Token | kind |
Token ID | 1611 |
Feature activation | -1.81e-04 |
Pos logit contributions | |
aro | +0.029 |
beans | +0.029 |
chers | +0.028 |
tickets | +0.027 |
suits | +0.027 |
Neg logit contributions | |
dent | -0.014 |
impact | -0.011 |
regret | -0.010 |
need | -0.009 |
ivering | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
dent | +0.000 |
regret | +0.000 |
impact | +0.000 |
need | +0.000 |
ivering | +0.000 |
Neg logit contributions | |
aro | -0.000 |
beans | -0.000 |
chers | -0.000 |
suits | -0.000 |
Off | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
aro | +0.007 |
beans | +0.007 |
chers | +0.007 |
tickets | +0.006 |
suits | +0.006 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.003 |
impact | -0.003 |
need | -0.003 |
ivering | -0.003 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
aro | +0.016 |
beans | +0.016 |
chers | +0.014 |
suits | +0.014 |
mons | +0.014 |
Neg logit contributions | |
dent | -0.017 |
regret | -0.016 |
need | -0.016 |
impact | -0.015 |
ivering | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
aro | +0.006 |
beans | +0.006 |
resp | +0.005 |
chers | +0.005 |
suits | +0.005 |
Neg logit contributions | |
dent | -0.002 |
regret | -0.002 |
need | -0.002 |
impact | -0.002 |
pain | -0.001 |
Token | clay |
Token ID | 21558 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.004 |
chers | +0.004 |
cakes | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.006 |
regret | -0.005 |
impact | -0.005 |
ivering | -0.005 |
need | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
aro | +0.145 |
rob | +0.143 |
ela | +0.139 |
chers | +0.135 |
beans | +0.134 |
Neg logit contributions | |
need | -0.097 |
dent | -0.088 |
impact | -0.081 |
end | -0.079 |
He | -0.079 |
Token | big |
Token ID | 1263 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
aro | +0.004 |
beans | +0.004 |
chers | +0.004 |
mons | +0.003 |
bags | +0.003 |
Neg logit contributions | |
dent | -0.003 |
regret | -0.002 |
need | -0.002 |
impact | -0.002 |
pain | -0.002 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
beans | +0.037 |
aro | +0.036 |
chers | +0.034 |
suits | +0.034 |
tickets | +0.034 |
Neg logit contributions | |
dent | -0.030 |
regret | -0.025 |
impact | -0.025 |
ivering | -0.024 |
need | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
dent | +0.019 |
need | +0.017 |
regret | +0.016 |
impact | +0.016 |
ivering | +0.015 |
Neg logit contributions | |
aro | -0.030 |
beans | -0.030 |
chers | -0.028 |
suits | -0.027 |
bags | -0.027 |
Token | told |
Token ID | 1297 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
aro | +0.006 |
suits | +0.006 |
beans | +0.005 |
ela | +0.005 |
chers | +0.005 |
Neg logit contributions | |
regret | -0.005 |
need | -0.004 |
dent | -0.004 |
pain | -0.004 |
damage | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
aro | +0.029 |
beans | +0.029 |
suits | +0.027 |
chers | +0.027 |
tickets | +0.027 |
Neg logit contributions | |
dent | -0.025 |
regret | -0.021 |
impact | -0.021 |
ivering | -0.020 |
need | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
aro | +0.043 |
beans | +0.041 |
chers | +0.040 |
suits | +0.039 |
tickets | +0.039 |
Neg logit contributions | |
dent | -0.041 |
impact | -0.035 |
regret | -0.035 |
ivering | -0.034 |
need | -0.033 |
Token | One |
Token ID | 3198 |
Feature activation | +3.92e-03 |
Pos logit contributions | |
aro | +0.044 |
beans | +0.044 |
chers | +0.042 |
suits | +0.041 |
tickets | +0.040 |
Neg logit contributions | |
dent | -0.027 |
regret | -0.022 |
impact | -0.022 |
need | -0.021 |
ivering | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
aro | +0.008 |
beans | +0.008 |
chers | +0.008 |
tickets | +0.007 |
bags | +0.007 |
Neg logit contributions | |
dent | -0.005 |
regret | -0.004 |
need | -0.004 |
impact | -0.004 |
ivering | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
beans | +0.056 |
aro | +0.054 |
chers | +0.051 |
cakes | +0.051 |
apr | +0.050 |
Neg logit contributions | |
dent | -0.036 |
need | -0.031 |
regret | -0.031 |
impact | -0.029 |
pain | -0.028 |
Token | Beat |
Token ID | 12568 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
beans | +0.064 |
aro | +0.061 |
mons | +0.055 |
chers | +0.055 |
cr | +0.055 |
Neg logit contributions | |
dent | -0.067 |
need | -0.061 |
regret | -0.060 |
pain | -0.056 |
impact | -0.056 |
Token | rice |
Token ID | 20970 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
apr | +0.111 |
beans | +0.109 |
kins | +0.104 |
cakes | +0.101 |
aro | +0.100 |
Neg logit contributions | |
dent | -0.108 |
regret | -0.103 |
hurting | -0.097 |
lose | -0.095 |
ivering | -0.094 |
Token | â |
Token ID | 22940 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
dent | +0.017 |
regret | +0.016 |
need | +0.016 |
impact | +0.014 |
pain | +0.014 |
Neg logit contributions | |
aro | -0.025 |
beans | -0.024 |
chers | -0.022 |
tickets | -0.021 |
cakes | -0.021 |
Token | € |
Token ID | 26391 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
aro | +0.007 |
beans | +0.007 |
suits | +0.007 |
chers | +0.007 |
Off | +0.007 |
Neg logit contributions | |
dent | -0.011 |
regret | -0.009 |
impact | -0.009 |
need | -0.009 |
ivering | -0.009 |
Token | ™ |
Token ID | 8151 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.023 |
chers | +0.021 |
tickets | +0.020 |
cakes | +0.020 |
Neg logit contributions | |
dent | -0.034 |
regret | -0.030 |
impact | -0.029 |
need | -0.029 |
ivering | -0.029 |
Token | s |
Token ID | 82 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
dent | +0.014 |
impact | +0.012 |
regret | +0.012 |
need | +0.011 |
ivering | +0.011 |
Neg logit contributions | |
aro | -0.016 |
beans | -0.015 |
chers | -0.015 |
suits | -0.014 |
tickets | -0.014 |
Token | ran |
Token ID | 4966 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
aro | +0.008 |
beans | +0.008 |
mons | +0.008 |
chers | +0.008 |
resp | +0.007 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.008 |
need | -0.008 |
impact | -0.008 |
ivering | -0.007 |
Token | over |
Token ID | 625 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
aro | +0.038 |
beans | +0.038 |
mons | +0.036 |
chers | +0.035 |
kins | +0.035 |
Neg logit contributions | |
dent | -0.031 |
regret | -0.028 |
need | -0.027 |
impact | -0.027 |
pain | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
beans | +0.059 |
aro | +0.059 |
chers | +0.057 |
mons | +0.056 |
resp | +0.055 |
Neg logit contributions | |
dent | -0.048 |
regret | -0.045 |
need | -0.044 |
impact | -0.042 |
pain | -0.041 |
Token | gave |
Token ID | 2921 |
Feature activation | +4.35e-04 |
Pos logit contributions | |
resp | +0.022 |
beans | +0.021 |
mons | +0.020 |
aro | +0.020 |
apr | +0.020 |
Neg logit contributions | |
regret | -0.017 |
dent | -0.017 |
crying | -0.016 |
need | -0.015 |
hurting | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
beans | +0.001 |
suits | +0.001 |
aro | +0.001 |
resp | +0.001 |
chers | +0.001 |
Neg logit contributions | |
regret | -0.001 |
dent | -0.001 |
need | -0.000 |
pain | -0.000 |
impact | -0.000 |
Token | skeleton |
Token ID | 18328 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
dent | +0.018 |
ivering | +0.016 |
impact | +0.016 |
regret | +0.015 |
need | +0.015 |
Neg logit contributions | |
beans | -0.017 |
aro | -0.017 |
chers | -0.016 |
tickets | -0.015 |
da | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
aro | +0.138 |
rob | +0.134 |
mons | +0.133 |
girls | +0.130 |
chers | +0.129 |
Neg logit contributions | |
need | -0.081 |
regret | -0.071 |
end | -0.071 |
dent | -0.068 |
impact | -0.067 |
Token | big |
Token ID | 1263 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
aro | +0.006 |
beans | +0.006 |
mons | +0.006 |
ils | +0.006 |
kins | +0.006 |
Neg logit contributions | |
dent | -0.003 |
need | -0.003 |
regret | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
aro | +0.042 |
beans | +0.042 |
chers | +0.040 |
suits | +0.038 |
mons | +0.038 |
Neg logit contributions | |
dent | -0.030 |
impact | -0.025 |
regret | -0.025 |
need | -0.024 |
ivering | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +5.11e-03 |
Pos logit contributions | |
dent | +0.022 |
regret | +0.019 |
impact | +0.018 |
need | +0.018 |
ivering | +0.017 |
Neg logit contributions | |
aro | -0.039 |
beans | -0.039 |
chers | -0.037 |
suits | -0.036 |
mons | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.010 |
suits | +0.009 |
tickets | +0.009 |
Neg logit contributions | |
dent | -0.006 |
regret | -0.005 |
impact | -0.005 |
need | -0.005 |
ivering | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.005 |
suits | +0.005 |
chers | +0.005 |
mons | +0.005 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.003 |
need | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | visit |
Token ID | 3187 |
Feature activation | +1.31e-04 |
Pos logit contributions | |
dent | +0.007 |
impact | +0.006 |
ivering | +0.006 |
regret | +0.006 |
need | +0.005 |
Neg logit contributions | |
aro | -0.008 |
beans | -0.008 |
chers | -0.008 |
tickets | -0.008 |
Off | -0.008 |
Token | people |
Token ID | 661 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
beans | +0.000 |
aro | +0.000 |
mons | +0.000 |
suits | +0.000 |
ista | +0.000 |
Neg logit contributions | |
dent | -0.000 |
need | -0.000 |
impact | -0.000 |
regret | -0.000 |
damage | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
aro | +0.035 |
beans | +0.034 |
mons | +0.032 |
resp | +0.031 |
cakes | +0.030 |
Neg logit contributions | |
need | -0.025 |
dent | -0.025 |
impact | -0.023 |
regret | -0.022 |
ivering | -0.022 |
Token | give |
Token ID | 1577 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
beans | +0.018 |
aro | +0.018 |
chers | +0.017 |
suits | +0.017 |
cakes | +0.017 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
impact | -0.011 |
need | -0.011 |
ivering | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
beans | +0.030 |
aro | +0.028 |
suits | +0.027 |
resp | +0.027 |
kins | +0.027 |
Neg logit contributions | |
need | -0.015 |
dent | -0.014 |
regret | -0.013 |
impact | -0.013 |
temptation | -0.012 |
Token | medals |
Token ID | 28057 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
aro | +0.132 |
rob | +0.126 |
beans | +0.125 |
ela | +0.124 |
mons | +0.118 |
Neg logit contributions | |
need | -0.088 |
end | -0.080 |
anymore | -0.071 |
impact | -0.071 |
my | -0.070 |
Token | for |
Token ID | 329 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
aro | +0.072 |
Hil | +0.066 |
Fel | +0.065 |
beans | +0.065 |
tad | +0.065 |
Neg logit contributions | |
dent | -0.038 |
need | -0.038 |
anymore | -0.036 |
impact | -0.033 |
end | -0.029 |
Token | being |
Token ID | 852 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
beans | +0.028 |
aro | +0.027 |
suits | +0.027 |
cakes | +0.026 |
bags | +0.026 |
Neg logit contributions | |
dent | -0.023 |
need | -0.022 |
impact | -0.021 |
regret | -0.021 |
pain | -0.020 |
Token | helpful |
Token ID | 7613 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
beans | +0.025 |
aro | +0.024 |
cakes | +0.023 |
mons | +0.023 |
fl | +0.023 |
Neg logit contributions | |
dent | -0.016 |
need | -0.015 |
regret | -0.014 |
lonely | -0.013 |
hurting | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
aro | +0.025 |
beans | +0.025 |
chers | +0.023 |
cakes | +0.022 |
mons | +0.022 |
Neg logit contributions | |
dent | -0.020 |
need | -0.018 |
impact | -0.018 |
regret | -0.017 |
ivering | -0.016 |
Token | ! |
Token ID | 0 |
Feature activation | +8.11e-03 |
Pos logit contributions | |
aro | +0.043 |
beans | +0.043 |
Off | +0.040 |
cakes | +0.040 |
suits | +0.039 |
Neg logit contributions | |
dent | -0.029 |
need | -0.027 |
regret | -0.023 |
impact | -0.023 |
ivering | -0.022 |
Token | Let |
Token ID | 3914 |
Feature activation | +9.25e-04 |
Pos logit contributions | |
beans | +0.015 |
aro | +0.015 |
chers | +0.014 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.011 |
regret | -0.009 |
impact | -0.009 |
need | -0.009 |
ivering | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +4.24e-04 |
Pos logit contributions | |
beans | +0.002 |
aro | +0.002 |
suits | +0.002 |
chers | +0.002 |
mons | +0.002 |
Neg logit contributions | |
dent | -0.001 |
regret | -0.001 |
need | -0.001 |
impact | -0.001 |
ivering | -0.001 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
beans | +0.001 |
aro | +0.001 |
chers | +0.001 |
suits | +0.001 |
tickets | +0.001 |
Neg logit contributions | |
dent | -0.001 |
regret | -0.001 |
impact | -0.000 |
need | -0.000 |
ivering | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -9.99e-04 |
Pos logit contributions | |
beans | +0.024 |
aro | +0.023 |
chers | +0.022 |
resp | +0.022 |
mons | +0.022 |
Neg logit contributions | |
dent | -0.023 |
need | -0.019 |
regret | -0.018 |
impact | -0.018 |
hurting | -0.017 |
Token | clay |
Token ID | 21558 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.002 |
impact | +0.002 |
ivering | +0.002 |
need | +0.001 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
chers | -0.001 |
tickets | -0.001 |
suits | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
aro | +0.124 |
ela | +0.114 |
Fre | +0.113 |
beans | +0.113 |
Fel | +0.110 |
Neg logit contributions | |
dent | -0.104 |
need | -0.096 |
anymore | -0.087 |
impact | -0.086 |
end | -0.082 |
Token | something |
Token ID | 1223 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
beans | +0.025 |
aro | +0.025 |
chers | +0.023 |
suits | +0.023 |
cakes | +0.023 |
Neg logit contributions | |
dent | -0.033 |
regret | -0.029 |
impact | -0.029 |
need | -0.029 |
pain | -0.027 |
Token | new |
Token ID | 649 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
aro | +0.063 |
beans | +0.062 |
chers | +0.059 |
mons | +0.059 |
suits | +0.058 |
Neg logit contributions | |
dent | -0.056 |
regret | -0.048 |
need | -0.047 |
impact | -0.047 |
pain | -0.043 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
aro | +0.064 |
beans | +0.061 |
cakes | +0.060 |
Hil | +0.059 |
mons | +0.059 |
Neg logit contributions | |
dent | -0.030 |
need | -0.026 |
anymore | -0.025 |
impact | -0.024 |
regret | -0.022 |
Token | Joe |
Token ID | 5689 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
beans | +0.017 |
aro | +0.016 |
chers | +0.016 |
tickets | +0.014 |
resp | +0.014 |
Neg logit contributions | |
dent | -0.022 |
regret | -0.020 |
need | -0.020 |
impact | -0.020 |
ivering | -0.019 |
Token | together |
Token ID | 1978 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
aro | +0.068 |
tickets | +0.066 |
resp | +0.065 |
mons | +0.064 |
ista | +0.063 |
Neg logit contributions | |
anymore | -0.062 |
dent | -0.062 |
need | -0.061 |
impact | -0.061 |
regret | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
dent | +0.011 |
impact | +0.010 |
regret | +0.010 |
need | +0.009 |
ivering | +0.009 |
Neg logit contributions | |
aro | -0.020 |
beans | -0.020 |
chers | -0.019 |
cakes | -0.019 |
suits | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
dent | +0.002 |
need | +0.002 |
impact | +0.002 |
regret | +0.002 |
pain | +0.001 |
Neg logit contributions | |
beans | -0.004 |
aro | -0.004 |
chers | -0.004 |
suits | -0.003 |
bags | -0.003 |
Token | introduce |
Token ID | 10400 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.023 |
mons | +0.023 |
cakes | +0.022 |
resp | +0.022 |
Neg logit contributions | |
regret | -0.016 |
dent | -0.015 |
need | -0.015 |
impact | -0.014 |
end | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.019 |
chers | +0.018 |
suits | +0.018 |
mons | +0.018 |
Neg logit contributions | |
dent | -0.026 |
impact | -0.024 |
regret | -0.024 |
need | -0.024 |
pain | -0.023 |
Token | bug |
Token ID | 5434 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
aro | +0.066 |
cakes | +0.058 |
chers | +0.057 |
bags | +0.057 |
mons | +0.056 |
Neg logit contributions | |
impact | -0.059 |
need | -0.059 |
dent | -0.058 |
temptation | -0.057 |
pain | -0.056 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
rob | +0.136 |
kins | +0.134 |
aro | +0.134 |
beans | +0.133 |
apr | +0.130 |
Neg logit contributions | |
need | -0.060 |
anymore | -0.054 |
impact | -0.054 |
my | -0.052 |
end | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
aro | +0.048 |
mons | +0.048 |
beans | +0.048 |
cakes | +0.047 |
chers | +0.046 |
Neg logit contributions | |
need | -0.023 |
dent | -0.023 |
regret | -0.022 |
impact | -0.022 |
anymore | -0.021 |
Token | each |
Token ID | 1123 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
aro | +0.032 |
beans | +0.032 |
suits | +0.031 |
mons | +0.030 |
cakes | +0.030 |
Neg logit contributions | |
dent | -0.036 |
need | -0.034 |
regret | -0.034 |
impact | -0.034 |
pain | -0.031 |
Token | other |
