |
aden | +0.163 |
aw | +0.157 |
ax | +0.156 |
Neg logit contributions | |
Sn | -0.045 |
cel | -0.042 |
cup | -0.040 |
sn | -0.039 |
elope | -0.039 |
Token | From |
Token ID | 3574 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
gol | +0.021 |
aden | +0.017 |
David | +0.017 |
aw | +0.017 |
cheated | +0.017 |
Neg logit contributions | |
Sn | -0.011 |
elope | -0.010 |
Pr | -0.010 |
Chick | -0.010 |
cel | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
bing | +0.006 |
pap | +0.006 |
isa | +0.006 |
Sn | +0.006 |
elope | +0.006 |
Neg logit contributions | |
gol | -0.020 |
aden | -0.017 |
David | -0.016 |
cheated | -0.016 |
aw | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
cel | +0.036 |
isa | +0.035 |
elope | +0.035 |
mary | +0.035 |
Sn | +0.035 |
Neg logit contributions | |
gol | -0.036 |
David | -0.025 |
he | -0.025 |
aden | -0.025 |
happened | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
gol | +0.018 |
aden | +0.014 |
David | +0.014 |
aw | +0.014 |
ival | +0.014 |
Neg logit contributions | |
Sn | -0.009 |
pap | -0.009 |
Pr | -0.009 |
elope | -0.009 |
mary | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
gol | +0.060 |
aden | +0.048 |
aw | +0.048 |
David | +0.047 |
cheated | +0.047 |
Neg logit contributions | |
Sn | -0.031 |
elope | -0.030 |
pap | -0.030 |
Pr | -0.030 |
isa | -0.029 |
Token | They |
Token ID | 2990 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
gol | +0.028 |
aw | +0.022 |
David | +0.022 |
aden | +0.022 |
cheated | +0.021 |
Neg logit contributions | |
cel | -0.020 |
isa | -0.020 |
elope | -0.019 |
pap | -0.019 |
Sn | -0.019 |
Token | hugged |
Token ID | 41130 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Sn | +0.016 |
cel | +0.016 |
isa | +0.016 |
pap | +0.016 |
elope | +0.015 |
Neg logit contributions | |
gol | -0.029 |
aw | -0.023 |
aden | -0.023 |
David | -0.023 |
cheated | -0.022 |
Token | each |
Token ID | 1123 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
gol | +0.016 |
aw | +0.014 |
aden | +0.013 |
David | +0.012 |
tant | +0.012 |
Neg logit contributions | |
cel | -0.011 |
isa | -0.011 |
elope | -0.011 |
pap | -0.011 |
bing | -0.011 |
Token | other |
Token ID | 584 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
gol | +0.027 |
aw | +0.022 |
aden | +0.022 |
David | +0.021 |
cheated | +0.020 |
Neg logit contributions | |
cel | -0.022 |
elope | -0.022 |
Sn | -0.022 |
isa | -0.022 |
bing | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
gol | +0.157 |
aw | +0.133 |
aden | +0.123 |
cheated | +0.121 |
ival | +0.119 |
Neg logit contributions | |
isa | -0.117 |
cel | -0.117 |
elope | -0.113 |
pap | -0.112 |
Chick | -0.110 |
Token | said |
Token ID | 531 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
isa | +0.006 |
cel | +0.006 |
Sn | +0.006 |
elope | +0.006 |
pap | +0.006 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Sn | +0.004 |
pap | +0.004 |
cel | +0.004 |
Pr | +0.004 |
bing | +0.004 |
Neg logit contributions | |
gol | -0.012 |
aden | -0.010 |
David | -0.010 |
aw | -0.010 |
ax | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
isa | +0.006 |
elope | +0.006 |
pap | +0.005 |
cel | +0.005 |
bing | +0.005 |
Neg logit contributions | |
gol | -0.008 |
David | -0.006 |
aw | -0.006 |
cheated | -0.006 |
arl | -0.006 |
Token | We |
Token ID | 1135 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
cel | +0.032 |
isa | +0.032 |
pap | +0.032 |
elope | +0.032 |
Sn | +0.031 |
Neg logit contributions | |
gol | -0.043 |
aw | -0.034 |
David | -0.033 |
aden | -0.032 |
cheated | -0.032 |
Token | They |
Token ID | 2990 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
gol | +0.001 |
aw | +0.001 |
David | +0.001 |
Tom | +0.001 |
ival | +0.001 |
Neg logit contributions | |
cel | -0.001 |
pap | -0.001 |
elope | -0.001 |
Sn | -0.001 |
Chick | -0.001 |
Token | smile |
Token ID | 8212 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
sn | +0.013 |
roast | +0.012 |
pur | +0.011 |
isa | +0.011 |
cel | +0.011 |
Neg logit contributions | |
gol | -0.038 |
David | -0.033 |
aw | -0.032 |
ival | -0.031 |
aden | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
gol | +0.027 |
aw | +0.022 |
aden | +0.021 |
cheated | +0.021 |
David | +0.021 |
Neg logit contributions | |
isa | -0.016 |
elope | -0.016 |
cel | -0.016 |
Sn | -0.016 |
pap | -0.016 |
Token | admire |
Token ID | 21099 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
gol | +0.028 |
aw | +0.022 |
aden | +0.022 |
David | +0.022 |
cheated | +0.021 |
Neg logit contributions | |
isa | -0.017 |
cel | -0.017 |
Sn | -0.017 |
elope | -0.017 |
pap | -0.016 |
Token | each |
Token ID | 1123 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
cel | +0.011 |
isa | +0.011 |
elope | +0.011 |
Sn | +0.011 |
pap | +0.011 |
Neg logit contributions | |
gol | -0.016 |
aw | -0.013 |
aden | -0.013 |
David | -0.013 |
cheated | -0.012 |
Token | other |
Token ID | 584 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
gol | +0.023 |
aw | +0.018 |
chalk | +0.018 |
cheated | +0.017 |
aden | +0.017 |
Neg logit contributions | |
cel | -0.024 |
Sn | -0.024 |
pap | -0.024 |
elope | -0.023 |
Chick | -0.023 |
Token | 's |
Token ID | 338 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
gol | +0.178 |
aw | +0.157 |
cheated | +0.146 |
aden | +0.144 |
trophies | +0.144 |
Neg logit contributions | |
cel | -0.116 |
pap | -0.114 |
elope | -0.112 |
Chick | -0.111 |
isa | -0.110 |
Token | drawings |
Token ID | 23388 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
pap | +0.031 |
elope | +0.030 |
cel | +0.030 |
isa | +0.030 |
bing | +0.030 |
Neg logit contributions | |
gol | -0.055 |
David | -0.045 |
aden | -0.044 |
aw | -0.044 |
ax | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
gol | +0.048 |
David | +0.041 |
aden | +0.040 |
aw | +0.040 |
ival | +0.038 |
Neg logit contributions | |
Sn | -0.013 |
cel | -0.013 |
elope | -0.013 |
isa | -0.013 |
bing | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
cel | +0.012 |
isa | +0.012 |
bing | +0.012 |
elope | +0.012 |
pap | +0.011 |
Neg logit contributions | |
gol | -0.015 |
aw | -0.012 |
David | -0.011 |
cheated | -0.011 |
aden | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
sn | +0.026 |
cel | +0.024 |