Token ID | 584 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
aro | +0.010 |
beans | +0.010 |
mons | +0.009 |
suits | +0.009 |
cakes | +0.009 |
Neg logit contributions | |
dent | -0.005 |
need | -0.005 |
impact | -0.005 |
regret | -0.005 |
end | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | +7.67e-03 |
Pos logit contributions | |
aro | +0.062 |
mons | +0.060 |
beans | +0.059 |
cakes | +0.057 |
resp | +0.057 |
Neg logit contributions | |
dent | -0.036 |
need | -0.034 |
regret | -0.033 |
impact | -0.033 |
anymore | -0.029 |
Token | you |
Token ID | 345 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
beans | +0.006 |
aro | +0.006 |
chers | +0.005 |
suits | +0.005 |
tickets | +0.005 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.004 |
impact | -0.004 |
need | -0.003 |
ivering | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.019 |
chers | +0.018 |
suits | +0.017 |
tickets | +0.017 |
Neg logit contributions | |
dent | -0.020 |
impact | -0.017 |
regret | -0.017 |
ivering | -0.016 |
need | -0.016 |
Token | play |
Token ID | 711 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
dent | +0.004 |
impact | +0.003 |
ivering | +0.003 |
regret | +0.003 |
pain | +0.003 |
Neg logit contributions | |
aro | -0.003 |
beans | -0.003 |
chers | -0.003 |
cakes | -0.003 |
tickets | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
aro | +0.033 |
beans | +0.032 |
suits | +0.030 |
ista | +0.030 |
tickets | +0.030 |
Neg logit contributions | |
dent | -0.029 |
impact | -0.025 |
need | -0.024 |
regret | -0.024 |
pain | -0.023 |
Token | my |
Token ID | 616 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
beans | +0.031 |
suits | +0.029 |
aro | +0.029 |
chers | +0.029 |
ista | +0.028 |
Neg logit contributions | |
dent | -0.024 |
need | -0.021 |
regret | -0.020 |
impact | -0.020 |
ivering | -0.019 |
Token | clay |
Token ID | 21558 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.005 |
regret | -0.004 |
impact | -0.004 |
need | -0.004 |
ivering | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
aro | +0.113 |
beans | +0.107 |
ela | +0.102 |
tickets | +0.102 |
Off | +0.101 |
Neg logit contributions | |
dent | -0.117 |
impact | -0.100 |
need | -0.099 |
regret | -0.095 |
ivering | -0.091 |
Token | but |
Token ID | 475 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
beans | +0.018 |
aro | +0.018 |
chers | +0.017 |
suits | +0.016 |
tickets | +0.016 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
impact | -0.011 |
need | -0.011 |
ivering | -0.010 |
Token | please |
Token ID | 3387 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
dent | +0.043 |
impact | +0.036 |
regret | +0.036 |
ivering | +0.035 |
need | +0.034 |
Neg logit contributions | |
aro | -0.054 |
beans | -0.054 |
chers | -0.050 |
tickets | -0.049 |
suits | -0.048 |
Token | be |
Token ID | 307 |
Feature activation | -7.75e-03 |
Pos logit contributions | |
dent | +0.012 |
ivering | +0.010 |
impact | +0.010 |
regret | +0.009 |
pain | +0.009 |
Neg logit contributions | |
beans | -0.012 |
aro | -0.012 |
chers | -0.012 |
tickets | -0.011 |
dads | -0.011 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
dent | +0.012 |
regret | +0.011 |
impact | +0.010 |
need | +0.010 |
ivering | +0.010 |
Neg logit contributions | |
beans | -0.013 |
aro | -0.013 |
chers | -0.012 |
suits | -0.012 |
cakes | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
beans | +0.058 |
apr | +0.057 |
aro | +0.055 |
ishes | +0.053 |
suits | +0.053 |
Neg logit contributions | |
dent | -0.051 |
regret | -0.046 |
need | -0.046 |
pain | -0.042 |
end | -0.041 |
Token | called |
Token ID | 1444 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.022 |
mons | +0.021 |
suits | +0.021 |
chers | +0.021 |
Neg logit contributions | |
dent | -0.016 |
need | -0.014 |
regret | -0.014 |
impact | -0.012 |
hurting | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
beans | +0.003 |
aro | +0.003 |
mons | +0.003 |
kins | +0.003 |
suits | +0.003 |
Neg logit contributions | |
dent | -0.003 |
need | -0.003 |
impact | -0.003 |
temptation | -0.003 |
regret | -0.003 |
Token | Throw |
Token ID | 39431 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
beans | +0.048 |
aro | +0.047 |
bags | +0.044 |
kins | +0.044 |
tickets | +0.043 |
Neg logit contributions | |
dent | -0.052 |
need | -0.046 |
impact | -0.045 |
ivering | -0.044 |
regret | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.014 |
kins | +0.014 |
cakes | +0.014 |
Neg logit contributions | |
dent | -0.009 |
need | -0.008 |
impact | -0.008 |
temptation | -0.007 |
pain | -0.007 |
Token | Light |
Token ID | 4401 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
aro | +0.024 |
beans | +0.022 |
Fre | +0.020 |
resp | +0.020 |
mons | +0.020 |
Neg logit contributions | |
dent | -0.027 |
need | -0.025 |
impact | -0.023 |
pain | -0.023 |
temptation | -0.023 |
Token | ". |
Token ID | 1911 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
beans | +0.116 |
rob | +0.116 |
aro | +0.115 |
apr | +0.113 |
Hil | +0.110 |
Neg logit contributions | |
need | -0.086 |
impact | -0.074 |
anymore | -0.073 |
dent | -0.072 |
end | -0.071 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
aro | +0.006 |
beans | +0.006 |
chers | +0.006 |
cakes | +0.005 |
tickets | +0.005 |
Neg logit contributions | |
dent | -0.005 |
need | -0.004 |
regret | -0.004 |
impact | -0.004 |
pain | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
mons | +0.049 |
apr | +0.049 |
beans | +0.049 |
resp | +0.049 |
bou | +0.048 |
Neg logit contributions | |
regret | -0.029 |
need | -0.029 |
sad | -0.027 |
dent | -0.026 |
crying | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
aro | +0.024 |
beans | +0.024 |
cakes | +0.021 |
chers | +0.021 |
kins | +0.021 |
Neg logit contributions | |
dent | -0.021 |
need | -0.019 |
regret | -0.019 |
impact | -0.018 |
pain | -0.017 |
Token | take |
Token ID | 1011 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
dent | +0.003 |
regret | +0.003 |
impact | +0.003 |
need | +0.003 |
ivering | +0.003 |
Neg logit contributions | |
beans | -0.004 |
aro | -0.004 |
chers | -0.004 |
suits | -0.004 |
cakes | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +3.81e-04 |
Pos logit contributions | |
aro | +0.039 |
beans | +0.039 |
suits | +0.037 |
chers | +0.037 |
Off | +0.037 |
Neg logit contributions | |
dent | -0.027 |
impact | -0.022 |
regret | -0.022 |
ivering | -0.021 |
need | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
beans | +0.001 |
aro | +0.001 |
chers | +0.001 |
suits | +0.001 |
cakes | +0.000 |
Neg logit contributions | |
dent | -0.001 |
impact | -0.001 |
regret | -0.001 |
ivering | -0.001 |
need | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
dent | +0.017 |
impact | +0.015 |
ivering | +0.015 |
regret | +0.014 |
temptation | +0.013 |
Neg logit contributions | |
aro | -0.012 |
beans | -0.011 |
da | -0.011 |
Hil | -0.011 |
Fre | -0.011 |
Token | cute |
Token ID | 13779 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
beans | +0.024 |
aro | +0.024 |
suits | +0.022 |
chers | +0.022 |
mons | +0.022 |
Neg logit contributions | |
dent | -0.028 |
impact | -0.025 |
regret | -0.022 |
ivering | -0.022 |
need | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
chers | +0.003 |
tickets | +0.003 |
cakes | +0.002 |
Neg logit contributions | |
dent | -0.002 |
regret | -0.002 |
need | -0.002 |
ivering | -0.002 |
impact | -0.002 |
Token | Beat |
Token ID | 12568 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
aro | +0.023 |
Hil | +0.023 |
suits | +0.023 |
Off | +0.023 |
tickets | +0.022 |
Neg logit contributions | |
dent | -0.016 |
ivering | -0.013 |
impact | -0.013 |
regret | -0.012 |
pain | -0.011 |
Token | rice |
Token ID | 20970 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
beans | +0.111 |
apr | +0.110 |
kins | +0.107 |
ishes | +0.105 |
poles | +0.104 |
Neg logit contributions | |
dent | -0.094 |
regret | -0.093 |
hurting | -0.086 |
crying | -0.085 |
weeping | -0.084 |
Token | had |
Token ID | 550 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
dent | +0.007 |
regret | +0.007 |
need | +0.007 |
impact | +0.006 |
ivering | +0.006 |
Neg logit contributions | |
aro | -0.009 |
beans | -0.009 |
chers | -0.008 |
cakes | -0.008 |
tickets | -0.008 |
Token | five |
Token ID | 1936 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.020 |
chers | +0.018 |
tickets | +0.017 |
suits | +0.017 |
Neg logit contributions | |
dent | -0.035 |
impact | -0.031 |
regret | -0.031 |
ivering | -0.030 |
need | -0.030 |
Token | fingers |
Token ID | 9353 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
aro | +0.013 |
beans | +0.013 |
chers | +0.012 |
Off | +0.012 |
cakes | +0.012 |
Neg logit contributions | |
dent | -0.014 |
need | -0.012 |
regret | -0.012 |
impact | -0.012 |
ivering | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
dent | +0.009 |
impact | +0.009 |
regret | +0.008 |
temptation | +0.008 |
ivering | +0.008 |
Neg logit contributions | |
aro | -0.005 |
beans | -0.005 |
da | -0.005 |
es | -0.005 |
fl | -0.005 |
Token | two |
Token ID | 734 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
aro | +0.026 |
beans | +0.025 |
mons | +0.023 |
chers | +0.023 |
suits | +0.023 |
Neg logit contributions | |
dent | -0.025 |
need | -0.022 |
impact | -0.022 |
regret | -0.022 |
pain | -0.021 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
beans | +0.047 |
aro | +0.047 |
mons | +0.043 |
fl | +0.042 |
cr | +0.042 |
Neg logit contributions | |
dent | -0.046 |
need | -0.042 |
regret | -0.040 |
impact | -0.040 |
pain | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.022 |
mons | +0.021 |
resp | +0.020 |
cakes | +0.020 |
Neg logit contributions | |
need | -0.019 |
regret | -0.019 |
dent | -0.019 |
impact | -0.017 |
end | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
aro | +0.074 |
beans | +0.070 |
mons | +0.064 |
resp | +0.064 |
fl | +0.063 |
Neg logit contributions | |
need | -0.045 |
dent | -0.041 |
regret | -0.041 |
pain | -0.037 |
impact | -0.037 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
aro | +0.062 |
beans | +0.057 |
es | +0.055 |
mons | +0.055 |
resp | +0.054 |
Neg logit contributions | |
dent | -0.030 |
need | -0.029 |
regret | -0.027 |
impact | -0.026 |
sad | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
beans | +0.057 |
aro | +0.057 |
fl | +0.056 |
chers | +0.055 |
Hil | +0.055 |
Neg logit contributions | |
dent | -0.013 |
need | -0.013 |
impact | -0.010 |
regret | -0.010 |
damage | -0.008 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
aro | +0.157 |
beans | +0.154 |
cr | +0.147 |
resp | +0.144 |
als | +0.144 |
Neg logit contributions | |
need | -0.074 |
dent | -0.067 |
impact | -0.064 |
pain | -0.062 |
regret | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
beans | +0.039 |
aro | +0.039 |
chers | +0.037 |
cakes | +0.037 |
resp | +0.036 |
Neg logit contributions | |
dent | -0.028 |
need | -0.025 |
impact | -0.025 |
regret | -0.024 |
pain | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
beans | +0.040 |
aro | +0.040 |
chers | +0.038 |
suits | +0.038 |
tickets | +0.038 |
Neg logit contributions | |
dent | -0.036 |
regret | -0.030 |
impact | -0.030 |
ivering | -0.029 |
need | -0.028 |
Token | played |
Token ID | 2826 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
aro | +0.029 |
beans | +0.029 |
resp | +0.028 |
mons | +0.028 |
cakes | +0.027 |
Neg logit contributions | |
need | -0.022 |
regret | -0.021 |
dent | -0.020 |
impact | -0.018 |
hate | -0.017 |
Token | together |
Token ID | 1978 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
aro | +0.032 |
mons | +0.029 |
beans | +0.028 |
fl | +0.027 |
Hil | +0.027 |
Neg logit contributions | |
dent | -0.026 |
anymore | -0.024 |
end | -0.024 |
impact | -0.024 |
need | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
beans | +0.043 |
chers | +0.041 |
aro | +0.040 |
suits | +0.040 |
mons | +0.040 |
Neg logit contributions | |
dent | -0.021 |
need | -0.018 |
regret | -0.018 |
impact | -0.017 |
pain | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -6.18e-04 |
Pos logit contributions | |
resp | +0.022 |
beans | +0.022 |
aro | +0.021 |
rob | +0.021 |
suits | +0.020 |
Neg logit contributions | |
dent | -0.021 |
regret | -0.021 |
need | -0.020 |
sad | -0.019 |
pain | -0.019 |
Token | each |
Token ID | 1123 |
Feature activation | +9.40e-04 |
Pos logit contributions | |
regret | +0.001 |
dent | +0.001 |
need | +0.001 |
end | +0.001 |
impact | +0.001 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
mons | -0.001 |
resp | -0.001 |
fl | -0.001 |
Token | gave |
Token ID | 2921 |
Feature activation | -6.36e-04 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
chers | +0.001 |
cakes | +0.001 |
resp | +0.001 |
Neg logit contributions | |
dent | -0.001 |
need | -0.001 |
regret | -0.001 |
impact | -0.001 |
ivering | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
need | +0.001 |
impact | +0.001 |
pain | +0.001 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
resp | -0.001 |
chers | -0.001 |
bags | -0.001 |
Token | cube |
Token ID | 23441 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
beans | +0.028 |
aro | +0.028 |
chers | +0.026 |
resp | +0.025 |
suits | +0.025 |
Neg logit contributions | |
dent | -0.029 |
impact | -0.025 |
regret | -0.025 |
need | -0.024 |
pain | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
aro | +0.152 |
rob | +0.149 |
Fre | +0.136 |
chers | +0.134 |
Fel | +0.133 |
Neg logit contributions | |
need | -0.066 |
dent | -0.062 |
end | -0.060 |
impact | -0.055 |
sad | -0.054 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
aro | +0.006 |
beans | +0.005 |
mons | +0.005 |
chers | +0.005 |
fl | +0.005 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.003 |
need | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
dent | +0.016 |
need | +0.013 |
regret | +0.013 |
impact | +0.013 |
anymore | +0.012 |
Neg logit contributions | |
aro | -0.030 |
beans | -0.029 |
chers | -0.027 |
suits | -0.027 |
apr | -0.027 |
Token | folded |
Token ID | 24650 |
Feature activation | +1.85e-03 |
Pos logit contributions | |
dent | +0.019 |
regret | +0.016 |
impact | +0.016 |
need | +0.016 |
pain | +0.014 |
Neg logit contributions | |
aro | -0.024 |
beans | -0.023 |
chers | -0.023 |
suits | -0.022 |
resp | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
chers | +0.003 |
resp | +0.003 |
suits | +0.003 |
Neg logit contributions | |
dent | -0.003 |
regret | -0.003 |
impact | -0.003 |
need | -0.003 |
pain | -0.002 |
Token | â |
Token ID | 22940 |
Feature activation | +9.01e-04 |
Pos logit contributions | |
dent | +0.003 |
regret | +0.002 |
impact | +0.002 |
need | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
beans | -0.004 |
aro | -0.003 |
chers | -0.003 |
suits | -0.003 |
tickets | -0.003 |
Token | € |
Token ID | 26391 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
aro | +0.001 |
beans | +0.001 |
chers | +0.001 |
suits | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
dent | -0.002 |
regret | -0.001 |
impact | -0.001 |
need | -0.001 |
ivering | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.027 |
chers | +0.025 |
suits | +0.025 |
tickets | +0.025 |
Neg logit contributions | |
dent | -0.032 |
regret | -0.027 |
impact | -0.027 |
need | -0.027 |
ivering | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
chers | +0.003 |
suits | +0.003 |
Off | +0.003 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
regret | -0.002 |
need | -0.002 |
ivering | -0.002 |
Token | So |
Token ID | 2396 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.002 |
ivering | +0.002 |
need | +0.002 |
impact | +0.002 |
Neg logit contributions | |
beans | -0.002 |
aro | -0.002 |
chers | -0.002 |
tickets | -0.002 |
suits | -0.002 |
Token | Beat |
Token ID | 12568 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.018 |
mons | +0.018 |
apr | +0.018 |
chers | +0.017 |
Neg logit contributions | |
dent | -0.016 |
need | -0.016 |
regret | -0.016 |
impact | -0.015 |
temptation | -0.014 |
Token | rice |
Token ID | 20970 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
apr | +0.112 |
beans | +0.107 |
kins | +0.106 |
herbs | +0.105 |
ishes | +0.105 |
Neg logit contributions | |
dent | -0.093 |
regret | -0.092 |
hy | -0.090 |
hurting | -0.084 |
lose | -0.084 |
Token | tried |
Token ID | 3088 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
aro | +0.010 |
beans | +0.009 |
chers | +0.009 |
suits | +0.009 |
mons | +0.009 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.008 |
need | -0.008 |
impact | -0.008 |
pain | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.003 |
tickets | +0.003 |
suits | +0.003 |
Neg logit contributions | |
dent | -0.006 |
impact | -0.005 |
regret | -0.005 |
ivering | -0.005 |
need | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.005 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.002 |
regret | -0.002 |
impact | -0.002 |
need | -0.001 |
ivering | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
aro | +0.011 |
beans | +0.011 |
resp | +0.011 |
chers | +0.011 |
cakes | +0.011 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.011 |
need | -0.010 |
impact | -0.010 |
pain | -0.009 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
chers | +0.005 |
Off | +0.005 |
cr | +0.005 |
Neg logit contributions | |
dent | -0.007 |
impact | -0.006 |
regret | -0.006 |
need | -0.006 |
pain | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -4.60e-03 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
Hil | +0.003 |
mons | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
dent | -0.001 |
need | -0.001 |
impact | -0.001 |
ivering | -0.001 |
anymore | -0.001 |
Token | Can |
Token ID | 1680 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
dent | +0.006 |
impact | +0.005 |
regret | +0.005 |
need | +0.005 |
ivering | +0.004 |
Neg logit contributions | |
beans | -0.009 |
aro | -0.009 |
chers | -0.009 |
suits | -0.008 |
tickets | -0.008 |
Token | we |
Token ID | 356 |
Feature activation | -6.20e-03 |
Pos logit contributions | |
dent | +0.006 |
regret | +0.005 |
impact | +0.005 |
need | +0.005 |
ivering | +0.005 |
Neg logit contributions | |
aro | -0.004 |
beans | -0.004 |
chers | -0.004 |
suits | -0.003 |
tickets | -0.003 |
Token | give |
Token ID | 1577 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
dent | +0.009 |
ivering | +0.007 |
impact | +0.007 |
regret | +0.007 |
pain | +0.007 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.010 |
chers | -0.010 |
tickets | -0.010 |
cakes | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
beans | +0.037 |
aro | +0.035 |
resp | +0.034 |
bags | +0.033 |
Fel | +0.033 |
Neg logit contributions | |
need | -0.019 |
dent | -0.018 |
regret | -0.017 |
impact | -0.017 |
end | -0.016 |
Token | some |
Token ID | 617 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
aro | +0.147 |
beans | +0.142 |
ela | +0.133 |
Fel | +0.130 |
mons | +0.127 |
Neg logit contributions | |
end | -0.078 |
need | -0.070 |
anymore | -0.065 |
dent | -0.064 |
my | -0.061 |
Token | t |
Token ID | 256 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
aro | +0.028 |
beans | +0.028 |
chers | +0.026 |
bags | +0.025 |
ela | +0.025 |
Neg logit contributions | |
dent | -0.029 |
need | -0.026 |
impact | -0.026 |
regret | -0.025 |
pain | -0.023 |
Token | eddy |
Token ID | 21874 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
beans | +0.045 |
aro | +0.044 |
chers | +0.041 |
suits | +0.040 |
poles | +0.040 |
Neg logit contributions | |
dent | -0.032 |
impact | -0.026 |
need | -0.025 |
ivering | -0.025 |
regret | -0.025 |
Token | bears |
Token ID | 13062 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
aro | +0.061 |
beans | +0.061 |
Fre | +0.060 |
Fre | +0.059 |
Off | +0.059 |
Neg logit contributions | |
dent | -0.046 |
need | -0.042 |
my | -0.039 |
end | -0.039 |
anymore | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
aro | +0.065 |
beans | +0.061 |
Hil | +0.059 |
Fel | +0.058 |
chers | +0.057 |
Neg logit contributions | |
dent | -0.035 |
need | -0.033 |
impact | -0.030 |
anymore | -0.029 |
regret | -0.028 |
Token | € |
Token ID | 26391 |
Feature activation | +8.15e-03 |
Pos logit contributions | |
dent | +0.026 |
regret | +0.022 |
impact | +0.022 |
need | +0.022 |
pain | +0.021 |
Neg logit contributions | |
aro | -0.020 |
beans | -0.019 |
chers | -0.018 |
cakes | -0.017 |
Off | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.013 |
chers | +0.012 |
tickets | +0.012 |
suits | +0.012 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.012 |
impact | -0.011 |
need | -0.011 |
ivering | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
dent | +0.019 |
impact | +0.016 |
regret | +0.016 |
ivering | +0.015 |
need | +0.015 |
Neg logit contributions | |
aro | -0.019 |
beans | -0.019 |
chers | -0.018 |
Off | -0.017 |
tickets | -0.017 |
Token | And |
Token ID | 1870 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
dent | +0.034 |
regret | +0.030 |
impact | +0.029 |
ivering | +0.029 |
need | +0.029 |
Neg logit contributions | |
beans | -0.034 |
aro | -0.033 |
chers | -0.031 |
suits | -0.031 |
tickets | -0.031 |
Token | so |
Token ID | 523 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
regret | +0.021 |
need | +0.020 |
dent | +0.019 |
impact | +0.019 |
temptation | +0.017 |
Neg logit contributions | |
beans | -0.028 |
suits | -0.028 |
bags | -0.027 |
apr | -0.027 |
mons | -0.026 |
Token | Beat |
Token ID | 12568 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
regret | +0.008 |
need | +0.008 |
dent | +0.008 |
impact | +0.008 |
ivering | +0.007 |
Neg logit contributions | |
beans | -0.008 |
suits | -0.007 |
apr | -0.007 |
resp | -0.007 |
mons | -0.007 |
Token | rice |
Token ID | 20970 |
Feature activation | -3.20e-04 |
Pos logit contributions | |
apr | +0.105 |
beans | +0.100 |
herbs | +0.098 |
kins | +0.096 |
strawberries | +0.095 |
Neg logit contributions | |
dent | -0.104 |
regret | -0.101 |
hy | -0.098 |
need | -0.092 |
hurting | -0.092 |
Token | had |
Token ID | 550 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
dent | +0.000 |
regret | +0.000 |
need | +0.000 |
impact | +0.000 |
ivering | +0.000 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
chers | -0.001 |
suits | -0.000 |
tickets | -0.000 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
aro | +0.026 |
beans | +0.025 |
chers | +0.023 |
suits | +0.022 |
cakes | +0.022 |
Neg logit contributions | |
dent | -0.031 |
regret | -0.028 |
impact | -0.028 |
need | -0.027 |
pain | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
dent | +0.014 |
impact | +0.012 |
regret | +0.012 |
ivering | +0.011 |
need | +0.011 |
Neg logit contributions | |
beans | -0.020 |
aro | -0.020 |
chers | -0.019 |
tickets | -0.019 |
cakes | -0.019 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
beans | +0.047 |
aro | +0.047 |
chers | +0.044 |
tickets | +0.042 |
suits | +0.042 |
Neg logit contributions | |
dent | -0.060 |
regret | -0.052 |
impact | -0.052 |
need | -0.050 |
ivering | -0.050 |
Token | One |
Token ID | 3198 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
dent | +0.009 |
regret | +0.007 |
impact | +0.007 |
ivering | +0.007 |
need | +0.007 |
Neg logit contributions | |
aro | -0.018 |
beans | -0.018 |
chers | -0.017 |
suits | -0.016 |
Off | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.015 |
bags | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.007 |
need | -0.006 |
regret | -0.006 |
impact | -0.006 |
pain | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
beans | +0.015 |
cakes | +0.014 |
chers | +0.014 |
bou | +0.014 |
bags | +0.013 |
Neg logit contributions | |
need | -0.004 |
dent | -0.004 |
pain | -0.003 |
end | -0.003 |
regret | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
beans | +0.022 |
rob | +0.021 |
ils | +0.021 |
resp | +0.021 |
chers | +0.020 |
Neg logit contributions | |
need | -0.011 |
sad | -0.011 |
dent | -0.010 |
gloomy | -0.010 |
He | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +7.19e-03 |
Pos logit contributions | |
need | +0.012 |
dent | +0.012 |
regret | +0.012 |
impact | +0.010 |
end | +0.010 |
Neg logit contributions | |
aro | -0.019 |
beans | -0.018 |
cakes | -0.017 |
resp | -0.017 |
chers | -0.017 |
Token | about |
Token ID | 546 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
beans | +0.014 |
aro | +0.014 |
chers | +0.013 |
suits | +0.013 |
cakes | +0.013 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.008 |
impact | -0.008 |
need | -0.008 |
ivering | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -4.47e-04 |
Pos logit contributions | |
aro | +0.147 |
beans | +0.139 |
chers | +0.136 |
cakes | +0.134 |
bags | +0.128 |
Neg logit contributions | |
need | -0.078 |
regret | -0.076 |
dent | -0.072 |
damage | -0.069 |
pain | -0.068 |
Token | have |
Token ID | 423 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.000 |
impact | +0.000 |
need | +0.000 |
ivering | +0.000 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
chers | -0.001 |
suits | -0.001 |
tickets | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
aro | +0.057 |
beans | +0.053 |
chers | +0.052 |
ista | +0.051 |
ela | +0.050 |
Neg logit contributions | |
need | -0.034 |
pain | -0.033 |
dent | -0.032 |
regret | -0.032 |
damage | -0.030 |
Token | meal |
Token ID | 9799 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
aro | +0.011 |
beans | +0.010 |
chers | +0.010 |
cakes | +0.009 |
es | +0.009 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.009 |
need | -0.009 |
impact | -0.009 |
pain | -0.008 |
Token | together |
Token ID | 1978 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
dent | +0.019 |
need | +0.017 |
regret | +0.017 |
impact | +0.016 |
ivering | +0.016 |
Neg logit contributions | |
aro | -0.029 |
beans | -0.027 |
chers | -0.026 |
resp | -0.026 |
fl | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aro | +0.016 |
beans | +0.016 |
chers | +0.015 |
cakes | +0.015 |
tickets | +0.015 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
impact | -0.011 |
need | -0.011 |
ivering | -0.010 |
Token | We |
Token ID | 775 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.026 |
chers | +0.025 |
kins | +0.025 |
bags | +0.024 |
Neg logit contributions | |
dent | -0.016 |
need | -0.013 |
impact | -0.013 |
regret | -0.012 |
ivering | -0.011 |
Token | can |
Token ID | 460 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
beans | +0.042 |
aro | +0.042 |
chers | +0.039 |
suits | +0.038 |
tickets | +0.038 |
Neg logit contributions | |
dent | -0.038 |
regret | -0.032 |
impact | -0.032 |
ivering | -0.031 |
need | -0.031 |
Token | use |
Token ID | 779 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
chers | +0.002 |
tickets | +0.002 |
bags | +0.002 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
regret | -0.002 |
ivering | -0.002 |
pain | -0.002 |
Token | our |
Token ID | 674 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
beans | +0.033 |
cakes | +0.031 |
ista | +0.030 |
resp | +0.030 |
aro | +0.030 |
Neg logit contributions | |
dent | -0.033 |
need | -0.029 |
regret | -0.026 |
impact | -0.026 |
damage | -0.026 |
Token | brain |
Token ID | 3632 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
dent | +0.022 |
need | +0.019 |
regret | +0.019 |
pain | +0.019 |
impact | +0.019 |
Neg logit contributions | |
aro | -0.014 |
beans | -0.013 |
cakes | -0.012 |
resp | -0.012 |
Off | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
aro | +0.125 |
beans | +0.114 |
resp | +0.112 |
Hil | +0.110 |
Fre | +0.110 |
Neg logit contributions | |
dent | -0.091 |
need | -0.084 |
anymore | -0.073 |
damage | -0.071 |
impact | -0.071 |
Token | think |
Token ID | 892 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
beans | +0.017 |
aro | +0.017 |
chers | +0.016 |
tickets | +0.016 |
poles | +0.015 |
Neg logit contributions | |
dent | -0.015 |
impact | -0.013 |
ivering | -0.013 |
regret | -0.013 |
need | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.018 |
suits | +0.017 |
chers | +0.017 |
fl | +0.017 |
Neg logit contributions | |
dent | -0.014 |
need | -0.012 |
impact | -0.011 |
regret | -0.011 |
ivering | -0.010 |
Token | something |
Token ID | 1223 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
beans | +0.026 |
aro | +0.025 |
suits | +0.024 |
cakes | +0.024 |
chers | +0.024 |
Neg logit contributions | |
dent | -0.030 |
impact | -0.026 |
regret | -0.026 |
need | -0.025 |
pain | -0.024 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aro | +0.063 |
beans | +0.063 |
mons | +0.061 |
suits | +0.060 |
apr | +0.060 |
Neg logit contributions | |
dent | -0.046 |
need | -0.042 |
regret | -0.041 |
impact | -0.039 |
anymore | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
dent | +0.004 |
regret | +0.003 |
need | +0.003 |
impact | +0.003 |
pain | +0.003 |
Neg logit contributions | |
beans | -0.009 |
aro | -0.009 |
chers | -0.009 |
suits | -0.009 |
tickets | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
impact | +0.001 |
need | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
aro | -0.004 |
beans | -0.004 |
chers | -0.003 |
tickets | -0.003 |
suits | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
aro | +0.033 |
beans | +0.030 |
fl | +0.029 |
Fre | +0.029 |
Fre | +0.028 |
Neg logit contributions | |
need | -0.015 |
dent | -0.015 |
regret | -0.014 |
my | -0.013 |
mean | -0.012 |
Token | teach |
Token ID | 4545 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
beans | +0.012 |
aro | +0.012 |
chers | +0.011 |
tickets | +0.011 |
bags | +0.011 |
Neg logit contributions | |
dent | -0.011 |
ivering | -0.010 |
impact | -0.010 |
regret | -0.009 |
pain | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
dent | +0.020 |
regret | +0.018 |
need | +0.018 |
impact | +0.018 |
pain | +0.017 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
suits | -0.017 |
chers | -0.017 |
bags | -0.016 |
Token | robot |
Token ID | 9379 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
Off | +0.007 |
chers | +0.007 |
aro | +0.007 |
fl | +0.007 |
tickets | +0.007 |
Neg logit contributions | |
dent | -0.013 |
ivering | -0.013 |
impact | -0.012 |
regret | -0.012 |
iver | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
aro | +0.138 |
rob | +0.138 |
beans | +0.135 |
suits | +0.132 |
chers | +0.127 |
Neg logit contributions | |
need | -0.078 |
dent | -0.060 |
end | -0.059 |
He | -0.059 |
regret | -0.058 |
Token | raise |
Token ID | 5298 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
aro | +0.011 |
beans | +0.011 |
chers | +0.010 |
tickets | +0.010 |
cakes | +0.010 |
Neg logit contributions | |
dent | -0.009 |
impact | -0.007 |
regret | -0.007 |
ivering | -0.007 |
need | -0.007 |
Token | its |
Token ID | 663 |
Feature activation | -7.94e-04 |
Pos logit contributions | |
dent | +0.009 |
regret | +0.008 |
need | +0.007 |
impact | +0.007 |
pain | +0.007 |
Neg logit contributions | |
beans | -0.007 |
aro | -0.007 |
chers | -0.007 |
suits | -0.007 |
resp | -0.007 |
Token | hands |
Token ID | 2832 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
impact | +0.001 |
ivering | +0.001 |
need | +0.001 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
chers | -0.001 |
tickets | -0.001 |
suits | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
aro | +0.036 |
beans | +0.034 |
chers | +0.033 |
resp | +0.032 |
tickets | +0.031 |
Neg logit contributions | |
dent | -0.027 |
need | -0.024 |
regret | -0.023 |
impact | -0.022 |
anymore | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
beans | +0.078 |
aro | +0.076 |
chers | +0.073 |
ils | +0.072 |
bags | +0.071 |
Neg logit contributions | |
dent | -0.039 |
regret | -0.031 |
need | -0.030 |
impact | -0.029 |
He | -0.028 |
Token | Let |
Token ID | 5756 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
aro | +0.040 |
beans | +0.040 |
chers | +0.038 |
tickets | +0.037 |
suits | +0.036 |
Neg logit contributions | |
dent | -0.038 |
impact | -0.032 |
regret | -0.032 |
need | -0.031 |
ivering | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
beans | +0.011 |
aro | +0.011 |
suits | +0.010 |
mons | +0.010 |
chers | +0.010 |
Neg logit contributions | |
dent | -0.006 |
regret | -0.005 |
need | -0.005 |
impact | -0.005 |
pain | -0.005 |
Token | give |
Token ID | 1577 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
beans | +0.016 |
aro | +0.016 |
chers | +0.016 |
tickets | +0.015 |
suits | +0.015 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.010 |
impact | -0.010 |
need | -0.009 |
ivering | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
beans | +0.010 |
resp | +0.009 |
suits | +0.009 |
aro | +0.009 |
bags | +0.009 |
Neg logit contributions | |
need | -0.004 |
dent | -0.004 |
regret | -0.004 |
temptation | -0.004 |
pain | -0.004 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
dent | +0.008 |
need | +0.007 |
regret | +0.007 |
impact | +0.007 |
pain | +0.007 |
Neg logit contributions | |
aro | -0.006 |
beans | -0.006 |
chers | -0.006 |
suits | -0.005 |
cakes | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
aro | +0.127 |
rob | +0.122 |
beans | +0.120 |
Fel | +0.118 |
chers | +0.115 |
Neg logit contributions | |
need | -0.088 |
my | -0.070 |
end | -0.069 |
dent | -0.068 |
impact | -0.068 |
Token | party |
Token ID | 2151 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
aro | +0.018 |
beans | +0.017 |
mons | +0.017 |
chers | +0.017 |
ils | +0.016 |