roast | +0.024 |
pap | +0.024 |
pur | +0.024 |
Neg logit contributions | |
gol | -0.052 |
David | -0.043 |
aw | -0.043 |
aden | -0.042 |
ival | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
elope | +0.003 |
Sn | +0.003 |
Pr | +0.003 |
isa | +0.003 |
Moon | +0.003 |
Neg logit contributions | |
gol | -0.007 |
David | -0.006 |
aden | -0.006 |
cheated | -0.006 |
aw | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
sn | +0.026 |
mary | +0.024 |
Sn | +0.024 |
pap | +0.024 |
elope | +0.024 |
Neg logit contributions | |
gol | -0.053 |
aden | -0.046 |
David | -0.046 |
arl | -0.045 |
aw | -0.044 |
Token | that |
Token ID | 326 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
gol | +0.011 |
aden | +0.009 |
David | +0.009 |
ax | +0.009 |
aw | +0.009 |
Neg logit contributions | |
pap | -0.003 |
Sn | -0.003 |
sn | -0.003 |
Pr | -0.003 |
mary | -0.003 |
Token | helping |
Token ID | 5742 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
isa | +0.024 |
cel | +0.024 |
elope | +0.024 |
Sn | +0.024 |
pap | +0.024 |
Neg logit contributions | |
gol | -0.045 |
aw | -0.037 |
aden | -0.036 |
David | -0.036 |
cheated | -0.035 |
Token | each |
Token ID | 1123 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
pap | +0.014 |
Sn | +0.014 |
Pr | +0.013 |
elope | +0.013 |
bing | +0.013 |
Neg logit contributions | |
gol | -0.037 |
David | -0.031 |
aw | -0.031 |
aden | -0.031 |
ival | -0.030 |
Token | other |
Token ID | 584 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
gol | +0.056 |
David | +0.047 |
aw | +0.047 |
aden | +0.046 |
ival | +0.045 |
Neg logit contributions | |
isa | -0.026 |
Pr | -0.025 |
pap | -0.025 |
sn | -0.025 |
elope | -0.024 |
Token | is |
Token ID | 318 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
gol | +0.215 |
David | +0.180 |
aden | +0.175 |
ax | +0.170 |
aw | +0.167 |
Neg logit contributions | |
sn | -0.097 |
elope | -0.096 |
pap | -0.096 |
Sn | -0.095 |
Pr | -0.093 |
Token | very |
Token ID | 845 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
isa | +0.014 |
cel | +0.014 |
Sn | +0.014 |
elope | +0.014 |
pap | +0.014 |
Neg logit contributions | |
gol | -0.023 |
aw | -0.018 |
aden | -0.018 |
David | -0.018 |
cheated | -0.017 |
Token | important |
Token ID | 1593 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
gol | +0.001 |
aw | +0.001 |
aden | +0.001 |
David | +0.001 |
ival | +0.001 |
Neg logit contributions | |
Sn | -0.001 |
pap | -0.001 |
elope | -0.001 |
isa | -0.001 |
cel | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
gol | +0.034 |
aw | +0.028 |
aden | +0.028 |
David | +0.028 |
cheated | +0.027 |
Neg logit contributions | |
isa | -0.014 |
cel | -0.014 |
Sn | -0.014 |
elope | -0.014 |
pap | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
elope | +0.013 |
Sn | +0.013 |
Pr | +0.013 |
isa | +0.012 |
pap | +0.012 |
Neg logit contributions | |
gol | -0.025 |
aden | -0.021 |
aw | -0.021 |
David | -0.020 |
cheated | -0.020 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
bing | +0.031 |
Sn | +0.031 |
cel | +0.031 |
isa | +0.031 |
elope | +0.030 |
Neg logit contributions | |
gol | -0.044 |
aw | -0.035 |
cheated | -0.034 |
David | -0.034 |
aden | -0.034 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
isa | +0.027 |
cel | +0.027 |
elope | +0.027 |
Sn | +0.026 |
bing | +0.026 |
Neg logit contributions | |
gol | -0.036 |
aw | -0.029 |
cheated | -0.028 |
David | -0.028 |
aden | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
cel | +0.001 |
isa | +0.001 |
Sn | +0.000 |
elope | +0.000 |
Pr | +0.000 |
Neg logit contributions | |
gol | -0.001 |
aw | -0.001 |
cheated | -0.001 |
aden | -0.001 |
happened | -0.001 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
isa | +0.011 |
cel | +0.011 |
Sn | +0.010 |
elope | +0.010 |
Moon | +0.010 |
Neg logit contributions | |
gol | -0.008 |
cheated | -0.006 |
happened | -0.006 |
aw | -0.006 |
chalk | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
cel | +0.008 |
elope | +0.008 |
isa | +0.008 |
Sn | +0.008 |
pap | +0.007 |
Neg logit contributions | |
gol | -0.014 |
aw | -0.012 |
aden | -0.011 |
happened | -0.011 |
cheated | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
Sn | +0.012 |
elope | +0.012 |
pap | +0.011 |
Pr | +0.011 |
cel | +0.011 |
Neg logit contributions | |
gol | -0.020 |
aw | -0.017 |
aden | -0.016 |
David | -0.016 |
cheated | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
gol | +0.003 |
aden | +0.002 |
aw | +0.002 |
cheated | +0.002 |
David | +0.002 |
Neg logit contributions | |
elope | -0.001 |
Sn | -0.001 |
Chick | -0.001 |
Pr | -0.001 |
pap | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Sn | +0.007 |
bing | +0.007 |
elope | +0.007 |
isa | +0.007 |
cel | +0.007 |
Neg logit contributions | |
gol | -0.017 |
aden | -0.014 |
aw | -0.014 |
cheated | -0.013 |
David | -0.013 |
Token | Thank |
Token ID | 10449 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
isa | +0.064 |
elope | +0.063 |
bing | +0.063 |
pap | +0.063 |
cel | +0.063 |
Neg logit contributions | |
gol | -0.058 |
aw | -0.044 |
David | -0.044 |
aden | -0.040 |
cheated | -0.039 |
Token | you |
Token ID | 345 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
mary | +0.007 |
cel | +0.006 |
elope | +0.006 |
isa | +0.006 |
knees | +0.006 |
Neg logit contributions | |
gol | -0.004 |
aw | -0.004 |
Tom | -0.003 |
ival | -0.003 |
David | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
gol | +0.002 |
aw | +0.002 |
Tommy | +0.002 |
ax | +0.002 |
aden | +0.002 |
Neg logit contributions | |
bing | -0.003 |
isa | -0.003 |
we | -0.003 |
cel | -0.003 |
elope | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
gol | +0.006 |
David | +0.005 |
aden | +0.005 |
aw | +0.004 |
ival | +0.004 |
Neg logit contributions | |
sn | -0.003 |
mary | -0.003 |
cel | -0.003 |
Sn | -0.003 |
pap | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
gol | +0.044 |
ival | +0.039 |
David | +0.037 |
cheated | +0.037 |
aw | +0.037 |
Neg logit contributions | |
Sn | -0.013 |
Chick | -0.012 |
Pr | -0.012 |
sn | -0.011 |
bing | -0.011 |
Token | seas |
Token ID | 21547 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
sn | +0.016 |
next | +0.015 |
pap | +0.014 |
Sn | +0.014 |
cel | +0.014 |