Neg logit contributions | |
dent | -0.012 |
need | -0.010 |
regret | -0.010 |
impact | -0.010 |
pain | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
aro | +0.048 |
Fel | +0.047 |
beans | +0.046 |
Fre | +0.044 |
Fre | +0.044 |
Neg logit contributions | |
dent | -0.022 |
need | -0.021 |
impact | -0.019 |
anymore | -0.017 |
my | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
beans | +0.029 |
chers | +0.027 |
aro | +0.027 |
ils | +0.027 |
bags | +0.027 |
Neg logit contributions | |
dent | -0.009 |
He | -0.008 |
need | -0.008 |
regret | -0.007 |
impact | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
beans | +0.021 |
aro | +0.020 |
chers | +0.019 |
bags | +0.019 |
suits | +0.019 |
Neg logit contributions | |
dent | -0.011 |
regret | -0.009 |
need | -0.008 |
impact | -0.008 |
ivering | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
dent | +0.003 |
impact | +0.003 |
regret | +0.002 |
ivering | +0.002 |
need | +0.002 |
Neg logit contributions | |
aro | -0.002 |
Off | -0.002 |
together | -0.002 |
beans | -0.002 |
es | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
dent | +0.016 |
impact | +0.015 |
regret | +0.014 |
need | +0.014 |
ivering | +0.013 |
Neg logit contributions | |
aro | -0.012 |
beans | -0.011 |
chers | -0.010 |
Off | -0.010 |
suits | -0.010 |
Token | We |
Token ID | 1135 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
beans | +0.051 |
aro | +0.050 |
chers | +0.047 |
suits | +0.047 |
tickets | +0.047 |
Neg logit contributions | |
dent | -0.034 |
regret | -0.027 |
need | -0.026 |
impact | -0.026 |
ivering | -0.026 |
Token | want |
Token ID | 765 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
aro | +0.024 |
beans | +0.024 |
chers | +0.024 |
suits | +0.023 |
bags | +0.023 |
Neg logit contributions | |
dent | -0.022 |
impact | -0.019 |
ivering | -0.019 |
regret | -0.018 |
temptation | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
beans | +0.035 |
aro | +0.034 |
chers | +0.032 |
suits | +0.031 |
ela | +0.030 |
Neg logit contributions | |
dent | -0.038 |
need | -0.033 |
regret | -0.033 |
impact | -0.032 |
damage | -0.031 |
Token | robot |
Token ID | 9379 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
dent | +0.012 |
regret | +0.010 |
impact | +0.010 |
need | +0.010 |
ivering | +0.010 |
Neg logit contributions | |
aro | -0.009 |
beans | -0.009 |
chers | -0.008 |
suits | -0.008 |
tickets | -0.008 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
aro | +0.130 |
beans | +0.128 |
Hil | +0.118 |
Fel | +0.117 |
Fre | +0.117 |
Neg logit contributions | |
dent | -0.091 |
need | -0.081 |
impact | -0.075 |
anymore | -0.071 |
regret | -0.068 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
tickets | +0.003 |
chers | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
dent | -0.004 |
impact | -0.004 |
regret | -0.004 |
ivering | -0.004 |
need | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.019 |
chers | +0.018 |
suits | +0.018 |
tickets | +0.018 |
Neg logit contributions | |
dent | -0.028 |
impact | -0.025 |
regret | -0.025 |
need | -0.024 |
ivering | -0.024 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
beans | +0.024 |
aro | +0.024 |
chers | +0.022 |
suits | +0.022 |
tickets | +0.021 |
Neg logit contributions | |
dent | -0.033 |
regret | -0.029 |
need | -0.028 |
impact | -0.028 |
pain | -0.027 |
Token | say |
Token ID | 910 |
Feature activation | -1.08e-03 |
Pos logit contributions | |
tickets | +0.026 |
chers | +0.026 |
beans | +0.026 |
suits | +0.025 |
aro | +0.025 |
Neg logit contributions | |
dent | -0.035 |
impact | -0.030 |
ivering | -0.029 |
regret | -0.026 |
earthquake | -0.025 |
Token | holiday |
Token ID | 9912 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
aro | +0.038 |
beans | +0.037 |
chers | +0.035 |
mons | +0.034 |
cakes | +0.033 |
Neg logit contributions | |
dent | -0.047 |
impact | -0.042 |
regret | -0.042 |
need | -0.041 |
ivering | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +8.46e-03 |
Pos logit contributions | |
aro | +0.017 |
beans | +0.016 |
resp | +0.015 |
Fre | +0.015 |
Fel | +0.015 |
Neg logit contributions | |
dent | -0.006 |
need | -0.005 |
impact | -0.005 |
regret | -0.005 |
anymore | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.014 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.010 |
impact | -0.010 |
need | -0.010 |
ivering | -0.010 |
Token | each |
Token ID | 1123 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
mons | +0.044 |
resp | +0.043 |
beans | +0.043 |
aro | +0.042 |
fl | +0.039 |
Neg logit contributions | |
need | -0.030 |
regret | -0.028 |
dent | -0.025 |
end | -0.024 |
my | -0.023 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
aro | +0.025 |
beans | +0.025 |
mons | +0.024 |
cakes | +0.024 |
resp | +0.024 |
Neg logit contributions | |
dent | -0.023 |
need | -0.022 |
regret | -0.021 |
impact | -0.020 |
pain | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
beans | +0.022 |
aro | +0.022 |
resp | +0.021 |
chers | +0.020 |
bags | +0.019 |
Neg logit contributions | |
dent | -0.018 |
regret | -0.017 |
need | -0.017 |
impact | -0.016 |
pain | -0.015 |
Token | big |
Token ID | 1263 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
rob | +0.144 |
aro | +0.142 |
beans | +0.127 |
mons | +0.126 |
resp | +0.126 |
Neg logit contributions | |
need | -0.066 |
end | -0.060 |
my | -0.051 |
empty | -0.049 |
have | -0.048 |
Token | hugs |
Token ID | 40657 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
aro | +0.086 |
beans | +0.083 |
mons | +0.079 |
chers | +0.078 |
resp | +0.075 |
Neg logit contributions | |
dent | -0.079 |
need | -0.077 |
impact | -0.073 |
regret | -0.070 |
pain | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
dent | +0.006 |
need | +0.006 |
regret | +0.005 |
impact | +0.005 |
pain | +0.005 |
Neg logit contributions | |
aro | -0.013 |
beans | -0.012 |
chers | -0.012 |
mons | -0.011 |
resp | -0.011 |
Token | thanked |
Token ID | 26280 |
Feature activation | +9.52e-05 |
Pos logit contributions | |
aro | +0.013 |
resp | +0.012 |
beans | +0.012 |
chers | +0.012 |
mons | +0.012 |
Neg logit contributions | |
need | -0.011 |
regret | -0.010 |
pain | -0.010 |
dent | -0.009 |
have | -0.008 |
Token | them |
Token ID | 606 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
beans | +0.000 |
aro | +0.000 |
chers | +0.000 |
suits | +0.000 |
mons | +0.000 |
Neg logit contributions | |
dent | -0.000 |
regret | -0.000 |
impact | -0.000 |
need | -0.000 |
ivering | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
aro | +0.004 |
beans | +0.004 |
chers | +0.004 |
tickets | +0.004 |
suits | +0.004 |
Neg logit contributions | |
dent | -0.006 |
impact | -0.005 |
regret | -0.005 |
ivering | -0.005 |
need | -0.005 |
Token | end |
Token ID | 886 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ivering | +0.011 |
dent | +0.010 |
iver | +0.008 |
ended | +0.008 |
bruised | +0.008 |
Neg logit contributions | |
tickets | -0.011 |
vows | -0.010 |
dads | -0.010 |
invitations | -0.010 |
poles | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -9.31e-03 |
Pos logit contributions | |
dent | +0.014 |
regret | +0.012 |
impact | +0.012 |
need | +0.011 |
ivering | +0.011 |
Neg logit contributions | |
beans | -0.022 |
aro | -0.022 |
chers | -0.021 |
suits | -0.020 |
tickets | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
dent | +0.018 |
regret | +0.016 |
impact | +0.016 |
need | +0.015 |
ivering | +0.015 |
Neg logit contributions | |
beans | -0.012 |
aro | -0.012 |
chers | -0.011 |
suits | -0.011 |
tickets | -0.011 |
Token | last |
Token ID | 938 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
dent | +0.015 |
ivering | +0.014 |
iver | +0.012 |
bruised | +0.011 |
naked | +0.011 |
Neg logit contributions | |
tickets | -0.016 |
vows | -0.015 |
poles | -0.015 |
dolphins | -0.014 |
beans | -0.014 |
Token | paragraph |
Token ID | 7322 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
dent | +0.023 |
ivering | +0.020 |
regret | +0.018 |
impact | +0.018 |
iver | +0.017 |
Neg logit contributions | |
aro | -0.026 |
beans | -0.026 |
tickets | -0.025 |
poles | -0.024 |
suits | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
dent | +0.112 |
regret | +0.093 |
impact | +0.093 |
ivering | +0.089 |
pain | +0.083 |
Neg logit contributions | |
beans | -0.095 |
chers | -0.095 |
aro | -0.094 |
tickets | -0.093 |
es | -0.093 |
Token | The |
Token ID | 383 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
dent | +0.023 |
impact | +0.018 |
ivering | +0.018 |
regret | +0.018 |
need | +0.016 |
Neg logit contributions | |
aro | -0.037 |
beans | -0.036 |
chers | -0.034 |
Off | -0.034 |
Fre | -0.034 |
Token | story |
Token ID | 1621 |
Feature activation | +6.60e-05 |
Pos logit contributions | |
dent | +0.007 |
ivering | +0.006 |
impact | +0.006 |
regret | +0.006 |
need | +0.006 |
Neg logit contributions | |
beans | -0.007 |
tickets | -0.006 |
aro | -0.006 |
chers | -0.006 |
poles | -0.006 |
Token | also |
Token ID | 635 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
beans | +0.000 |
aro | +0.000 |
chers | +0.000 |
suits | +0.000 |
tickets | +0.000 |
Neg logit contributions | |
dent | -0.000 |
regret | -0.000 |
impact | -0.000 |
need | -0.000 |
ivering | -0.000 |
Token | creates |
Token ID | 8075 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
dent | +0.016 |
need | +0.015 |
regret | +0.015 |
impact | +0.014 |
pain | +0.013 |
Neg logit contributions | |
beans | -0.019 |
aro | -0.019 |
suits | -0.018 |
mons | -0.018 |
apr | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
dent | +0.011 |
regret | +0.009 |
need | +0.009 |
pain | +0.009 |
ivering | +0.009 |
Neg logit contributions | |
beans | -0.014 |
chers | -0.014 |
aro | -0.014 |
tickets | -0.014 |
suits | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
aro | +0.011 |
beans | +0.011 |
chers | +0.011 |
suits | +0.010 |
tickets | +0.010 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.009 |
need | -0.009 |
impact | -0.008 |
pain | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.60e-04 |
Pos logit contributions | |
dent | +0.040 |
impact | +0.035 |
regret | +0.034 |
need | +0.033 |
ivering | +0.032 |
Neg logit contributions | |
beans | -0.041 |
aro | -0.041 |
chers | -0.039 |
suits | -0.038 |
tickets | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
dent | +0.000 |
regret | +0.000 |
need | +0.000 |
pain | +0.000 |
impact | +0.000 |
Neg logit contributions | |
beans | -0.000 |
aro | -0.000 |
chers | -0.000 |
suits | -0.000 |
resp | -0.000 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
dent | +0.032 |
impact | +0.030 |
regret | +0.029 |
need | +0.028 |
ivering | +0.028 |
Neg logit contributions | |
beans | -0.026 |
aro | -0.025 |
da | -0.025 |
suits | -0.024 |
chers | -0.024 |
Token | man |
Token ID | 805 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
dent | +0.029 |
impact | +0.028 |
regret | +0.028 |
need | +0.027 |
temptation | +0.026 |
Neg logit contributions | |
beans | -0.015 |
aro | -0.015 |
fl | -0.014 |
chers | -0.013 |
bags | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
dent | +0.128 |
impact | +0.120 |
temptation | +0.113 |
meantime | +0.107 |
regret | +0.107 |
Neg logit contributions | |
together | -0.061 |
chers | -0.053 |
aro | -0.051 |
da | -0.051 |
es | -0.051 |
Token | She |
Token ID | 1375 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
dent | +0.006 |
impact | +0.005 |
regret | +0.005 |
ivering | +0.005 |
need | +0.005 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.011 |
cakes | -0.010 |
suits | -0.010 |
chers | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
dent | +0.018 |
regret | +0.015 |
need | +0.015 |
ivering | +0.014 |
impact | +0.013 |
Neg logit contributions | |
beans | -0.022 |
aro | -0.021 |
chers | -0.020 |
tickets | -0.020 |
cakes | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
dent | +0.003 |
regret | +0.002 |
need | +0.002 |
sad | +0.002 |
sincere | +0.002 |
Neg logit contributions | |
beans | -0.006 |
suits | -0.006 |
aro | -0.006 |
Off | -0.006 |
chers | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.005 |
regret | -0.004 |
need | -0.004 |
impact | -0.004 |
ivering | -0.004 |
Token | sick |
Token ID | 6639 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
dent | +0.053 |
impact | +0.047 |
ivering | +0.046 |
spine | +0.043 |
earthquake | +0.041 |
Neg logit contributions | |
beans | -0.044 |
dolphins | -0.043 |
da | -0.043 |
together | -0.042 |
cr | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
dent | +0.069 |
impact | +0.062 |
regret | +0.060 |
sincere | +0.058 |
ivering | +0.058 |
Neg logit contributions | |
beans | -0.047 |
together | -0.046 |
es | -0.046 |
cr | -0.044 |
aro | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
dent | +0.035 |
ivering | +0.035 |
impact | +0.034 |
regret | +0.030 |
hurting | +0.029 |
Neg logit contributions | |
beans | -0.038 |
Off | -0.038 |
mons | -0.038 |
aro | -0.038 |
Finn | -0.037 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
dent | +0.022 |
impact | +0.021 |
ivering | +0.019 |
temptation | +0.019 |
regret | +0.018 |
Neg logit contributions | |
beans | -0.017 |
aro | -0.017 |
chers | -0.015 |
da | -0.015 |
suits | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
dent | +0.056 |
impact | +0.050 |
ivering | +0.048 |
spine | +0.045 |
earthquake | +0.043 |
Neg logit contributions | |
dolphins | -0.048 |
beans | -0.047 |
herbs | -0.046 |
da | -0.046 |
aro | -0.046 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
dent | +0.029 |
impact | +0.026 |
ivering | +0.025 |
regret | +0.024 |
need | +0.022 |
Neg logit contributions | |
beans | -0.032 |
aro | -0.031 |
da | -0.030 |
tickets | -0.030 |
cr | -0.030 |
Token | my |
Token ID | 1820 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
impact | +0.086 |
dent | +0.081 |
regret | +0.076 |
need | +0.075 |
hate | +0.071 |
Neg logit contributions | |
fl | -0.097 |
cr | -0.095 |
es | -0.093 |
cakes | -0.091 |
kins | -0.088 |
Token | ac |
Token ID | 936 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
impact | +0.076 |
dent | +0.075 |
sincere | +0.067 |
meantime | +0.066 |
unts | +0.064 |
Neg logit contributions | |
es | -0.064 |
beans | -0.062 |
fl | -0.061 |
kins | -0.061 |
cr | -0.060 |
Token | he |
Token ID | 258 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
dent | +0.034 |
impact | +0.031 |
regret | +0.030 |
need | +0.029 |
sincere | +0.027 |
Neg logit contributions | |
beans | -0.040 |
aro | -0.039 |
chers | -0.037 |
mons | -0.036 |
cakes | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
dent | +0.020 |
impact | +0.018 |
regret | +0.017 |
need | +0.016 |
ivering | +0.016 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.020 |
kins | -0.019 |
es | -0.018 |
chers | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ivering | +0.031 |
dent | +0.031 |
impact | +0.030 |
regret | +0.026 |
hurting | +0.025 |
Neg logit contributions | |
Off | -0.035 |
mons | -0.035 |
beans | -0.035 |
Fre | -0.035 |
Finn | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -3.13e-04 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.002 |
need | +0.002 |
impact | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.002 |
cakes | -0.002 |
tickets | -0.002 |
Token | Spot |
Token ID | 15899 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.000 |
need | +0.000 |
pain | +0.000 |
impact | +0.000 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
chers | -0.000 |
suits | -0.000 |
cakes | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | +8.64e-05 |
Pos logit contributions | |
dent | +0.006 |
regret | +0.005 |
need | +0.005 |
ivering | +0.005 |
pain | +0.005 |
Neg logit contributions | |
aro | -0.010 |
beans | -0.009 |
cakes | -0.009 |
chers | -0.009 |
tickets | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
beans | +0.000 |
aro | +0.000 |
chers | +0.000 |
suits | +0.000 |
kins | +0.000 |
Neg logit contributions | |
dent | -0.000 |
regret | -0.000 |
pain | -0.000 |
need | -0.000 |
impact | -0.000 |
Token | fire |
Token ID | 2046 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
dent | +0.013 |
impact | +0.011 |
regret | +0.011 |
need | +0.011 |
ivering | +0.011 |
Neg logit contributions | |
beans | -0.013 |
aro | -0.012 |
chers | -0.012 |
suits | -0.012 |
tickets | -0.011 |
Token | man |
Token ID | 805 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
aro | +0.008 |
beans | +0.007 |
fl | +0.007 |
chers | +0.007 |
bags | +0.007 |
Neg logit contributions | |
dent | -0.011 |
impact | -0.011 |
regret | -0.010 |
need | -0.010 |
temptation | -0.010 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
dent | +0.117 |
impact | +0.106 |
temptation | +0.100 |
regret | +0.096 |
pain | +0.096 |
Neg logit contributions | |
together | -0.065 |
chers | -0.063 |
aro | -0.062 |
aboard | -0.058 |
es | -0.058 |
Token | down |
Token ID | 866 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
dent | +0.003 |
need | +0.003 |
regret | +0.003 |
impact | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.003 |
cakes | -0.003 |
mons | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
beans | +0.011 |
aro | +0.011 |
chers | +0.010 |
suits | +0.010 |
mons | +0.009 |
Neg logit contributions | |
dent | -0.013 |
need | -0.011 |
regret | -0.011 |
impact | -0.011 |
pain | -0.011 |
Token | street |
Token ID | 4675 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
aro | +0.025 |
beans | +0.024 |
suits | +0.023 |
tickets | +0.023 |
poles | +0.023 |
Neg logit contributions | |
dent | -0.017 |
impact | -0.014 |
regret | -0.014 |
ivering | -0.013 |
need | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
dent | +0.022 |
impact | +0.021 |
regret | +0.019 |
ivering | +0.018 |
pain | +0.018 |
Neg logit contributions | |
together | -0.016 |
aro | -0.015 |
tickets | -0.014 |
suits | -0.014 |
poles | -0.014 |
Token | heavy |
Token ID | 4334 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
dent | +0.033 |
impact | +0.030 |
regret | +0.029 |
ivering | +0.028 |
need | +0.027 |
Neg logit contributions | |
beans | -0.039 |
aro | -0.039 |
chers | -0.037 |
tickets | -0.036 |
suits | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
dent | +0.070 |
impact | +0.068 |
regret | +0.066 |
sincere | +0.065 |
ivering | +0.064 |
Neg logit contributions | |
together | -0.039 |
beans | -0.035 |
poles | -0.035 |
es | -0.034 |
tickets | -0.033 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
dent | +0.034 |
impact | +0.030 |
regret | +0.030 |
ivering | +0.029 |
need | +0.026 |
Neg logit contributions | |
aro | -0.051 |
beans | -0.051 |
mons | -0.048 |
cakes | -0.048 |
Off | -0.048 |
Token | loses |
Token ID | 14754 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
dent | +0.041 |
impact | +0.040 |
ivering | +0.037 |
regret | +0.037 |
temptation | +0.035 |
Neg logit contributions | |
beans | -0.031 |
aro | -0.029 |
chers | -0.029 |
suits | -0.028 |
tickets | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
dent | +0.032 |
impact | +0.030 |
regret | +0.029 |
ivering | +0.028 |
need | +0.028 |
Neg logit contributions | |
aro | -0.023 |
beans | -0.022 |
tickets | -0.020 |
chers | -0.020 |
poles | -0.020 |
Token | balance |
Token ID | 5236 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
ivering | +0.058 |
dent | +0.056 |
impact | +0.054 |
regret | +0.053 |
sincere | +0.051 |
Neg logit contributions | |
beans | -0.043 |
tickets | -0.042 |
poles | -0.042 |
da | -0.041 |
sandwiches | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
impact | +0.107 |
dent | +0.104 |
regret | +0.099 |
sincere | +0.094 |
ivering | +0.092 |
Neg logit contributions | |
es | -0.065 |
aro | -0.063 |
kins | -0.063 |
beans | -0.063 |
together | -0.061 |
Token | He |
Token ID | 679 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
dent | +0.017 |
impact | +0.017 |
ivering | +0.016 |
regret | +0.015 |
need | +0.013 |
Neg logit contributions | |
aro | -0.028 |
beans | -0.028 |
mons | -0.027 |
cakes | -0.026 |
Finn | -0.026 |
Token | falls |
Token ID | 8953 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
impact | +0.044 |
ivering | +0.043 |
dent | +0.041 |
iver | +0.038 |
earthquake | +0.038 |
Neg logit contributions | |
aro | -0.032 |
beans | -0.032 |
ls | -0.031 |
poles | -0.031 |
chers | -0.030 |
Token | off |
Token ID | 572 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
impact | +0.033 |
dent | +0.031 |
regret | +0.031 |
ivering | +0.030 |
sincere | +0.030 |
Neg logit contributions | |
aro | -0.013 |
together | -0.012 |
fl | -0.012 |
cr | -0.011 |
bags | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
dent | +0.014 |
impact | +0.012 |
regret | +0.012 |
ivering | +0.012 |
need | +0.012 |
Neg logit contributions | |
aro | -0.009 |
beans | -0.008 |
chers | -0.008 |
tickets | -0.007 |
suits | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
dent | +0.031 |
regret | +0.027 |
impact | +0.026 |
need | +0.026 |
ivering | +0.026 |
Neg logit contributions | |
beans | -0.035 |
aro | -0.035 |
chers | -0.033 |
tickets | -0.032 |
suits | -0.032 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
dent | +0.017 |
regret | +0.015 |
need | +0.015 |
impact | +0.015 |
ivering | +0.014 |
Neg logit contributions | |
beans | -0.019 |
aro | -0.019 |
chers | -0.019 |
tickets | -0.018 |
resp | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
dent | +0.006 |
regret | +0.005 |
need | +0.005 |
impact | +0.005 |
pain | +0.005 |
Neg logit contributions | |
beans | -0.005 |
aro | -0.005 |
chers | -0.004 |
suits | -0.004 |
tickets | -0.004 |
Token | bright |
Token ID | 6016 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
dent | +0.020 |
impact | +0.019 |
regret | +0.018 |
need | +0.018 |
ivering | +0.018 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
da | -0.017 |
suits | -0.017 |
chers | -0.017 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.012 |
impact | +0.012 |
need | +0.012 |
temptation | +0.011 |
Neg logit contributions | |
da | -0.011 |
bou | -0.010 |
beans | -0.010 |
aro | -0.010 |
fl | -0.010 |
Token | man |
Token ID | 805 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
dent | +0.028 |
regret | +0.027 |
impact | +0.026 |
need | +0.026 |
temptation | +0.024 |
Neg logit contributions | |
beans | -0.019 |
aro | -0.019 |
fl | -0.018 |
cakes | -0.017 |
bags | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
dent | +0.116 |
impact | +0.108 |
temptation | +0.102 |
meantime | +0.098 |
regret | +0.097 |
Neg logit contributions | |
together | -0.065 |
chers | -0.060 |
aro | -0.058 |
fl | -0.056 |
aboard | -0.056 |
Token | |
Token ID | 220 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
dent | +0.010 |
impact | +0.008 |
regret | +0.008 |
ivering | +0.008 |
need | +0.007 |
Neg logit contributions | |
beans | -0.014 |
aro | -0.013 |
cakes | -0.013 |
suits | -0.013 |
chers | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
dent | +0.012 |
impact | +0.011 |
regret | +0.011 |
ivering | +0.010 |
pain | +0.010 |
Neg logit contributions | |
aro | -0.010 |
beans | -0.009 |
chers | -0.009 |
Off | -0.009 |
suits | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
dent | +0.002 |
impact | +0.002 |
regret | +0.002 |
ivering | +0.002 |
need | +0.002 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.002 |
suits | -0.002 |
chers | -0.002 |
Off | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
dent | +0.022 |
impact | +0.020 |
regret | +0.019 |
need | +0.019 |
ivering | +0.018 |
Neg logit contributions | |
beans | -0.014 |
aro | -0.013 |
chers | -0.013 |
suits | -0.012 |
Off | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
dent | +0.004 |
impact | +0.003 |
ivering | +0.003 |
regret | +0.003 |
need | +0.003 |
Neg logit contributions | |
beans | -0.004 |
aro | -0.004 |
da | -0.003 |
chers | -0.003 |
dolphins | -0.003 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
dent | +0.039 |
ivering | +0.035 |
impact | +0.034 |
iver | +0.033 |
hurting | +0.031 |
Neg logit contributions | |
da | -0.028 |
beans | -0.027 |
bou | -0.025 |
fish | -0.023 |
tad | -0.022 |
Token | feeling |
Token ID | 4203 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
dent | +0.002 |
ivering | +0.002 |
regret | +0.002 |
impact | +0.002 |
need | +0.002 |
Neg logit contributions | |
beans | -0.002 |
aro | -0.002 |
da | -0.002 |
tickets | -0.002 |
fl | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
dent | +0.012 |
impact | +0.010 |
regret | +0.010 |
ivering | +0.009 |
need | +0.009 |
Neg logit contributions | |
aro | -0.014 |
beans | -0.014 |
chers | -0.013 |
suits | -0.013 |
tickets | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
dent | +0.026 |
ivering | +0.024 |
impact | +0.024 |
regret | +0.022 |
iver | +0.021 |
Neg logit contributions | |
aro | -0.014 |
beans | -0.013 |
da | -0.012 |
tickets | -0.012 |
poles | -0.012 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
dent | +0.034 |
impact | +0.028 |
ivering | +0.028 |
regret | +0.027 |
need | +0.025 |
Neg logit contributions | |
beans | -0.036 |
da | -0.034 |
aro | -0.034 |
tickets | -0.033 |
fl | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
dent | +0.076 |
impact | +0.066 |
regret | +0.061 |
need | +0.058 |
damage | +0.054 |
Neg logit contributions | |
fl | -0.109 |
es | -0.105 |
cr | -0.105 |
kins | -0.103 |
cakes | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
dent | +0.062 |
impact | +0.053 |
regret | +0.050 |
need | +0.048 |
sincere | +0.048 |
Neg logit contributions | |
beans | -0.054 |
fl | -0.051 |
aro | -0.049 |
cr | -0.048 |
da | -0.048 |
Token | She |
Token ID | 1375 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
dent | +0.005 |
impact | +0.004 |
regret | +0.004 |
ivering | +0.004 |
need | +0.004 |
Neg logit contributions | |
aro | -0.007 |
beans | -0.007 |
Off | -0.007 |
cakes | -0.007 |
Hil | -0.007 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
dent | +0.014 |
regret | +0.012 |
impact | +0.012 |
need | +0.012 |
ivering | +0.011 |
Neg logit contributions | |
aro | -0.012 |
beans | -0.012 |
chers | -0.011 |
suits | -0.011 |
tickets | -0.011 |
Token | very |
Token ID | 845 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
dent | +0.019 |
impact | +0.016 |
ivering | +0.015 |
spine | +0.014 |
earthquake | +0.013 |
Neg logit contributions | |
aro | -0.014 |
beans | -0.014 |
da | -0.014 |
Fre | -0.013 |
herbs | -0.013 |
Token | feels |
Token ID | 5300 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
dent | +0.016 |
impact | +0.014 |
ivering | +0.014 |
regret | +0.014 |
need | +0.013 |
Neg logit contributions | |
beans | -0.015 |
aro | -0.015 |
chers | -0.014 |
tickets | -0.014 |
suits | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
dent | +0.036 |
impact | +0.032 |
ivering | +0.031 |
spine | +0.027 |
iver | +0.027 |
Neg logit contributions | |
aro | -0.047 |
beans | -0.047 |
dolphins | -0.046 |
da | -0.045 |
ge | -0.045 |
Token | burn |
Token ID | 4245 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
impact | +0.066 |
dent | +0.066 |
meantime | +0.060 |
ivering | +0.059 |
my | +0.059 |
Neg logit contributions | |
beans | -0.055 |
da | -0.053 |
cor | -0.052 |
fish | -0.050 |
kernels | -0.048 |
Token | in |
Token ID | 287 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
dent | +0.080 |
impact | +0.079 |
regret | +0.074 |
need | +0.068 |
sincere | +0.067 |
Neg logit contributions | |
beans | -0.051 |
aro | -0.050 |
kins | -0.050 |
es | -0.049 |
cr | -0.048 |
Token | his |
Token ID | 465 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
dent | +0.060 |
impact | +0.060 |
ivering | +0.059 |
regret | +0.055 |
iver | +0.054 |
Neg logit contributions | |
aro | -0.024 |
poles | -0.023 |
tickets | -0.021 |
beans | -0.021 |
apr | -0.021 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
dent | +0.042 |
regret | +0.037 |
impact | +0.037 |
ivering | +0.036 |
need | +0.034 |
Neg logit contributions | |
beans | -0.053 |
aro | -0.051 |
tickets | -0.050 |
suits | -0.049 |
poles | -0.049 |
Token | my |
Token ID | 1820 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
impact | +0.082 |
dent | +0.079 |
regret | +0.079 |
need | +0.070 |
hate | +0.067 |
Neg logit contributions | |
es | -0.095 |
fl | -0.094 |
kins | -0.094 |
cr | -0.094 |
cakes | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
dent | +0.077 |
impact | +0.075 |
regret | +0.071 |
sincere | +0.068 |
meantime | +0.063 |
Neg logit contributions | |
beans | -0.060 |
es | -0.060 |
cr | -0.058 |
kins | -0.056 |
together | -0.055 |
Token | He |
Token ID | 679 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
dent | +0.018 |
impact | +0.017 |
ivering | +0.016 |
regret | +0.014 |
need | +0.013 |
Neg logit contributions | |
aro | -0.031 |
beans | -0.030 |
mons | -0.030 |
cakes | -0.029 |
Fre | -0.029 |
Token | is |
Token ID | 318 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
dent | +0.023 |
impact | +0.021 |
ivering | +0.020 |
regret | +0.020 |
temptation | +0.019 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.020 |
tickets | -0.020 |
suits | -0.019 |
Token | angry |
Token ID | 7954 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
dent | +0.054 |
impact | +0.053 |
ivering | +0.043 |
temptation | +0.042 |
regret | +0.041 |
Neg logit contributions | |
aro | -0.061 |
beans | -0.060 |
chers | -0.059 |
dolphins | -0.057 |
together | -0.057 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
beans | +0.012 |
aro | +0.012 |
chers | +0.011 |
suits | +0.011 |
mons | +0.011 |
Neg logit contributions | |
dent | -0.017 |
regret | -0.015 |
impact | -0.015 |
ivering | -0.015 |
need | -0.014 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.010 |
suits | +0.010 |
bags | +0.009 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.007 |
need | -0.007 |
pain | -0.007 |
impact | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
aro | +0.007 |
beans | +0.006 |
chers | +0.006 |
suits | +0.006 |
cakes | +0.006 |
Neg logit contributions | |
dent | -0.008 |
regret | -0.007 |
need | -0.007 |
impact | -0.007 |
ivering | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
beans | +0.009 |
aro | +0.009 |
chers | +0.009 |
suits | +0.008 |
tickets | +0.008 |
Neg logit contributions | |
dent | -0.007 |
impact | -0.006 |
regret | -0.006 |
ivering | -0.005 |
need | -0.005 |
Token | holding |
Token ID | 4769 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
dent | +0.019 |
impact | +0.016 |
regret | +0.016 |
need | +0.016 |
ivering | +0.015 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.019 |
suits | -0.019 |
tickets | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
dent | +0.011 |
regret | +0.010 |
need | +0.010 |
impact | +0.009 |
pain | +0.009 |
Neg logit contributions | |
aro | -0.010 |
beans | -0.010 |
chers | -0.009 |
cakes | -0.009 |
resp | -0.009 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ivering | +0.120 |
iver | +0.112 |
impact | +0.104 |
ivery | +0.101 |
dent | +0.099 |
Neg logit contributions | |
da | -0.057 |
shells | -0.055 |
beans | -0.054 |
tickets | -0.054 |
mons | -0.053 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
dent | +0.043 |
ivering | +0.043 |
regret | +0.041 |
impact | +0.040 |
iver | +0.040 |
Neg logit contributions | |
beans | -0.027 |
da | -0.025 |
aro | -0.024 |
mons | -0.023 |
tickets | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
beans | +0.034 |
aro | +0.033 |
tickets | +0.031 |
suits | +0.031 |
cr | +0.031 |
Neg logit contributions | |
dent | -0.034 |
impact | -0.030 |
regret | -0.029 |
ivering | -0.029 |
need | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.019 |
chers | +0.018 |
tickets | +0.017 |
suits | +0.017 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.009 |
need | -0.009 |
impact | -0.009 |
pain | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
aro | +0.009 |
beans | +0.009 |
chers | +0.008 |
suits | +0.008 |
tickets | +0.008 |
Neg logit contributions | |
dent | -0.007 |
impact | -0.006 |
regret | -0.006 |
need | -0.006 |
ivering | -0.005 |
Token | ? |
Token ID | 30 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
dent | +0.020 |
impact | +0.017 |
regret | +0.017 |
ivering | +0.016 |
need | +0.016 |
Neg logit contributions | |
beans | -0.023 |
aro | -0.023 |
chers | -0.022 |
suits | -0.022 |
tickets | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
aro | +0.021 |
beans | +0.021 |
chers | +0.020 |
tickets | +0.020 |
suits | +0.019 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.007 |
impact | -0.006 |
need | -0.006 |
ivering | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.003 |
chers | +0.003 |
suits | +0.002 |
tickets | +0.002 |
Neg logit contributions | |
dent | -0.003 |
regret | -0.002 |
need | -0.002 |
impact | -0.002 |
ivering | -0.002 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
chers | +0.005 |
suits | +0.005 |
cakes | +0.005 |
Neg logit contributions | |
dent | -0.006 |
regret | -0.006 |
need | -0.006 |
impact | -0.006 |
pain | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
dent | +0.030 |
regret | +0.027 |
need | +0.026 |
impact | +0.026 |
pain | +0.025 |
Neg logit contributions | |
beans | -0.026 |
aro | -0.026 |
suits | -0.025 |
chers | -0.025 |
resp | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
dent | +0.031 |
regret | +0.028 |
need | +0.027 |
impact | +0.027 |
pain | +0.025 |
Neg logit contributions | |
aro | -0.025 |
beans | -0.024 |
chers | -0.023 |
suits | -0.022 |
cakes | -0.022 |