Neg logit contributions | |
gol | -0.017 |
David | -0.014 |
arl | -0.013 |
ival | -0.013 |
aden | -0.013 |
Token | hell |
Token ID | 12758 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
gol | +0.132 |
aw | +0.098 |
aden | +0.098 |
David | +0.097 |
cheated | +0.093 |
Neg logit contributions | |
isa | -0.131 |
cel | -0.130 |
elope | -0.130 |
Sn | -0.130 |
pap | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
gol | +0.055 |
aw | +0.046 |
aden | +0.044 |
cheated | +0.043 |
ax | +0.042 |
Neg logit contributions | |
cel | -0.034 |
isa | -0.034 |
pap | -0.033 |
elope | -0.033 |
Sn | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
gol | +0.057 |
aden | +0.045 |
aw | +0.045 |
David | +0.045 |
ival | +0.043 |
Neg logit contributions | |
pap | -0.036 |
isa | -0.036 |
Sn | -0.036 |
elope | -0.036 |
cel | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
gol | +0.009 |
aden | +0.008 |
David | +0.008 |
aw | +0.007 |
ax | +0.007 |
Neg logit contributions | |
Sn | -0.002 |
pap | -0.002 |
cel | -0.002 |
Pr | -0.002 |
sn | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
gol | +0.038 |
David | +0.031 |
aw | +0.030 |
aden | +0.030 |
cheated | +0.030 |
Neg logit contributions | |
isa | -0.024 |
elope | -0.023 |
cel | -0.022 |
Sn | -0.022 |
pap | -0.021 |
Token | Wow |
Token ID | 22017 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
Sn | +0.014 |
isa | +0.014 |
cel | +0.013 |
elope | +0.013 |
pap | +0.013 |
Neg logit contributions | |
gol | -0.017 |
aw | -0.013 |
aden | -0.013 |
David | -0.013 |
cheated | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
gol | +0.045 |
aw | +0.038 |
aden | +0.037 |
David | +0.036 |
cheated | +0.036 |
Neg logit contributions | |
isa | -0.025 |
elope | -0.024 |
pap | -0.024 |
Sn | -0.024 |
cel | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
gol | +0.003 |
David | +0.002 |
aw | +0.002 |
aden | +0.002 |
ival | +0.002 |
Neg logit contributions | |
Sn | -0.001 |
pap | -0.001 |
cel | -0.001 |
Pr | -0.001 |
Chick | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
gol | +0.041 |
aden | +0.034 |
aw | +0.034 |
David | +0.033 |
cheated | +0.033 |
Neg logit contributions | |
isa | -0.015 |
Sn | -0.015 |
pap | -0.015 |
elope | -0.015 |
cel | -0.015 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
isa | +0.012 |
Sn | +0.012 |
pap | +0.012 |
elope | +0.012 |
cel | +0.012 |
Neg logit contributions | |
gol | -0.019 |
aw | -0.015 |
aden | -0.015 |
David | -0.015 |
cheated | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Sn | +0.020 |
sn | +0.019 |
Pr | +0.019 |
mary | +0.019 |
bing | +0.019 |
Neg logit contributions | |
gol | -0.062 |
aden | -0.052 |
David | -0.052 |
cheated | -0.051 |
ival | -0.050 |
Token | One |
Token ID | 1881 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
gol | +0.016 |
aw | +0.013 |
aden | +0.013 |
David | +0.012 |
cheated | +0.012 |
Neg logit contributions | |
isa | -0.009 |
elope | -0.009 |
Sn | -0.009 |
cel | -0.009 |
pap | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
cel | +0.052 |
Sn | +0.050 |
bing | +0.049 |
isa | +0.048 |
pap | +0.048 |
Neg logit contributions | |
gol | -0.063 |
aw | -0.050 |
David | -0.047 |
aden | -0.047 |
ax | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
cel | +0.034 |
elope | +0.034 |
Sn | +0.034 |
isa | +0.033 |
mary | +0.033 |
Neg logit contributions | |
gol | -0.059 |
aw | -0.048 |
David | -0.047 |
aden | -0.046 |
cheated | -0.046 |
Token | Tony |
Token ID | 8832 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
gol | +0.004 |
aw | +0.003 |
David | +0.003 |
aden | +0.003 |
cheated | +0.003 |
Neg logit contributions | |
cel | -0.003 |
Sn | -0.003 |
elope | -0.003 |
isa | -0.003 |
pap | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
isa | +0.018 |
elope | +0.017 |
pap | +0.017 |
sn | +0.017 |
mary | +0.017 |
Neg logit contributions | |
gol | -0.034 |
aden | -0.027 |
David | -0.027 |
arl | -0.026 |
ival | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
gol | +0.088 |
aden | +0.074 |
David | +0.073 |
arl | +0.072 |
ival | +0.071 |
Neg logit contributions | |
pap | -0.028 |
Pr | -0.028 |
Bee | -0.025 |
Moon | -0.025 |
Chick | -0.025 |
Token | whole |
Token ID | 2187 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
pap | +0.005 |
sn | +0.004 |
bit | +0.004 |
pur | +0.004 |
elope | +0.004 |
Neg logit contributions | |
gol | -0.008 |
aden | -0.007 |
aw | -0.007 |
David | -0.007 |
anes | -0.007 |
Token | bunch |
Token ID | 7684 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
sn | +0.022 |
pap | +0.022 |
elope | +0.021 |
pur | +0.020 |
Pr | +0.020 |
Neg logit contributions | |
gol | -0.044 |
aden | -0.039 |
cheated | -0.037 |
David | -0.037 |
aw | -0.036 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
gol | +0.045 |
aw | +0.037 |
aden | +0.036 |
arl | +0.036 |
David | +0.036 |
Neg logit contributions | |
Sn | -0.031 |
Chick | -0.029 |
Pr | -0.029 |
pap | -0.029 |
elope | -0.029 |
Token | my |
Token ID | 1820 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
gol | +0.056 |
ival | +0.046 |
arl | +0.044 |
tant | +0.043 |
David | +0.043 |
Neg logit contributions | |
sn | -0.025 |
isa | -0.024 |
elope | -0.023 |
cup | -0.023 |
pap | -0.022 |
Token | found |
Token ID | 1043 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
gol | +0.003 |
arl | +0.002 |
aden | +0.002 |
David | +0.002 |
ival | +0.002 |
Neg logit contributions | |
pap | -0.001 |
sn | -0.001 |
cel | -0.001 |
isa | -0.001 |
elope | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
gol | +0.096 |
arl | +0.080 |
David | +0.079 |
ane | +0.079 |
ival | +0.079 |
Neg logit contributions | |
Sn | -0.023 |
Chick | -0.022 |
Pr | -0.021 |
sn | -0.021 |
one | -0.021 |
Token | sword |
Token ID | 8429 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
pap | +0.009 |
Sn | +0.008 |
sn | +0.008 |
bit | +0.008 |
pur | +0.008 |
Neg logit contributions | |
gol | -0.016 |
aw | -0.016 |
aden | -0.015 |
ax | -0.014 |
David | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
gol | +0.090 |
David | +0.081 |
aden | +0.078 |
ival | +0.076 |
aw | +0.075 |
Neg logit contributions | |
sn | -0.023 |
cel | -0.023 |
following | -0.022 |
bing | -0.021 |
making | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