Token | do |
Token ID | 466 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
dent | +0.093 |
impact | +0.081 |
temptation | +0.076 |
pain | +0.076 |
earthquake | +0.070 |
Neg logit contributions | |
together | -0.082 |
es | -0.079 |
chers | -0.078 |
mary | -0.077 |
fl | -0.077 |
Token | it |
Token ID | 340 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
dent | +0.027 |
regret | +0.023 |
impact | +0.023 |
need | +0.023 |
ivering | +0.022 |
Neg logit contributions | |
aro | -0.028 |
beans | -0.028 |
chers | -0.026 |
suits | -0.026 |
tickets | -0.025 |
Token | before |
Token ID | 878 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
dent | +0.029 |
impact | +0.024 |
regret | +0.024 |
need | +0.023 |
ivering | +0.023 |
Neg logit contributions | |
beans | -0.028 |
aro | -0.027 |
chers | -0.026 |
cakes | -0.025 |
suits | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
dent | +0.021 |
impact | +0.018 |
regret | +0.018 |
ivering | +0.017 |
need | +0.017 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.019 |
tickets | -0.019 |
cakes | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
aro | +0.029 |
beans | +0.028 |
chers | +0.028 |
tickets | +0.027 |
bags | +0.026 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
need | -0.011 |
impact | -0.010 |
temptation | -0.009 |
Token | when |
Token ID | 618 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
dent | +0.015 |
impact | +0.013 |
regret | +0.013 |
ivering | +0.012 |
need | +0.012 |
Neg logit contributions | |
beans | -0.010 |
aro | -0.010 |
chers | -0.009 |
suits | -0.009 |
tickets | -0.009 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.014 |
tickets | +0.014 |
suits | +0.014 |
Neg logit contributions | |
dent | -0.016 |
impact | -0.014 |
ivering | -0.014 |
regret | -0.014 |
need | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -9.76e-03 |
Pos logit contributions | |
dent | +0.023 |
impact | +0.020 |
regret | +0.019 |
ivering | +0.019 |
need | +0.019 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.020 |
tickets | -0.019 |
suits | -0.019 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
dent | +0.016 |
impact | +0.014 |
regret | +0.013 |
temptation | +0.013 |
ivering | +0.013 |
Neg logit contributions | |
beans | -0.016 |
aro | -0.015 |
chers | -0.015 |
suits | -0.014 |
bags | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
dent | +0.020 |
impact | +0.018 |
ivering | +0.018 |
spine | +0.016 |
iver | +0.015 |
Neg logit contributions | |
beans | -0.017 |
dolphins | -0.017 |
aro | -0.017 |
herbs | -0.016 |
props | -0.016 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
dent | +0.016 |
impact | +0.015 |
regret | +0.014 |
ivering | +0.014 |
need | +0.013 |
Neg logit contributions | |
beans | -0.014 |
aro | -0.013 |
suits | -0.013 |
tickets | -0.013 |
chers | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
impact | +0.081 |
dent | +0.075 |
regret | +0.072 |
need | +0.070 |
sincere | +0.064 |
Neg logit contributions | |
fl | -0.099 |
cr | -0.097 |
cakes | -0.095 |
es | -0.089 |
cream | -0.087 |
Token | rum |
Token ID | 7440 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
impact | +0.078 |
dent | +0.074 |
sincere | +0.069 |
meantime | +0.068 |
unts | +0.066 |
Neg logit contributions | |
fl | -0.060 |
cr | -0.056 |
beans | -0.055 |
es | -0.053 |
led | -0.052 |
Token | ble |
Token ID | 903 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
dent | +0.075 |
impact | +0.072 |
regret | +0.068 |
need | +0.065 |
hy | +0.064 |
Neg logit contributions | |
kins | -0.035 |
aro | -0.031 |
beans | -0.029 |
mons | -0.028 |
together | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +5.26e-04 |
Pos logit contributions | |
dent | +0.067 |
impact | +0.064 |
sincere | +0.057 |
regret | +0.057 |
Promise | +0.056 |
Neg logit contributions | |
together | -0.034 |
cr | -0.034 |
beans | -0.031 |
es | -0.029 |
bags | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
cakes | +0.001 |
beans | +0.001 |
aro | +0.001 |
mons | +0.001 |
Hil | +0.001 |
Neg logit contributions | |
dent | -0.001 |
impact | -0.001 |
ivering | -0.001 |
regret | -0.001 |
need | -0.001 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.60e-03 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.002 |
impact | +0.002 |
need | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
aro | -0.003 |
beans | -0.003 |
chers | -0.002 |
cakes | -0.002 |
suits | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
dent | +0.007 |
impact | +0.005 |
ivering | +0.005 |
spine | +0.005 |
regret | +0.004 |
Neg logit contributions | |
aro | -0.008 |
beans | -0.008 |
dolphins | -0.008 |
chers | -0.007 |
together | -0.007 |
Token | pain |
Token ID | 2356 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.027 |
ivering | +0.026 |
regret | +0.024 |
need | +0.024 |
Neg logit contributions | |
beans | -0.022 |
da | -0.020 |
suits | -0.019 |
fish | -0.019 |
tad | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
dent | +0.050 |
impact | +0.046 |
regret | +0.044 |
temptation | +0.042 |
need | +0.042 |
Neg logit contributions | |
aro | -0.031 |
beans | -0.030 |
together | -0.028 |
cr | -0.028 |
chers | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.027 |
ivering | +0.026 |
regret | +0.025 |
iver | +0.023 |
Neg logit contributions | |
aro | -0.019 |
beans | -0.018 |
tickets | -0.017 |
poles | -0.017 |
dolphins | -0.016 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
dent | +0.042 |
impact | +0.038 |
regret | +0.037 |
ivering | +0.037 |
need | +0.035 |
Neg logit contributions | |
beans | -0.048 |
aro | -0.045 |
tickets | -0.045 |
da | -0.044 |
poles | -0.044 |
Token | my |
Token ID | 1820 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
dent | +0.074 |
impact | +0.071 |
regret | +0.064 |
need | +0.062 |
sincere | +0.056 |
Neg logit contributions | |
cr | -0.102 |
fl | -0.101 |
es | -0.099 |
kins | -0.098 |
cakes | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
dent | +0.075 |
impact | +0.070 |
sincere | +0.064 |
meantime | +0.061 |
regret | +0.061 |
Neg logit contributions | |
beans | -0.052 |
cr | -0.050 |
es | -0.050 |
fl | -0.050 |
together | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
dent | +0.005 |
impact | +0.005 |
regret | +0.004 |
ivering | +0.004 |
need | +0.004 |
Neg logit contributions | |
aro | -0.009 |
beans | -0.009 |
suits | -0.009 |
Fre | -0.008 |
Off | -0.008 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
dent | +0.026 |
impact | +0.023 |
regret | +0.022 |
ivering | +0.022 |
need | +0.021 |
Neg logit contributions | |
beans | -0.020 |
aro | -0.019 |
chers | -0.018 |
suits | -0.018 |
tickets | -0.017 |
Token | sick |
Token ID | 6639 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
dent | +0.036 |
impact | +0.033 |
ivering | +0.031 |
spine | +0.030 |
meantime | +0.028 |
Neg logit contributions | |
herbs | -0.029 |
aro | -0.029 |
dolphins | -0.028 |
beans | -0.028 |
Finn | -0.028 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
aro | +0.008 |
beans | +0.007 |
chers | +0.007 |
tickets | +0.007 |
Off | +0.007 |
Neg logit contributions | |
dent | -0.007 |
regret | -0.007 |
need | -0.006 |
pain | -0.006 |
ivering | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
dent | +0.035 |
ivering | +0.028 |
impact | +0.028 |
iver | +0.025 |
spine | +0.025 |
Neg logit contributions | |
beans | -0.028 |
dolphins | -0.027 |
aro | -0.026 |
herbs | -0.026 |
ge | -0.026 |
Token | weight |
Token ID | 3463 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
dent | +0.065 |
impact | +0.058 |
sincere | +0.056 |
ivering | +0.056 |
opl | +0.056 |
Neg logit contributions | |
beans | -0.033 |
da | -0.029 |
cor | -0.027 |
tad | -0.027 |
suits | -0.027 |
Token | in |
Token ID | 287 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
dent | +0.035 |
impact | +0.033 |
regret | +0.031 |
sincere | +0.029 |
ivering | +0.029 |
Neg logit contributions | |
beans | -0.023 |
aro | -0.021 |
cr | -0.020 |
bags | -0.020 |
da | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
dent | +0.044 |
ivering | +0.041 |
impact | +0.041 |
regret | +0.039 |
need | +0.036 |
Neg logit contributions | |
aro | -0.020 |
beans | -0.019 |
poles | -0.019 |
tickets | -0.019 |
apr | -0.019 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
dent | +0.036 |
impact | +0.032 |
regret | +0.031 |
ivering | +0.030 |
need | +0.029 |
Neg logit contributions | |
beans | -0.041 |
aro | -0.038 |
suits | -0.038 |
da | -0.038 |
tickets | -0.038 |
Token | my |
Token ID | 1820 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
dent | +0.075 |
impact | +0.071 |
regret | +0.066 |
need | +0.065 |
sincere | +0.060 |
Neg logit contributions | |
fl | -0.101 |
cr | -0.100 |
cakes | -0.098 |
mons | -0.092 |
es | -0.091 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
dent | +0.078 |
impact | +0.071 |
sincere | +0.065 |
regret | +0.064 |
need | +0.063 |
Neg logit contributions | |
beans | -0.056 |
cr | -0.051 |
fl | -0.050 |
da | -0.047 |
cakes | -0.047 |
Token | couldn |
Token ID | 3521 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
dent | +0.024 |
impact | +0.021 |
ivering | +0.021 |
regret | +0.020 |
need | +0.020 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.019 |
cakes | -0.019 |
tickets | -0.019 |
Token | 't |
Token ID | 470 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
chers | +0.005 |
cakes | +0.005 |
tickets | +0.005 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
regret | -0.002 |
ivering | -0.002 |
need | -0.002 |
Token | move |
Token ID | 1445 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
dent | +0.054 |
impact | +0.044 |
ivering | +0.044 |
sincere | +0.042 |
chaos | +0.040 |
Neg logit contributions | |
beans | -0.041 |
cr | -0.038 |
aro | -0.036 |
fish | -0.034 |
zzy | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
beans | +0.027 |
suits | +0.026 |
apr | +0.026 |
pic | +0.026 |
aro | +0.025 |
Neg logit contributions | |
dent | -0.019 |
regret | -0.015 |
impact | -0.015 |
need | -0.014 |
ivering | -0.014 |
Token | there |
Token ID | 612 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.010 |
cakes | +0.010 |
tickets | +0.010 |
Neg logit contributions | |
dent | -0.007 |
need | -0.006 |
regret | -0.006 |
impact | -0.005 |
ivering | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
dent | +0.045 |
impact | +0.040 |
regret | +0.039 |
need | +0.038 |
ivering | +0.038 |
Neg logit contributions | |
aro | -0.030 |
beans | -0.030 |
chers | -0.027 |
suits | -0.026 |
tickets | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
aro | +0.029 |
beans | +0.029 |
chers | +0.027 |
suits | +0.026 |
cakes | +0.025 |
Neg logit contributions | |
dent | -0.038 |
regret | -0.033 |
need | -0.033 |
impact | -0.033 |
ivering | -0.032 |
Token | mail |
Token ID | 6920 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
beans | +0.003 |
aro | +0.003 |
chers | +0.003 |
suits | +0.003 |
tickets | +0.003 |
Neg logit contributions | |
dent | -0.003 |
impact | -0.003 |
regret | -0.003 |
need | -0.003 |
ivering | -0.003 |
Token | man |
Token ID | 805 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
dent | +0.042 |
regret | +0.038 |
impact | +0.037 |
need | +0.036 |
ivering | +0.036 |
Neg logit contributions | |
aro | -0.026 |
beans | -0.026 |
chers | -0.024 |
tickets | -0.023 |
suits | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
dent | +0.121 |
impact | +0.107 |
temptation | +0.103 |
regret | +0.102 |
pain | +0.098 |
Neg logit contributions | |
aro | -0.059 |
beans | -0.055 |
together | -0.054 |
chers | -0.053 |
es | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
dent | +0.030 |
impact | +0.026 |
regret | +0.026 |
ivering | +0.025 |
need | +0.022 |
Neg logit contributions | |
aro | -0.048 |
beans | -0.047 |
suits | -0.045 |
tickets | -0.045 |
cakes | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
dent | +0.026 |
impact | +0.024 |
regret | +0.023 |
ivering | +0.023 |
temptation | +0.022 |
Neg logit contributions | |
beans | -0.019 |
aro | -0.019 |
chers | -0.018 |
suits | -0.018 |
tickets | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
dent | +0.046 |
impact | +0.044 |
ivering | +0.042 |
regret | +0.039 |
temptation | +0.038 |
Neg logit contributions | |
tickets | -0.023 |
aro | -0.022 |
together | -0.022 |
da | -0.021 |
chers | -0.021 |
Token | mail |
Token ID | 6920 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
dent | +0.023 |
impact | +0.021 |
regret | +0.020 |
ivering | +0.020 |
need | +0.019 |
Neg logit contributions | |
beans | -0.019 |
aro | -0.018 |
suits | -0.017 |
da | -0.017 |
chers | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
beans | +0.017 |
aro | +0.016 |
chers | +0.016 |
cakes | +0.016 |
tickets | +0.016 |
Neg logit contributions | |
dent | -0.011 |
need | -0.009 |
regret | -0.009 |
impact | -0.009 |
ivering | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aro | +0.009 |
beans | +0.009 |
chers | +0.008 |
suits | +0.008 |
Off | +0.008 |
Neg logit contributions | |
dent | -0.016 |
impact | -0.015 |
regret | -0.015 |
ivering | -0.014 |
need | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
dent | +0.036 |
impact | +0.032 |
regret | +0.032 |
ivering | +0.031 |
need | +0.031 |
Neg logit contributions | |
aro | -0.022 |
beans | -0.022 |
chers | -0.020 |
suits | -0.019 |
tickets | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
aro | +0.031 |
beans | +0.030 |
chers | +0.029 |
suits | +0.027 |
cakes | +0.027 |
Neg logit contributions | |
dent | -0.037 |
regret | -0.033 |
need | -0.033 |
impact | -0.032 |
pain | -0.032 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
beans | +0.002 |
aro | +0.002 |
chers | +0.002 |
suits | +0.002 |
tickets | +0.002 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
regret | -0.002 |
need | -0.002 |
ivering | -0.002 |
Token | man |
Token ID | 805 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
dent | +0.008 |
regret | +0.007 |
impact | +0.007 |
ivering | +0.007 |
need | +0.007 |
Neg logit contributions | |
beans | -0.006 |
aro | -0.006 |
chers | -0.005 |
tickets | -0.005 |
suits | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
dent | +0.132 |
impact | +0.119 |
temptation | +0.115 |
regret | +0.112 |
damage | +0.110 |
Neg logit contributions | |
aro | -0.048 |
together | -0.046 |
es | -0.042 |
chers | -0.041 |
da | -0.041 |
Token | He |
Token ID | 679 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
dent | +0.035 |
impact | +0.032 |
regret | +0.032 |
ivering | +0.032 |
temptation | +0.028 |
Neg logit contributions | |
aro | -0.043 |
beans | -0.042 |
cakes | -0.041 |
suits | -0.041 |
poles | -0.040 |
Token | had |
Token ID | 550 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
dent | +0.027 |
impact | +0.025 |
regret | +0.023 |
ivering | +0.023 |
need | +0.022 |
Neg logit contributions | |
beans | -0.022 |
aro | -0.021 |
chers | -0.020 |
suits | -0.020 |
kins | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
dent | +0.008 |
impact | +0.008 |
ivering | +0.008 |
regret | +0.007 |
temptation | +0.007 |
Neg logit contributions | |
da | -0.002 |
tickets | -0.002 |
poles | -0.002 |
apr | -0.002 |
aro | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
dent | +0.004 |
impact | +0.004 |
ivering | +0.004 |
regret | +0.003 |
need | +0.003 |
Neg logit contributions | |
beans | -0.003 |
da | -0.003 |
aro | -0.003 |
suits | -0.003 |
tickets | -0.003 |
Token | bite |
Token ID | 13197 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
dent | +0.022 |
regret | +0.019 |
impact | +0.018 |
ivering | +0.018 |
need | +0.018 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.020 |
suits | -0.019 |
tickets | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
dent | +0.024 |
regret | +0.021 |
impact | +0.021 |
need | +0.020 |
ivering | +0.019 |
Neg logit contributions | |
beans | -0.027 |
aro | -0.027 |
chers | -0.026 |
suits | -0.025 |
cakes | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
aro | +0.011 |
chers | +0.011 |
suits | +0.011 |
beans | +0.011 |
resp | +0.010 |
Neg logit contributions | |
dent | -0.007 |
regret | -0.007 |
need | -0.007 |
pain | -0.007 |
temptation | -0.006 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
dent | +0.026 |
regret | +0.023 |
impact | +0.022 |
need | +0.022 |
ivering | +0.021 |
Neg logit contributions | |
aro | -0.029 |
beans | -0.029 |
chers | -0.027 |
suits | -0.026 |
tickets | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
dent | +0.043 |
impact | +0.037 |
ivering | +0.037 |
regret | +0.033 |
need | +0.033 |
Neg logit contributions | |
beans | -0.028 |
aro | -0.026 |
da | -0.025 |
cr | -0.024 |
strawberries | -0.024 |
Token | tum |