gol | +0.021 |
arl | +0.018 |
aw | +0.018 |
David | +0.017 |
aden | +0.017 |
Neg logit contributions | |
Sn | -0.009 |
sn | -0.009 |
Chick | -0.009 |
Pr | -0.009 |
pap | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
gol | +0.065 |
David | +0.053 |
aw | +0.053 |
aden | +0.052 |
ax | +0.050 |
Neg logit contributions | |
cel | -0.037 |
Sn | -0.036 |
isa | -0.036 |
elope | -0.036 |
sn | -0.035 |
Token | forgotten |
Token ID | 11564 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
gol | +0.053 |
David | +0.043 |
arl | +0.043 |
aden | +0.043 |
ax | +0.042 |
Neg logit contributions | |
sn | -0.021 |
cel | -0.019 |
Sn | -0.018 |
eyel | -0.018 |
Pr | -0.017 |
Token | about |
Token ID | 546 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
gol | +0.074 |
David | +0.063 |
ival | +0.060 |
aden | +0.060 |
Kyle | +0.060 |
Neg logit contributions | |
because | -0.019 |
sn | -0.019 |
before | -0.019 |
Sn | -0.018 |
making | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Sn | +0.003 |
sn | +0.003 |
making | +0.003 |
Pr | +0.003 |
cel | +0.003 |
Neg logit contributions | |
gol | -0.008 |
aw | -0.006 |
David | -0.006 |
ival | -0.006 |
ax | -0.006 |
Token | need |
Token ID | 761 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
gol | +0.015 |
David | +0.012 |
aden | +0.012 |
aw | +0.012 |
ival | +0.011 |
Neg logit contributions | |
cel | -0.012 |
Sn | -0.011 |
sn | -0.011 |
elope | -0.011 |
roast | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
gol | +0.014 |
aw | +0.011 |
aden | +0.011 |
David | +0.011 |
cheated | +0.011 |
Neg logit contributions | |
Sn | -0.007 |
isa | -0.007 |
pap | -0.007 |
cel | -0.007 |
elope | -0.007 |
Token | bath |
Token ID | 7837 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
pap | +0.022 |
sn | +0.021 |
Sn | +0.021 |
roast | +0.020 |
pur | +0.020 |
Neg logit contributions | |
gol | -0.039 |
aw | -0.034 |
aden | -0.034 |
David | -0.033 |
ax | -0.032 |
Token | ." |
Token ID | 526 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Sn | +0.027 |
isa | +0.026 |
pap | +0.025 |
cel | +0.025 |
bing | +0.025 |
Neg logit contributions | |
gol | -0.076 |
David | -0.065 |
aden | -0.064 |
aw | -0.064 |
cheated | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
gol | +0.016 |
aden | +0.013 |
aw | +0.013 |
David | +0.013 |
cheated | +0.013 |
Neg logit contributions | |
Sn | -0.009 |
elope | -0.009 |
pap | -0.009 |
Pr | -0.009 |
Chick | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
gol | +0.045 |
aden | +0.036 |
aw | +0.035 |
David | +0.035 |
cheated | +0.035 |
Neg logit contributions | |
Sn | -0.024 |
elope | -0.024 |
cel | -0.023 |
Chick | -0.023 |
isa | -0.023 |
Token | Their |
Token ID | 14574 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
gol | +0.013 |
aw | +0.010 |
aden | +0.010 |
David | +0.010 |
cheated | +0.010 |
Neg logit contributions | |
isa | -0.010 |
Sn | -0.010 |
cel | -0.010 |
elope | -0.010 |
pap | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
pap | +0.000 |
Sn | +0.000 |
elope | +0.000 |
sn | +0.000 |
pur | +0.000 |
Neg logit contributions | |
gol | -0.001 |
aden | -0.001 |
David | -0.001 |
aw | -0.001 |
ax | -0.001 |
Token | agreed |
Token ID | 4987 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
isa | +0.006 |
Sn | +0.006 |
cel | +0.006 |
elope | +0.006 |
pap | +0.006 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
isa | +0.019 |
elope | +0.019 |
cel | +0.019 |
Sn | +0.018 |
bing | +0.018 |
Neg logit contributions | |
gol | -0.032 |
aw | -0.027 |
aden | -0.026 |
David | -0.026 |
ax | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
isa | +0.014 |
cel | +0.013 |
elope | +0.013 |
Sn | +0.013 |
pap | +0.013 |
Neg logit contributions | |
gol | -0.019 |
aw | -0.015 |
aden | -0.015 |
David | -0.015 |
cheated | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
bing | +0.011 |
isa | +0.011 |
pap | +0.010 |
elope | +0.010 |
cel | +0.010 |
Neg logit contributions | |
gol | -0.011 |
cheated | -0.010 |
aw | -0.010 |
happened | -0.009 |
aden | -0.009 |
Token | sick |
Token ID | 6639 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
isa | +0.005 |
cel | +0.005 |
elope | +0.005 |
Sn | +0.004 |
pap | +0.004 |
Neg logit contributions | |
gol | -0.008 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.006 |
Token | ." |
Token ID | 526 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
Sn | +0.019 |
isa | +0.018 |
cel | +0.018 |
elope | +0.018 |
pap | +0.018 |
Neg logit contributions | |
gol | -0.062 |
David | -0.052 |
aden | -0.052 |
aw | -0.051 |
ival | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
gol | +0.002 |
aden | +0.001 |
aw | +0.001 |
David | +0.001 |
cheated | +0.001 |
Neg logit contributions | |
Sn | -0.001 |
isa | -0.001 |
pap | -0.001 |
elope | -0.001 |
cel | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
gol | +0.039 |
aden | +0.031 |
aw | +0.031 |
David | +0.030 |
cheated | +0.030 |
Neg logit contributions | |
Sn | -0.022 |
elope | -0.022 |
isa | -0.022 |
pap | -0.022 |
Pr | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
gol | +0.009 |
aw | +0.007 |
David | +0.007 |
aden | +0.007 |
cheated | +0.006 |
Neg logit contributions | |
cel | -0.009 |
Sn | -0.008 |
isa | -0.008 |
elope | -0.008 |
pap | -0.008 |
Token | Let |
Token ID | 5756 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
isa | +0.040 |
cel | +0.040 |
Sn | +0.040 |
elope | +0.040 |
pap | +0.039 |
Neg logit contributions | |
gol | -0.060 |
aw | -0.048 |
aden | -0.048 |
David | -0.047 |
cheated | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
isa | +0.008 |
cel | +0.008 |
elope | +0.008 |
Sn | +0.008 |
pap | +0.007 |
Neg logit contributions | |
gol | -0.019 |
aw | -0.017 |
happened | -0.016 |
aden | -0.016 |
David | -0.016 |
Token | move |
Token ID | 1445 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
isa | +0.044 |
cel | +0.044 |
Sn | +0.044 |
elope | +0.043 |
pap | +0.043 |
Neg logit contributions | |
gol | -0.089 |
aw | -0.073 |
aden | -0.072 |
David | -0.072 |
cheated | -0.070 |
Token | away |
Token ID | 1497 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
isa | +0.036 |
Sn | +0.036 |
elope | +0.036 |
cel | +0.036 |
pap | +0.035 |
Neg logit contributions | |
gol | -0.069 |
David | -0.055 |
aden | -0.055 |
aw | -0.055 |
cheated | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
gol | +0.050 |
aw | +0.041 |
aden | +0.041 |
David | +0.041 |
cheated | +0.039 |
Neg logit contributions | |
isa | -0.023 |
cel | -0.023 |
Sn | -0.023 |
elope | -0.023 |
pap | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
gol | +0.080 |
aw | +0.067 |
aden | +0.066 |
David | +0.066 |
cheated | +0.064 |
Neg logit contributions | |
isa | -0.031 |
cel | -0.031 |
Sn | -0.030 |
elope | -0.030 |
pap | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
gol | +0.020 |
aden | +0.017 |
David | +0.016 |
aw | +0.016 |
cheated | +0.016 |
Neg logit contributions | |
elope | -0.011 |
Sn | -0.011 |
Pr | -0.011 |
isa | -0.011 |
pap | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
gol | +0.042 |
aden | +0.034 |
cheated | +0.033 |
aw | +0.033 |
trophies | +0.033 |
Neg logit contributions | |
elope | -0.018 |
Sn | -0.018 |
isa | -0.017 |
Chick | -0.017 |
Pr | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
gol | +0.010 |
aden | +0.008 |
cheated | +0.008 |
aw | +0.008 |
happened | +0.008 |
Neg logit contributions | |
elope | -0.004 |
isa | -0.004 |
Sn | -0.004 |
bing | -0.004 |
cel | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
Sn | +0.013 |
pap | +0.013 |
elope | +0.013 |
cel | +0.013 |
Moon | +0.013 |
Neg logit contributions | |
gol | -0.027 |
David | -0.022 |
aw | -0.022 |
aden | -0.022 |
ax | -0.021 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
gol | +0.043 |
aw | +0.035 |
aden | +0.035 |
David | +0.034 |
cheated | +0.033 |
Neg logit contributions | |
isa | -0.023 |
cel | -0.023 |
Sn | -0.023 |
elope | -0.023 |
pap | -0.023 |
Token | said |
Token ID | 531 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
cel | +0.030 |
Sn | +0.030 |
isa | +0.030 |
pap | +0.029 |
bing | +0.029 |
Neg logit contributions | |
gol | -0.049 |
aw | -0.040 |
aden | -0.038 |
David | -0.038 |
cheated | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.006 |
aden | +0.006 |
David | +0.006 |
cheated | +0.006 |
Neg logit contributions | |
isa | -0.004 |
cel | -0.004 |
elope | -0.004 |
Sn | -0.004 |
pap | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
gol | +0.025 |
aw | +0.020 |
David | +0.019 |
cheated | +0.018 |
Tommy | +0.018 |
Neg logit contributions | |
isa | -0.022 |
elope | -0.021 |
cel | -0.020 |
bing | -0.020 |
mary | -0.019 |
Token | I |
Token ID | 40 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
cel | +0.019 |
isa | +0.019 |
pap | +0.019 |
Sn | +0.019 |
elope | +0.019 |
Neg logit contributions | |
gol | -0.022 |
aw | -0.018 |
David | -0.017 |
aden | -0.017 |
cheated | -0.016 |
Token | will |
Token ID | 481 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
gol | +0.057 |
aw | +0.046 |
David | +0.046 |
aden | +0.045 |
ival | +0.043 |
Neg logit contributions | |
elope | -0.036 |
isa | -0.035 |
Sn | -0.035 |
pap | -0.035 |
sn | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
gol | +0.144 |
aw | +0.118 |
aden | +0.117 |
David | +0.117 |
cheated | +0.114 |
Neg logit contributions | |
isa | -0.059 |
cel | -0.059 |
elope | -0.058 |
Sn | -0.058 |
pap | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
gol | +0.025 |
aw | +0.021 |
aden | +0.021 |
ival | +0.020 |
cheated | +0.020 |
Neg logit contributions | |
Sn | -0.013 |
Pr | -0.013 |
pap | -0.013 |
elope | -0.012 |
Chick | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
gol | +0.034 |
aw | +0.028 |
aden | +0.028 |
cheated | +0.027 |
tant | +0.026 |
Neg logit contributions | |
Sn | -0.017 |
elope | -0.016 |
Pr | -0.016 |
Chick | -0.016 |
pap | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.007 |
aden | +0.007 |
David | +0.006 |
cheated | +0.006 |
Neg logit contributions | |
Sn | -0.006 |
isa | -0.006 |
elope | -0.006 |
pap | -0.006 |
cel | -0.006 |
Token | two |
Token ID | 734 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
Sn | +0.014 |
sn | +0.014 |
pap | +0.013 |
following | +0.013 |
Moon | +0.013 |
Neg logit contributions | |
gol | -0.029 |
aw | -0.025 |
David | -0.025 |
aden | -0.024 |
ax | -0.024 |
Token | spent |
Token ID | 3377 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
gol | +0.047 |
David | +0.039 |
arl | +0.038 |
aden | +0.036 |
fault | +0.036 |
Neg logit contributions | |
sn | -0.024 |
pap | -0.023 |
Sn | -0.022 |
Pr | -0.022 |
pur | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
elope | +0.032 |
isa | +0.032 |
Sn | +0.032 |
cel | +0.031 |
bing | +0.031 |
Neg logit contributions | |
gol | -0.078 |
aden | -0.065 |
David | -0.065 |
cheated | -0.062 |
aw | -0.062 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
gol | +0.033 |
aw | +0.027 |
aden | +0.027 |
David | +0.027 |
cheated | +0.026 |
Neg logit contributions | |
isa | -0.016 |
Sn | -0.016 |
cel | -0.016 |
elope | -0.016 |
pap | -0.016 |
Token | bouncing |
Token ID | 30713 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
cel | +0.014 |
isa | +0.014 |
bing | +0.014 |
Sn | +0.014 |
elope | +0.014 |
Neg logit contributions | |
gol | -0.036 |
David | -0.031 |
aden | -0.030 |
aw | -0.030 |
arl | -0.029 |
Token | until |
Token ID | 1566 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
bing | +0.003 |
sn | +0.003 |
Sn | +0.003 |
bed | +0.003 |
elope | +0.003 |
Neg logit contributions | |
gol | -0.009 |
David | -0.009 |
aden | -0.008 |
arl | -0.008 |
ax | -0.008 |
Token | soon |
Token ID | 2582 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Sn | +0.008 |
Pr | +0.008 |
sn | +0.007 |
roast | +0.007 |
Chick | +0.007 |
Neg logit contributions | |
gol | -0.019 |
aden | -0.016 |
arl | -0.016 |
aw | -0.016 |
ival | -0.016 |
Token | need |
Token ID | 761 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
isa | +0.009 |
elope | +0.009 |
Sn | +0.009 |
cel | +0.009 |
pap | +0.009 |
Neg logit contributions | |
gol | -0.014 |
David | -0.011 |
aw | -0.011 |
aden | -0.011 |
ival | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
gol | +0.007 |
aden | +0.006 |
aw | +0.006 |
David | +0.006 |
ival | +0.006 |
Neg logit contributions | |
pap | -0.003 |
Pr | -0.003 |
isa | -0.003 |
Sn | -0.003 |
Chick | -0.003 |
Token | be |
Token ID | 307 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