Token ID | 11814 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
dent | +0.029 |
ivering | +0.025 |
impact | +0.025 |
regret | +0.025 |
need | +0.023 |
Neg logit contributions | |
beans | -0.031 |
aro | -0.029 |
tickets | -0.028 |
mons | -0.028 |
apr | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
impact | +0.075 |
dent | +0.075 |
need | +0.068 |
regret | +0.066 |
sincere | +0.060 |
Neg logit contributions | |
fl | -0.102 |
cakes | -0.098 |
cr | -0.097 |
es | -0.091 |
mons | -0.088 |
Token | stretch |
Token ID | 7539 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
dent | +0.073 |
impact | +0.070 |
meantime | +0.063 |
need | +0.061 |
sincere | +0.060 |
Neg logit contributions | |
fl | -0.064 |
beans | -0.063 |
da | -0.061 |
cr | -0.061 |
cakes | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
dent | +0.056 |
impact | +0.049 |
regret | +0.047 |
need | +0.045 |
ivering | +0.045 |
Neg logit contributions | |
beans | -0.056 |
aro | -0.055 |
chers | -0.052 |
suits | -0.051 |
cakes | -0.051 |
Token | happiness |
Token ID | 12157 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
dent | +0.041 |
ivering | +0.040 |
impact | +0.037 |
umpy | +0.035 |
iver | +0.035 |
Neg logit contributions | |
strawberries | -0.025 |
da | -0.025 |
beans | -0.024 |
tickets | -0.024 |
apr | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
dent | +0.037 |
impact | +0.030 |
regret | +0.030 |
need | +0.029 |
ivering | +0.028 |
Neg logit contributions | |
beans | -0.057 |
aro | -0.056 |
chers | -0.053 |
suits | -0.052 |
tickets | -0.052 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.003 |
need | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -7.15e-03 |
Pos logit contributions | |
dent | +0.011 |
impact | +0.009 |
temptation | +0.009 |
regret | +0.008 |
sincere | +0.008 |
Neg logit contributions | |
fl | -0.016 |
suits | -0.016 |
bags | -0.015 |
ishes | -0.015 |
Off | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
dent | +0.011 |
regret | +0.010 |
impact | +0.010 |
need | +0.010 |
ivering | +0.009 |
Neg logit contributions | |
aro | -0.012 |
beans | -0.012 |
chers | -0.011 |
tickets | -0.011 |
cakes | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
dent | +0.003 |
regret | +0.003 |
need | +0.003 |
impact | +0.003 |
pain | +0.003 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.003 |
suits | -0.003 |
resp | -0.002 |
Token | fire |
Token ID | 2046 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
dent | +0.011 |
impact | +0.010 |
regret | +0.010 |
ivering | +0.010 |
need | +0.010 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.011 |
chers | -0.010 |
suits | -0.010 |
tickets | -0.010 |
Token | man |
Token ID | 805 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
aro | +0.010 |
beans | +0.010 |
fl | +0.009 |
chers | +0.009 |
bags | +0.009 |
Neg logit contributions | |
dent | -0.018 |
impact | -0.017 |
regret | -0.017 |
temptation | -0.016 |
ivering | -0.016 |
Token | walking |
Token ID | 6155 |
Feature activation | +3.80e-04 |
Pos logit contributions | |
dent | +0.113 |
impact | +0.103 |
temptation | +0.098 |
meantime | +0.095 |
regret | +0.093 |
Neg logit contributions | |
together | -0.062 |
chers | -0.058 |
aro | -0.053 |
aboard | -0.052 |
es | -0.052 |
Token | down |
Token ID | 866 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
beans | +0.001 |
aro | +0.001 |
chers | +0.001 |
resp | +0.001 |
mons | +0.001 |
Neg logit contributions | |
dent | -0.001 |
need | -0.001 |
regret | -0.000 |
impact | -0.000 |
ivering | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
beans | +0.014 |
aro | +0.013 |
chers | +0.013 |
suits | +0.012 |
tickets | +0.012 |
Neg logit contributions | |
dent | -0.015 |
regret | -0.013 |
need | -0.013 |
impact | -0.013 |
ivering | -0.012 |
Token | street |
Token ID | 4675 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
beans | +0.029 |
aro | +0.029 |
suits | +0.028 |
chers | +0.028 |
tickets | +0.028 |
Neg logit contributions | |
dent | -0.018 |
regret | -0.015 |
impact | -0.015 |
ivering | -0.014 |
need | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
dent | +0.024 |
impact | +0.022 |
regret | +0.021 |
pain | +0.020 |
ivering | +0.020 |
Neg logit contributions | |
together | -0.017 |
aro | -0.015 |
tickets | -0.015 |
suits | -0.014 |
poles | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.001 |
impact | +0.001 |
need | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.002 |
suits | -0.002 |
tickets | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.019 |
chers | +0.018 |
suits | +0.018 |
tickets | +0.018 |
Neg logit contributions | |
dent | -0.014 |
regret | -0.011 |
impact | -0.011 |
need | -0.011 |
ivering | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
dent | +0.005 |
impact | +0.005 |
regret | +0.005 |
ivering | +0.005 |
hurting | +0.004 |
Neg logit contributions | |
aro | -0.004 |
Off | -0.004 |
suits | -0.004 |
beans | -0.004 |
together | -0.004 |
Token | They |
Token ID | 2990 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.025 |
regret | +0.025 |
need | +0.024 |
ivering | +0.023 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
chers | -0.017 |
suits | -0.017 |
Off | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
dent | +0.015 |
regret | +0.014 |
need | +0.014 |
pain | +0.012 |
sincere | +0.012 |
Neg logit contributions | |
aro | -0.018 |
beans | -0.017 |
fl | -0.016 |
resp | -0.016 |
chers | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
dent | +0.041 |
need | +0.036 |
pain | +0.034 |
regret | +0.034 |
impact | +0.033 |
Neg logit contributions | |
aro | -0.041 |
beans | -0.040 |
resp | -0.039 |
chers | -0.038 |
Off | -0.037 |
Token | cheese |
Token ID | 9891 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
dent | +0.117 |
ivering | +0.116 |
impact | +0.113 |
regret | +0.113 |
earthquake | +0.109 |
Neg logit contributions | |
beans | -0.057 |
da | -0.054 |
sandwiches | -0.050 |
tickets | -0.050 |
poles | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
aro | +0.011 |
Hil | +0.010 |
Fre | +0.010 |
Fre | +0.010 |
Fel | +0.010 |
Neg logit contributions | |
dent | -0.007 |
end | -0.006 |
need | -0.006 |
pain | -0.006 |
bleeding | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
dent | +0.044 |
need | +0.037 |
pain | +0.037 |
regret | +0.037 |
hurting | +0.034 |
Neg logit contributions | |
aro | -0.044 |
chers | -0.041 |
beans | -0.041 |
resp | -0.041 |
Off | -0.039 |
Token | ham |
Token ID | 8891 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ivering | +0.099 |
dent | +0.098 |
regret | +0.096 |
impact | +0.095 |
iver | +0.094 |
Neg logit contributions | |
beans | -0.053 |
da | -0.049 |
tickets | -0.045 |
sandwiches | -0.044 |
poles | -0.044 |
Token | on |
Token ID | 319 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
dent | +0.049 |
regret | +0.043 |
impact | +0.042 |
need | +0.042 |
ivering | +0.041 |
Neg logit contributions | |
aro | -0.032 |
beans | -0.032 |
chers | -0.029 |
suits | -0.028 |
tickets | -0.028 |
Token | they |
Token ID | 484 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
aro | +0.027 |
chers | +0.025 |
beans | +0.025 |
rob | +0.024 |
resp | +0.024 |
Neg logit contributions | |
dent | -0.013 |
need | -0.013 |
pain | -0.012 |
gloomy | -0.011 |
sad | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
dent | +0.021 |
ivering | +0.017 |
impact | +0.017 |
regret | +0.016 |
temptation | +0.015 |
Neg logit contributions | |
beans | -0.028 |
aro | -0.027 |
chers | -0.027 |
suits | -0.027 |
tickets | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.014 |
cakes | +0.013 |
bags | +0.013 |
Neg logit contributions | |
dent | -0.015 |
regret | -0.013 |
need | -0.013 |
pain | -0.013 |
impact | -0.012 |
Token | big |
Token ID | 1263 |
Feature activation | -6.47e-04 |
Pos logit contributions | |
dent | +0.014 |
impact | +0.012 |
regret | +0.012 |
ivering | +0.012 |
need | +0.012 |
Neg logit contributions | |
beans | -0.012 |
aro | -0.012 |
chers | -0.011 |
tickets | -0.011 |
suits | -0.011 |
Token | snow |
Token ID | 6729 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
ivering | +0.001 |
impact | +0.001 |
need | +0.001 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
da | -0.001 |
tickets | -0.001 |
poles | -0.001 |
Token | man |
Token ID | 805 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
dent | +0.004 |
regret | +0.004 |
impact | +0.004 |
need | +0.004 |
ivering | +0.004 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.003 |
suits | -0.002 |
tickets | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
dent | +0.104 |
impact | +0.094 |
regret | +0.089 |
temptation | +0.088 |
ivering | +0.086 |
Neg logit contributions | |
chers | -0.069 |
together | -0.068 |
aro | -0.067 |
aboard | -0.065 |
tickets | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
dent | +0.035 |
impact | +0.031 |
regret | +0.031 |
ivering | +0.031 |
need | +0.030 |
Neg logit contributions | |
aro | -0.020 |
beans | -0.020 |
chers | -0.018 |
tickets | -0.018 |
suits | -0.017 |
Token | park |
Token ID | 3952 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
dent | +0.015 |
impact | +0.014 |
ivering | +0.014 |
regret | +0.014 |
temptation | +0.013 |
Neg logit contributions | |
da | -0.012 |
tickets | -0.011 |
poles | -0.011 |
suits | -0.011 |
fl | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
dent | +0.050 |
impact | +0.045 |
regret | +0.044 |
ivering | +0.042 |
pain | +0.040 |
Neg logit contributions | |
aro | -0.048 |
beans | -0.046 |
tickets | -0.046 |
suits | -0.045 |
together | -0.045 |
Token | He |
Token ID | 679 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.010 |
impact | +0.010 |
need | +0.009 |
ivering | +0.009 |
Neg logit contributions | |
aro | -0.026 |
beans | -0.026 |
chers | -0.025 |
tickets | -0.024 |
suits | -0.024 |
Token | He |
Token ID | 1544 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
dent | +0.022 |
impact | +0.019 |
regret | +0.019 |
need | +0.018 |
ivering | +0.018 |
Neg logit contributions | |
aro | -0.019 |
beans | -0.019 |
chers | -0.018 |
Off | -0.018 |
suits | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
aro | +0.011 |
beans | +0.010 |
cakes | +0.010 |
chers | +0.010 |
mons | +0.010 |
Neg logit contributions | |
dent | -0.007 |
regret | -0.007 |
need | -0.007 |
pain | -0.006 |
sincere | -0.006 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.022 |
chers | +0.021 |
suits | +0.020 |
cakes | +0.020 |
Neg logit contributions | |
dent | -0.030 |
regret | -0.027 |
need | -0.027 |
impact | -0.026 |
pain | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
dent | +0.021 |
regret | +0.019 |
need | +0.018 |
impact | +0.018 |
pain | +0.018 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
chers | -0.017 |
suits | -0.017 |
resp | -0.016 |
Token | troubled |
Token ID | 17840 |
Feature activation | -7.08e-03 |
Pos logit contributions | |
dent | +0.036 |
impact | +0.033 |
ivering | +0.032 |
regret | +0.032 |
need | +0.031 |
Neg logit contributions | |
beans | -0.032 |
aro | -0.029 |
da | -0.029 |
suits | -0.028 |
tickets | -0.028 |
Token | man |
Token ID | 582 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
dent | +0.012 |
regret | +0.010 |
impact | +0.010 |
ivering | +0.010 |
need | +0.010 |
Neg logit contributions | |
beans | -0.010 |
aro | -0.010 |
da | -0.009 |
tickets | -0.009 |
suits | -0.009 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
dent | +0.107 |
impact | +0.091 |
temptation | +0.086 |
ivering | +0.085 |
pain | +0.084 |
Neg logit contributions | |
aro | -0.066 |
beans | -0.066 |
together | -0.063 |
chers | -0.061 |
cr | -0.061 |
Token | in |
Token ID | 287 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
dent | +0.019 |
regret | +0.016 |
impact | +0.016 |
need | +0.016 |
ivering | +0.015 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
chers | -0.017 |
suits | -0.016 |
cakes | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
dent | +0.034 |
ivering | +0.032 |
impact | +0.031 |
regret | +0.029 |
iver | +0.029 |
Neg logit contributions | |
aro | -0.015 |
tickets | -0.015 |
beans | -0.015 |
poles | -0.014 |
da | -0.013 |
Token | same |
Token ID | 976 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
suits | +0.005 |
da | +0.005 |
tickets | +0.005 |
poles | +0.004 |
ge | +0.004 |
Neg logit contributions | |
dent | -0.007 |
impact | -0.006 |
ivering | -0.006 |
iver | -0.006 |
need | -0.006 |
Token | direction |
Token ID | 4571 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
dent | +0.003 |
regret | +0.003 |
impact | +0.003 |
ivering | +0.003 |
need | +0.003 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
suits | -0.003 |
tickets | -0.003 |
poles | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
dent | +0.002 |
impact | +0.002 |
regret | +0.002 |
ivering | +0.002 |
need | +0.002 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.002 |
suits | -0.002 |
Off | -0.002 |
tickets | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
dent | +0.008 |
need | +0.007 |
regret | +0.007 |
impact | +0.007 |
ivering | +0.007 |
Neg logit contributions | |
beans | -0.008 |
aro | -0.008 |
chers | -0.007 |
tickets | -0.007 |
bags | -0.007 |
Token | Let |
Token ID | 5756 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
aro | +0.030 |
beans | +0.029 |
chers | +0.028 |
bags | +0.026 |
kins | +0.026 |
Neg logit contributions | |
dent | -0.023 |
need | -0.019 |
regret | -0.019 |
pain | -0.019 |
impact | -0.018 |
Token | 's |
Token ID | 338 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
dent | +0.003 |
need | +0.003 |
regret | +0.003 |
pain | +0.003 |
end | +0.002 |
Neg logit contributions | |
beans | -0.008 |
aro | -0.007 |
chers | -0.007 |
suits | -0.007 |
ista | -0.007 |
Token | count |
Token ID | 954 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
dent | +0.013 |
impact | +0.011 |
regret | +0.011 |
ivering | +0.011 |
need | +0.010 |
Neg logit contributions | |
beans | -0.017 |
aro | -0.017 |
chers | -0.016 |
tickets | -0.016 |
suits | -0.016 |
Token | how |
Token ID | 703 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
beans | +0.040 |
aro | +0.038 |
chers | +0.036 |
suits | +0.035 |
mons | +0.035 |
Neg logit contributions | |
dent | -0.037 |
need | -0.033 |
impact | -0.030 |
regret | -0.029 |
anymore | -0.029 |
Token | many |
Token ID | 867 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
beans | +0.108 |
aro | +0.106 |
chers | +0.102 |
rob | +0.101 |
fl | +0.098 |
Neg logit contributions | |
need | -0.072 |
dent | -0.071 |
regret | -0.061 |
temptation | -0.061 |
damage | -0.059 |
Token | steps |
Token ID | 4831 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
beans | +0.045 |
aro | +0.044 |
chers | +0.042 |
cakes | +0.041 |
resp | +0.040 |
Neg logit contributions | |
dent | -0.054 |
need | -0.048 |
impact | -0.045 |
regret | -0.045 |
pain | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -9.66e-04 |
Pos logit contributions | |
beans | +0.034 |
aro | +0.033 |
resp | +0.030 |
chers | +0.030 |
ista | +0.030 |
Neg logit contributions | |
dent | -0.027 |
need | -0.025 |
impact | -0.022 |
regret | -0.021 |
damage | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
dent | +0.002 |
ivering | +0.001 |
impact | +0.001 |
regret | +0.001 |
need | +0.001 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.001 |
tickets | -0.001 |
poles | -0.001 |
chers | -0.001 |
Token | hole |
Token ID | 7604 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
dent | +0.014 |
ivering | +0.014 |
impact | +0.013 |
regret | +0.013 |
sincere | +0.012 |
Neg logit contributions | |
poles | -0.011 |
tickets | -0.010 |
beans | -0.010 |
aro | -0.010 |
da | -0.009 |
Token | ever |
Token ID | 1683 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
dent | +0.005 |
need | +0.005 |
regret | +0.005 |
impact | +0.005 |
ivering | +0.005 |
Neg logit contributions | |
beans | -0.007 |
aro | -0.007 |
suits | -0.007 |
apr | -0.007 |
resp | -0.007 |
Token | after |
Token ID | 706 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
dent | +0.009 |
regret | +0.008 |
impact | +0.008 |
ivering | +0.007 |
need | +0.007 |
Neg logit contributions | |
beans | -0.006 |
aro | -0.006 |
suits | -0.006 |
chers | -0.005 |
tickets | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
beans | +0.040 |
aro | +0.038 |
suits | +0.037 |
chers | +0.037 |
Off | +0.036 |
Neg logit contributions | |
dent | -0.026 |
need | -0.022 |
regret | -0.022 |
impact | -0.021 |
ivering | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.009 |
bags | +0.009 |
suits | +0.009 |
Neg logit contributions | |
dent | -0.006 |
regret | -0.005 |
need | -0.005 |
impact | -0.005 |