isa | +0.023 |
cel | +0.023 |
elope | +0.022 |
Sn | +0.022 |
pap | +0.022 |
Neg logit contributions | |
gol | -0.051 |
aw | -0.041 |
aden | -0.041 |
David | -0.041 |
cheated | -0.040 |
Token | wealthy |
Token ID | 11574 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
sn | +0.034 |
pap | +0.034 |
Sn | +0.033 |
mary | +0.033 |
Pr | +0.032 |
Neg logit contributions | |
gol | -0.050 |
aden | -0.041 |
David | -0.040 |
ival | -0.040 |
ane | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Sn | +0.014 |
pap | +0.014 |
bing | +0.013 |
elope | +0.013 |
cel | +0.013 |
Neg logit contributions | |
gol | -0.038 |
David | -0.033 |
aden | -0.032 |
aw | -0.032 |
ival | -0.031 |
Token | be |
Token ID | 307 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
pap | +0.019 |
Sn | +0.019 |
sn | +0.019 |
elope | +0.019 |
Chick | +0.019 |
Neg logit contributions | |
gol | -0.053 |
aw | -0.044 |
ival | -0.044 |
aden | -0.044 |
David | -0.043 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
sn | +0.032 |
pap | +0.032 |
mary | +0.031 |
elope | +0.031 |
bing | +0.031 |
Neg logit contributions | |
gol | -0.059 |
aden | -0.049 |
David | -0.047 |
ival | -0.047 |
ane | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
Sn | +0.018 |
pap | +0.017 |
bing | +0.017 |
elope | +0.017 |
cel | +0.017 |
Neg logit contributions | |
gol | -0.058 |
David | -0.050 |
aden | -0.049 |
aw | -0.049 |
ival | -0.048 |
Token | Their |
Token ID | 5334 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Sn | +0.015 |
Pr | +0.015 |
Chick | +0.014 |
elope | +0.014 |
pap | +0.014 |
Neg logit contributions | |
gol | -0.038 |
ival | -0.032 |
aden | -0.032 |
aw | -0.031 |
ax | -0.031 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
pap | +0.016 |
Sn | +0.015 |
elope | +0.015 |
sn | +0.014 |
pur | +0.014 |
Neg logit contributions | |
gol | -0.057 |
aw | -0.049 |
aden | -0.049 |
David | -0.048 |
ival | -0.047 |
Token | smiled |
Token ID | 13541 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
isa | +0.025 |
Sn | +0.025 |
elope | +0.025 |
cel | +0.025 |
pap | +0.024 |
Neg logit contributions | |
gol | -0.039 |
aw | -0.031 |
aden | -0.031 |
David | -0.030 |
cheated | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
isa | +0.008 |
cel | +0.008 |
Sn | +0.008 |
elope | +0.008 |
pap | +0.008 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.015 |
aden | -0.015 |
David | -0.015 |
cheated | -0.014 |
Token | ok |
Token ID | 12876 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
isa | +0.005 |
Sn | +0.005 |
cel | +0.005 |
elope | +0.005 |
pap | +0.005 |
Neg logit contributions | |
gol | -0.008 |
aw | -0.007 |
aden | -0.006 |
David | -0.006 |
cheated | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
cel | +0.065 |
bing | +0.063 |
isa | +0.062 |
Sn | +0.062 |
pap | +0.062 |
Neg logit contributions | |
gol | -0.118 |
aw | -0.098 |
aden | -0.096 |
David | -0.096 |
cheated | -0.095 |
Token | She |
Token ID | 1375 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
isa | +0.009 |
Sn | +0.009 |
cel | +0.009 |
elope | +0.009 |
pap | +0.009 |
Neg logit contributions | |
gol | -0.016 |
aw | -0.013 |
aden | -0.013 |
David | -0.013 |
cheated | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
isa | +0.029 |
cel | +0.029 |
Sn | +0.029 |
elope | +0.028 |
bing | +0.028 |
Neg logit contributions | |
gol | -0.044 |
aw | -0.035 |
aden | -0.035 |
David | -0.034 |
cheated | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Sn | +0.002 |
pap | +0.002 |
sn | +0.002 |
Pr | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
gol | -0.007 |
aden | -0.006 |
David | -0.006 |
aw | -0.006 |
ax | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Sn | +0.007 |
pap | +0.007 |
Pr | +0.007 |
isa | +0.007 |
elope | +0.007 |
Neg logit contributions | |
gol | -0.017 |
aw | -0.014 |
aden | -0.014 |
David | -0.013 |
ax | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
gol | +0.008 |
aw | +0.006 |
cheated | +0.006 |
aden | +0.006 |
David | +0.006 |
Neg logit contributions | |
isa | -0.004 |
cel | -0.004 |
Sn | -0.004 |
pap | -0.004 |
elope | -0.004 |
Token | ok |
Token ID | 12876 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
gol | +0.005 |
aw | +0.004 |
aden | +0.004 |
David | +0.004 |
cheated | +0.004 |
Neg logit contributions | |
isa | -0.003 |
Sn | -0.003 |
cel | -0.003 |
elope | -0.003 |
pap | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
cel | +0.063 |
bing | +0.061 |
Sn | +0.061 |
isa | +0.060 |
roast | +0.059 |
Neg logit contributions | |
gol | -0.095 |
aw | -0.079 |
David | -0.077 |
aden | -0.077 |
cheated | -0.075 |
Token | make |
Token ID | 787 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Sn | +0.012 |
elope | +0.012 |
isa | +0.012 |
cel | +0.012 |
pap | +0.012 |
Neg logit contributions | |
gol | -0.039 |
aw | -0.033 |
aden | -0.032 |
David | -0.032 |
ival | -0.031 |
Token | help |
Token ID | 1037 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
gol | +0.024 |
aw | +0.020 |
aden | +0.020 |
David | +0.019 |
cheated | +0.019 |
Neg logit contributions | |
Sn | -0.011 |
isa | -0.011 |
cel | -0.011 |
pap | -0.011 |
elope | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
elope | +0.027 |
isa | +0.027 |
cel | +0.027 |
pap | +0.026 |
Moon | +0.026 |
Neg logit contributions | |
gol | -0.042 |
David | -0.034 |
aden | -0.034 |
he | -0.033 |
aw | -0.033 |
Token | telling |
Token ID | 5149 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
gol | +0.011 |
aw | +0.009 |
aden | +0.009 |
David | +0.009 |
ax | +0.009 |
Neg logit contributions | |
isa | -0.004 |
elope | -0.004 |
cel | -0.004 |
bing | -0.004 |
Sn | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
elope | +0.037 |
cel | +0.037 |
bing | +0.036 |
isa | +0.036 |
mary | +0.035 |
Neg logit contributions | |
gol | -0.039 |
aw | -0.032 |
aden | -0.032 |
David | -0.031 |
ax | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
isa | +0.027 |
Sn | +0.027 |
pap | +0.027 |
elope | +0.027 |
cel | +0.027 |
Neg logit contributions | |
gol | -0.056 |
aw | -0.046 |
aden | -0.046 |
David | -0.045 |
cheated | -0.044 |
Token | M |
Token ID | 44 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
Sn | +0.022 |
isa | +0.022 |
cel | +0.021 |
elope | +0.021 |
bing | +0.021 |
Neg logit contributions | |
gol | -0.041 |
aden | -0.033 |
aw | -0.033 |
David | -0.033 |
cheated | -0.032 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
cel | +0.137 |
elope | +0.135 |
Sn | +0.133 |
isa | +0.133 |
bing | +0.133 |
Neg logit contributions | |
gol | -0.197 |
aw | -0.162 |
aden | -0.157 |
David | -0.154 |
ival | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
pap | +0.039 |
Sn | +0.039 |
isa | +0.039 |
elope | +0.038 |
Pr | +0.038 |
Neg logit contributions | |
gol | -0.091 |
aden | -0.075 |
aw | -0.074 |
David | -0.074 |
cheated | -0.072 |
Token | I |
Token ID | 314 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
elope | +0.004 |
isa | +0.004 |
bing | +0.004 |
cel | +0.004 |
eyel | +0.004 |
Neg logit contributions | |
gol | -0.005 |
aden | -0.004 |
aw | -0.004 |
ax | -0.003 |
ival | -0.003 |
Token | wanna |
Token ID | 18869 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
gol | +0.046 |
aw | +0.038 |
aden | +0.037 |
David | +0.036 |
ival | +0.035 |
Neg logit contributions | |
pap | -0.028 |
Sn | -0.028 |
elope | -0.028 |
cel | -0.028 |
isa | -0.028 |
Token | invite |
Token ID | 14037 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
gol | +0.062 |
aden | +0.050 |
David | +0.050 |
aw | +0.049 |
cheated | +0.048 |
Neg logit contributions | |
isa | -0.035 |
elope | -0.035 |
cel | -0.034 |
pap | -0.034 |
bing | -0.034 |
Token | joy |
Token ID | 8716 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
cel | +0.006 |
Sn | +0.006 |
isa | +0.006 |
bing | +0.005 |
elope | +0.005 |
Neg logit contributions | |
gol | -0.009 |
aw | -0.007 |
aden | -0.007 |
David | -0.007 |
cheated | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
gol | +0.013 |
aw | +0.010 |
aden | +0.010 |
David | +0.010 |
cheated | +0.010 |
Neg logit contributions | |
isa | -0.012 |
cel | -0.012 |
Sn | -0.012 |
elope | -0.012 |
pap | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
gol | +0.004 |
aw | +0.003 |
David | +0.003 |
aden | +0.003 |
cheated | +0.003 |
Neg logit contributions | |
cel | -0.003 |
isa | -0.003 |
Sn | -0.003 |
elope | -0.003 |
bing | -0.003 |
Token | new |
Token ID | 649 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
gol | +0.020 |
aw | +0.017 |
aden | +0.016 |
David | +0.016 |
happened | +0.016 |
Neg logit contributions | |
Sn | -0.012 |
cel | -0.012 |
isa | -0.012 |
elope | -0.011 |
bing | -0.011 |
Token | baby |
Token ID | 5156 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
gol | +0.079 |
happened | +0.066 |
aw | +0.064 |
fault | +0.060 |
chalk | +0.060 |
Neg logit contributions | |
cel | -0.076 |
Stacy | -0.073 |
Sn | -0.072 |
Luna | -0.069 |
isa | -0.069 |
Token | chick |
Token ID | 17943 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
cel | +0.022 |
eyel | +0.022 |
Sn | +0.021 |
Stacy | +0.021 |
hips | +0.020 |
Neg logit contributions | |
gol | -0.034 |
aw | -0.033 |
happened | -0.029 |
he | -0.029 |
ane | -0.028 |
Token | together |
Token ID | 1978 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
cel | +0.106 |
isa | +0.103 |
Sn | +0.102 |
pap | +0.099 |
bing | +0.096 |
Neg logit contributions | |
gol | -0.176 |
aw | -0.149 |
cheated | -0.139 |
aden | -0.137 |
ax | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
isa | +0.010 |
Sn | +0.010 |
elope | +0.010 |
cel | +0.010 |
pap | +0.010 |
Neg logit contributions | |
gol | -0.032 |
aden | -0.027 |
David | -0.027 |
aw | -0.027 |
cheated | -0.026 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
gol | +0.011 |
aw | +0.009 |
aden | +0.009 |
David | +0.009 |
cheated | +0.009 |
Neg logit contributions | |
Sn | -0.006 |
elope | -0.006 |
cel | -0.006 |
Pr | -0.006 |
isa | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
gol | +0.017 |
aden | +0.014 |
tant | +0.014 |
David | +0.014 |
aw | +0.014 |
Neg logit contributions | |
Sn | -0.006 |
elope | -0.006 |
Pr | -0.005 |
Flower | -0.005 |
Moon | -0.005 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Pr | +0.012 |
elope | +0.012 |
pap | +0.012 |
Ana | +0.011 |
isa | +0.011 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.015 |
David | -0.014 |
ival | -0.014 |
aden | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
cel | +0.014 |
we | +0.014 |
bing | +0.013 |
isa | +0.013 |
bes | +0.013 |
Neg logit contributions | |
gol | -0.012 |
happened | -0.011 |
aw | -0.010 |
Tommy | -0.010 |
cheated | -0.010 |
Token | special |
Token ID | 2041 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
gol | +0.018 |
Tommy | +0.016 |
happened | +0.016 |
aw | +0.016 |
av | +0.015 |
Neg logit contributions | |
we | -0.022 |
cel | -0.020 |
roast | -0.018 |
isa | -0.018 |
convince | -0.018 |
Token | days |
Token ID | 1528 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
gol | +0.029 |
happened | +0.027 |
chalk | +0.023 |
aw | +0.023 |
trophies | +0.022 |
Neg logit contributions | |
Sn | -0.030 |
cel | -0.030 |
Chick | -0.029 |
mary | -0.029 |
Pr | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gol | +0.041 |
aden | +0.035 |
David | +0.035 |
aw | +0.034 |
cheated | +0.033 |
Neg logit contributions | |
isa | -0.015 |
Sn | -0.015 |
elope | -0.015 |
pap | -0.015 |
Pr | -0.014 |
Token | like |
Token ID | 588 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
gol | +0.041 |
aw | +0.035 |
Tommy | +0.033 |
happened | +0.033 |
cheated | +0.032 |
Neg logit contributions | |
cel | -0.027 |
bing | -0.024 |
isa | -0.024 |
hips | -0.024 |
we | -0.023 |
Token | Honey |
Token ID | 21788 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
gol | +0.038 |
aw | +0.032 |
David | +0.031 |
aden | +0.031 |
ival | +0.030 |
Neg logit contributions | |
pap | -0.015 |
Sn | -0.015 |
Moon | -0.014 |
Pr | -0.014 |
Flower | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Sn | +0.087 |
cel | +0.087 |
isa | +0.085 |
elope | +0.084 |
bing | +0.082 |
Neg logit contributions | |
gol | -0.195 |
aw | -0.164 |
aden | -0.158 |
David | -0.158 |
cheated | -0.155 |
Token | birthday |
Token ID | 10955 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
pap | +0.026 |
Sn | +0.026 |
elope | +0.026 |
isa | +0.026 |
cel | +0.026 |
Neg logit contributions | |
gol | -0.051 |
aw | -0.041 |
aden | -0.041 |
David | -0.041 |
cheated | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Sn | +0.011 |
isa | +0.011 |
elope | +0.011 |
pap | +0.011 |
cel | +0.011 |
Neg logit contributions | |
gol | -0.029 |
David | -0.024 |
aden | -0.024 |
aw | -0.023 |
cheated | -0.023 |
Token | Buzz |
Token ID | 15753 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
gol | +0.055 |
aden | +0.046 |
David | +0.045 |
aw | +0.045 |
cheated | +0.044 |
Neg logit contributions | |
Sn | -0.022 |
pap | -0.022 |
elope | -0.021 |
isa | -0.021 |
cel | -0.021 |
Token | y |
Token ID | 88 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
isa | +0.055 |
elope | +0.054 |
pap | +0.053 |
Sn | +0.052 |
mary | +0.052 |
Neg logit contributions | |
gol | -0.092 |
aden | -0.073 |
David | -0.073 |
aw | -0.072 |
ival | -0.071 |
Token | shop |
Token ID | 6128 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
pap | +0.020 |
Sn | +0.019 |
Moon | +0.019 |
Pr | +0.018 |
sn | +0.018 |
Neg logit contributions | |
gol | -0.027 |
aden | -0.023 |
David | -0.023 |
cheated | -0.022 |
aw | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
cel | +0.009 |
isa | +0.009 |
elope | +0.009 |
bing | +0.008 |
Sn | +0.008 |
Neg logit contributions | |
gol | -0.018 |
aw | -0.015 |
aden | -0.015 |
David | -0.014 |
ival | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
gol | +0.009 |
aw | +0.007 |
David | +0.006 |
chalk | +0.006 |
aden | +0.006 |
Neg logit contributions | |
isa | -0.008 |
bing | -0.008 |
we | -0.008 |
elope | -0.008 |
cel | -0.008 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
cel | +0.019 |
bing | +0.019 |
isa | +0.019 |
Sn | +0.019 |
elope | +0.019 |
Neg logit contributions | |
gol | -0.028 |
aw | -0.022 |
David | -0.022 |
aden | -0.022 |
cheated | -0.021 |
Token | Po |
Token ID | 7695 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
elope | +0.023 |
isa | +0.023 |
cel | +0.022 |
bing | +0.021 |
Sn | +0.021 |
Neg logit contributions | |
gol | -0.039 |
aw | -0.032 |
aden | -0.031 |
chalk | -0.030 |
ax | -0.030 |
Token | ppy |
Token ID | 14097 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Sn | +0.062 |
elope | +0.062 |
isa | +0.061 |
bing | +0.061 |
cel | +0.061 |
Neg logit contributions | |
gol | -0.130 |
aw | -0.108 |
aden | -0.108 |
David | -0.105 |
ax | -0.103 |
Token | some |
Token ID | 617 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
cel | +0.111 |
isa | +0.108 |
elope | +0.107 |
Sn | +0.106 |
bing | +0.106 |
Neg logit contributions | |
gol | -0.190 |
aw | -0.157 |
David | -0.154 |
aden | -0.154 |
ival | -0.149 |
Token | money |
Token ID | 1637 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
sn | +0.053 |
pap | +0.053 |
Pr | +0.052 |
roast | +0.052 |
Sn | +0.052 |
Neg logit contributions | |
gol | -0.083 |
David | -0.070 |
aden | -0.069 |
ax | -0.065 |
cheated | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
gol | +0.115 |
David | +0.095 |
aden | +0.095 |
aw | +0.094 |
cheated | +0.092 |
Neg logit contributions | |
Sn | -0.038 |
pap | -0.037 |
Pr | -0.036 |
isa | -0.035 |
mary | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
gol | +0.016 |
aw | +0.013 |
David | +0.013 |
aden | +0.013 |
cheated | +0.012 |
Neg logit contributions | |
cel | -0.009 |
isa | -0.009 |
elope | -0.009 |
bing | -0.009 |
Sn | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
Sn | +0.003 |
pap | +0.003 |
Pr | +0.003 |
cel | +0.003 |
Chick | +0.003 |
Neg logit contributions | |
gol | -0.010 |
aden | -0.008 |
David | -0.008 |
aw | -0.008 |
cheated | -0.008 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
gol | +0.036 |
aden | +0.029 |
David | +0.028 |
arl | +0.028 |
aw | +0.028 |
Neg logit contributions | |
sn | -0.023 |
pur | -0.022 |
pap | -0.021 |
cel | -0.021 |
elope | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
gol | +0.065 |
aw | +0.054 |
aden | +0.054 |
David | +0.053 |
ival | +0.053 |
Neg logit contributions | |
pap | -0.028 |
bing | -0.028 |
Sn | -0.028 |
cel | -0.028 |
isa | -0.028 |
Token | |
Token ID | 220 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Pr | +0.002 |
Sn | +0.002 |
elope | +0.002 |
pap | +0.002 |
cel | +0.002 |
Neg logit contributions | |
gol | -0.004 |
aden | -0.003 |
cheated | -0.003 |
aw | -0.003 |
ival | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Pr | +0.025 |
Sn | +0.025 |
elope | +0.024 |
Chick | +0.024 |
Luna | +0.023 |
Neg logit contributions | |
gol | -0.083 |
tant | -0.069 |
trophies | -0.068 |
aw | -0.067 |
aden | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
gol | +0.006 |
cheated | +0.005 |
aden | +0.005 |
trophies | +0.005 |
tant | +0.005 |
Neg logit contributions | |
elope | -0.003 |
Pr | -0.003 |
Sn | -0.003 |
mary | -0.003 |
Chick | -0.003 |
Token | Sad |
Token ID | 26699 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
elope | +0.008 |
isa | +0.007 |
Sn | +0.007 |
cel | +0.007 |
bing | +0.007 |
Neg logit contributions | |
gol | -0.013 |
aden | -0.010 |
cheated | -0.010 |
aw | -0.010 |
David | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
isa | +0.090 |
elope | +0.090 |
pap | +0.089 |
Pr | +0.086 |
Sn | +0.085 |
Neg logit contributions | |
gol | -0.220 |
David | -0.179 |
aden | -0.179 |
ival | -0.179 |
cheated | -0.177 |
Token | upset |
Token ID | 9247 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
gol | +0.034 |
aden | +0.027 |
aw | +0.027 |
David | +0.026 |
ival | +0.026 |
Neg logit contributions | |
isa | -0.027 |
elope | -0.027 |
Sn | -0.027 |
pap | -0.027 |
bing | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
gol | +0.101 |
aden | +0.082 |
David | +0.082 |
aw | +0.082 |
cheated | +0.079 |
Neg logit contributions | |
isa | -0.045 |
Sn | -0.045 |
elope | -0.045 |
cel | -0.045 |
pap | -0.044 |
Token | Sandy |
Token ID | 17581 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
gol | +0.038 |
aden | +0.030 |
David | +0.030 |
aw | +0.030 |
cheated | +0.029 |
Neg logit contributions | |
Sn | -0.025 |
elope | -0.025 |
isa | -0.025 |
pap | -0.025 |
cel | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
elope | +0.006 |
isa | +0.006 |
Sn | +0.006 |
cel | +0.006 |
pap | +0.006 |
Neg logit contributions | |
gol | -0.013 |
aden | -0.011 |
David | -0.011 |
aw | -0.011 |
ival | -0.010 |