ivering | -0.005 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
aro | +0.019 |
beans | +0.018 |
mons | +0.017 |
chers | +0.017 |
fl | +0.017 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.013 |
need | -0.013 |
impact | -0.011 |
pain | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
beans | +0.033 |
resp | +0.031 |
aro | +0.029 |
chers | +0.028 |
suits | +0.028 |
Neg logit contributions | |
regret | -0.020 |
dent | -0.020 |
pain | -0.018 |
need | -0.018 |
my | -0.017 |
Token | some |
Token ID | 617 |
Feature activation | -4.65e-04 |
Pos logit contributions | |
aro | +0.133 |
beans | +0.130 |
rob | +0.127 |
kins | +0.125 |
chers | +0.119 |
Neg logit contributions | |
need | -0.070 |
end | -0.066 |
my | -0.062 |
regret | -0.062 |
damage | -0.054 |
Token | cake |
Token ID | 12187 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
need | +0.001 |
impact | +0.001 |
pain | +0.001 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
chers | -0.001 |
suits | -0.001 |
Off | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
aro | +0.061 |
Fel | +0.060 |
Fre | +0.057 |
chers | +0.056 |
Hil | +0.055 |
Neg logit contributions | |
dent | -0.021 |
need | -0.016 |
anymore | -0.015 |
my | -0.014 |
regret | -0.014 |
Token | juice |
Token ID | 13135 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
aro | +0.013 |
beans | +0.012 |
ela | +0.012 |
Area | +0.012 |
chers | +0.012 |
Neg logit contributions | |
regret | -0.010 |
dent | -0.010 |
need | -0.010 |
pain | -0.010 |
damage | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
aro | +0.025 |
Fre | +0.024 |
Fel | +0.023 |
beans | +0.023 |
arm | +0.023 |
Neg logit contributions | |
dent | -0.010 |
need | -0.008 |
anymore | -0.007 |
regret | -0.007 |
impact | -0.007 |
Token | played |
Token ID | 2826 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
aro | +0.004 |
beans | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.003 |
impact | -0.003 |
need | -0.003 |
ivering | -0.003 |
Token | together |
Token ID | 1978 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
aro | +0.004 |
beans | +0.003 |
Fre | +0.003 |
Hil | +0.003 |
resp | +0.003 |
Neg logit contributions | |
dent | -0.004 |
need | -0.004 |
impact | -0.004 |
regret | -0.004 |
anymore | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-03 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
chers | +0.005 |
cakes | +0.005 |
mons | +0.005 |
Neg logit contributions | |
dent | -0.003 |
impact | -0.003 |
need | -0.003 |
regret | -0.003 |
ivering | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +8.15e-03 |
Pos logit contributions | |
dent | +0.005 |
regret | +0.004 |
impact | +0.004 |
need | +0.004 |
ivering | +0.004 |
Neg logit contributions | |
beans | -0.007 |
aro | -0.007 |
chers | -0.007 |
suits | -0.007 |
tickets | -0.007 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
aro | +0.017 |
beans | +0.016 |
mons | +0.015 |
fl | +0.015 |
poles | +0.015 |
Neg logit contributions | |
regret | -0.010 |
need | -0.009 |
dent | -0.009 |
my | -0.008 |
sad | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
beans | +0.022 |
resp | +0.020 |
suits | +0.020 |
chers | +0.019 |
Off | +0.019 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.012 |
need | -0.012 |
my | -0.011 |
pain | -0.011 |
Token | each |
Token ID | 1123 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
aro | +0.126 |
rob | +0.121 |
beans | +0.114 |
kins | +0.113 |
ves | +0.110 |
Neg logit contributions | |
need | -0.064 |
end | -0.063 |
my | -0.059 |
regret | -0.052 |
damage | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
aro | +0.036 |
beans | +0.035 |
chers | +0.033 |
bags | +0.032 |
resp | +0.031 |
Neg logit contributions | |
dent | -0.035 |
need | -0.033 |
regret | -0.031 |
impact | -0.031 |
pain | -0.030 |
Token | cookie |
Token ID | 19751 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
chers | +0.004 |
Fre | +0.004 |
mons | +0.004 |
Neg logit contributions | |
dent | -0.003 |
need | -0.003 |
regret | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
aro | +0.031 |
Fre | +0.029 |
Hil | +0.029 |
Fre | +0.028 |
chers | +0.028 |
Neg logit contributions | |
dent | -0.015 |
need | -0.012 |
pain | -0.011 |
regret | -0.011 |
impact | -0.011 |
Token | let |
Token ID | 1309 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
dent | +0.002 |
need | +0.002 |
regret | +0.002 |
pain | +0.002 |
damage | +0.002 |
Neg logit contributions | |
aro | -0.003 |
suits | -0.003 |
beans | -0.003 |
Area | -0.003 |
chers | -0.003 |
Token | again |
Token ID | 757 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
resp | +0.002 |
cakes | +0.002 |
mons | +0.002 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
pain | -0.002 |
regret | -0.002 |
anymore | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
aro | +0.013 |
beans | +0.013 |
cakes | +0.013 |
chers | +0.013 |
resp | +0.013 |
Neg logit contributions | |
dent | -0.006 |
need | -0.005 |
regret | -0.005 |
impact | -0.005 |
pain | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
beans | +0.015 |
aro | +0.015 |
chers | +0.014 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.010 |
impact | -0.010 |
need | -0.010 |
ivering | -0.010 |
Token | tossed |
Token ID | 22591 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.013 |
resp | +0.013 |
mons | +0.013 |
cakes | +0.013 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.009 |
need | -0.008 |
impact | -0.007 |
pain | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
aro | +0.027 |
resp | +0.026 |
beans | +0.026 |
chers | +0.025 |
cakes | +0.025 |
Neg logit contributions | |
dent | -0.018 |
impact | -0.015 |
pain | -0.015 |
need | -0.015 |
regret | -0.015 |
Token | hoop |
Token ID | 44792 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
dent | +0.004 |
regret | +0.003 |
impact | +0.003 |
need | +0.003 |
ivering | +0.003 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.002 |
chers | -0.002 |
tickets | -0.002 |
suits | -0.002 |
Token | higher |
Token ID | 2440 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
aro | +0.099 |
resp | +0.096 |
beans | +0.094 |
Fre | +0.092 |
ports | +0.092 |
Neg logit contributions | |
dent | -0.084 |
need | -0.072 |
anymore | -0.069 |
impact | -0.068 |
hurting | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +8.80e-03 |
Pos logit contributions | |
aro | +0.072 |
chers | +0.071 |
beans | +0.068 |
resp | +0.068 |
cakes | +0.067 |
Neg logit contributions | |
dent | -0.039 |
impact | -0.030 |
need | -0.028 |
pain | -0.027 |
regret | -0.027 |
Token | higher |
Token ID | 2440 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
aro | +0.014 |
beans | +0.014 |
resp | +0.014 |
chers | +0.013 |
tickets | +0.013 |
Neg logit contributions | |
dent | -0.014 |
regret | -0.012 |
impact | -0.012 |
need | -0.012 |
hurting | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
aro | +0.021 |
beans | +0.021 |
chers | +0.020 |
cakes | +0.020 |
resp | +0.019 |
Neg logit contributions | |
dent | -0.018 |
impact | -0.015 |
regret | -0.015 |
need | -0.014 |
ivering | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
aro | +0.017 |
beans | +0.017 |
resp | +0.016 |
chers | +0.016 |
tickets | +0.015 |
Neg logit contributions | |
dent | -0.017 |
regret | -0.015 |
impact | -0.015 |
need | -0.014 |
ivering | -0.013 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
aro | +0.037 |
beans | +0.036 |
chers | +0.035 |
bags | +0.033 |
tickets | +0.033 |
Neg logit contributions | |
dent | -0.019 |
need | -0.015 |
impact | -0.014 |
regret | -0.014 |
ivering | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
dent | +0.029 |
regret | +0.025 |
impact | +0.025 |
ivering | +0.024 |
need | +0.023 |
Neg logit contributions | |
beans | -0.026 |
aro | -0.025 |
chers | -0.024 |
suits | -0.024 |
tickets | -0.024 |
Token | can |
Token ID | 460 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
aro | +0.040 |
beans | +0.039 |
rob | +0.038 |
chers | +0.037 |
kins | +0.036 |
Neg logit contributions | |
need | -0.014 |
dent | -0.013 |
end | -0.011 |
impact | -0.011 |
regret | -0.010 |
Token | we |
Token ID | 356 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
dent | +0.017 |
need | +0.016 |
regret | +0.015 |
impact | +0.014 |
temptation | +0.014 |
Neg logit contributions | |
beans | -0.017 |
suits | -0.016 |
chers | -0.016 |
bags | -0.016 |
aro | -0.015 |
Token | give |
Token ID | 1577 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
dent | +0.033 |
regret | +0.028 |
impact | +0.028 |
ivering | +0.027 |
need | +0.026 |
Neg logit contributions | |
aro | -0.034 |
beans | -0.034 |
chers | -0.031 |
suits | -0.031 |
tickets | -0.031 |
Token | them |
Token ID | 606 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
beans | +0.025 |
ibr | +0.024 |
bags | +0.024 |
kins | +0.024 |
ela | +0.023 |
Neg logit contributions | |
need | -0.013 |
end | -0.011 |
hurting | -0.011 |
my | -0.011 |
hurt | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
beans | +0.115 |
ela | +0.112 |
aro | +0.111 |
chers | +0.107 |
rob | +0.105 |
Neg logit contributions | |
end | -0.069 |
need | -0.061 |
my | -0.056 |
anymore | -0.056 |
mean | -0.052 |
Token | bread |
Token ID | 8509 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.013 |
chers | +0.013 |
ela | +0.012 |
bags | +0.012 |
Neg logit contributions | |
dent | -0.018 |
need | -0.017 |
impact | -0.016 |
regret | -0.016 |
pain | -0.015 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
aro | +0.060 |
beans | +0.058 |
chers | +0.056 |
Fel | +0.055 |
Hil | +0.055 |
Neg logit contributions | |
dent | -0.034 |
need | -0.029 |
impact | -0.026 |
ivering | -0.025 |
anymore | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
aro | +0.009 |
beans | +0.009 |
chers | +0.009 |
bags | +0.008 |
cakes | +0.008 |
Neg logit contributions | |
dent | -0.008 |
need | -0.007 |
regret | -0.007 |
pain | -0.006 |
impact | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
aro | +0.009 |
beans | +0.008 |
chers | +0.008 |
cakes | +0.008 |
resp | +0.008 |
Neg logit contributions | |
dent | -0.005 |
regret | -0.004 |
need | -0.004 |
ivering | -0.004 |
pain | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.013 |
chers | +0.012 |
suits | +0.012 |
mons | +0.012 |
Neg logit contributions | |
dent | -0.011 |
regret | -0.010 |
need | -0.010 |
impact | -0.009 |
pain | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
beans | +0.035 |
aro | +0.035 |
chers | +0.032 |
tickets | +0.032 |
suits | +0.032 |
Neg logit contributions | |
dent | -0.027 |
regret | -0.024 |
need | -0.023 |
ivering | -0.022 |
impact | -0.022 |
Token | raining |
Token ID | 43079 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
aro | +0.026 |
beans | +0.026 |
chers | +0.025 |
suits | +0.024 |
tickets | +0.024 |
Neg logit contributions | |
dent | -0.015 |
impact | -0.013 |
regret | -0.012 |
need | -0.012 |
ivering | -0.011 |
Token | outside |
Token ID | 2354 |
Feature activation | +6.59e-04 |
Pos logit contributions | |
beans | +0.044 |
aro | +0.044 |
chers | +0.041 |
suits | +0.040 |
tickets | +0.040 |
Neg logit contributions | |
dent | -0.046 |
regret | -0.040 |
impact | -0.040 |
need | -0.038 |
ivering | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-04 |
Pos logit contributions | |
beans | +0.001 |
aro | +0.001 |
cakes | +0.001 |
together | +0.001 |
tickets | +0.001 |
Neg logit contributions | |
dent | -0.001 |
impact | -0.001 |
regret | -0.001 |
ivering | -0.001 |
sincere | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
aro | +0.000 |
beans | +0.000 |
chers | +0.000 |
tickets | +0.000 |
suits | +0.000 |
Neg logit contributions | |
dent | -0.000 |
impact | -0.000 |
regret | -0.000 |
ivering | -0.000 |
need | -0.000 |
Token | got |
Token ID | 1392 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
aro | +0.039 |
beans | +0.039 |
suits | +0.037 |
chers | +0.037 |
tickets | +0.036 |
Neg logit contributions | |
dent | -0.036 |
impact | -0.031 |
ivering | -0.030 |
regret | -0.029 |
temptation | -0.028 |
Token | all |
Token ID | 477 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
aro | +0.039 |
beans | +0.037 |
chers | +0.036 |
tickets | +0.036 |
cakes | +0.035 |
Neg logit contributions | |
dent | -0.030 |
impact | -0.026 |
ivering | -0.025 |
regret | -0.024 |
need | -0.022 |
Token | wet |
Token ID | 9583 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
beans | +0.032 |
aro | +0.032 |
chers | +0.030 |
suits | +0.029 |
tickets | +0.029 |
Neg logit contributions | |
dent | -0.020 |
regret | -0.017 |
impact | -0.016 |
need | -0.016 |
ivering | -0.016 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.023 |
chers | +0.021 |
suits | +0.021 |
tickets | +0.021 |
Neg logit contributions | |
dent | -0.020 |
regret | -0.017 |
impact | -0.017 |
need | -0.016 |
ivering | -0.016 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
beans | +0.017 |
aro | +0.017 |
chers | +0.016 |
suits | +0.016 |
tickets | +0.016 |
Neg logit contributions | |
dent | -0.014 |
impact | -0.012 |
regret | -0.012 |
need | -0.011 |
ivering | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
beans | +0.042 |
chers | +0.041 |
aro | +0.040 |
suits | +0.039 |
rob | +0.038 |
Neg logit contributions | |
need | -0.022 |
dent | -0.021 |
pain | -0.021 |
regret | -0.020 |
sad | -0.019 |
Token | knife |
Token ID | 9845 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
dent | +0.046 |
ivering | +0.044 |
regret | +0.041 |
impact | +0.041 |
iver | +0.040 |
Neg logit contributions | |
beans | -0.032 |
mons | -0.028 |
strawberries | -0.028 |
da | -0.027 |
cakes | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
aro | +0.021 |
beans | +0.020 |
chers | +0.019 |
resp | +0.018 |
cakes | +0.018 |
Neg logit contributions | |
dent | -0.015 |
need | -0.013 |
regret | -0.013 |
impact | -0.012 |
ivering | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
dent | +0.025 |
need | +0.022 |
regret | +0.022 |
pain | +0.021 |
damage | +0.020 |
Neg logit contributions | |
aro | -0.030 |
beans | -0.029 |
chers | -0.028 |
resp | -0.027 |
suits | -0.027 |
Token | spoon |
Token ID | 24556 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
dent | +0.045 |
ivering | +0.043 |
impact | +0.041 |
regret | +0.041 |
iver | +0.041 |
Neg logit contributions | |
beans | -0.028 |
aro | -0.025 |
mons | -0.025 |
da | -0.025 |
tickets | -0.024 |
Token | from |
Token ID | 422 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.014 |
chers | +0.014 |
Off | +0.013 |
resp | +0.013 |
Neg logit contributions | |
dent | -0.008 |
need | -0.007 |
regret | -0.007 |
impact | -0.006 |
ivering | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.027 |
chers | +0.025 |
suits | +0.024 |
cakes | +0.024 |
Neg logit contributions | |
dent | -0.036 |
regret | -0.032 |
impact | -0.031 |
need | -0.031 |
ivering | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.023 |
regret | +0.023 |
ivering | +0.022 |
need | +0.022 |
Neg logit contributions | |
beans | -0.039 |
aro | -0.039 |
chers | -0.037 |
tickets | -0.036 |
suits | -0.036 |
Token | bag |
Token ID | 6131 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
dent | +0.016 |
regret | +0.014 |
impact | +0.014 |
ivering | +0.014 |
need | +0.013 |
Neg logit contributions | |
beans | -0.014 |
aro | -0.014 |
tickets | -0.014 |
chers | -0.013 |
suits | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
dent | +0.018 |
impact | +0.015 |
regret | +0.015 |
ivering | +0.014 |
need | +0.014 |
Neg logit contributions | |
beans | -0.024 |
aro | -0.023 |
chers | -0.022 |
suits | -0.022 |
tickets | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
dent | +0.002 |
impact | +0.001 |
regret | +0.001 |
ivering | +0.001 |
need | +0.001 |
Neg logit contributions | |
beans | -0.005 |
aro | -0.005 |
chers | -0.005 |
suits | -0.005 |
tickets | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
beans | +0.011 |
aro | +0.011 |
chers | +0.011 |
suits | +0.010 |
tickets | +0.010 |
Neg logit contributions | |
dent | -0.009 |
regret | -0.008 |
impact | -0.008 |
need | -0.007 |
ivering | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
beans | +0.025 |
aro | +0.025 |
chers | +0.023 |
cakes | +0.023 |
suits | +0.023 |
Neg logit contributions | |
dent | -0.024 |
impact | -0.021 |
regret | -0.020 |
ivering | -0.020 |
need | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
aro | +0.017 |
beans | +0.017 |
chers | +0.016 |
suits | +0.016 |
Off | +0.016 |
Neg logit contributions | |
dent | -0.016 |
impact | -0.014 |
regret | -0.014 |
ivering | -0.013 |
need | -0.013 |
Token | L |
Token ID | 43 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
dent | +0.006 |
regret | +0.006 |
impact | +0.006 |
need | +0.005 |
ivering | +0.005 |
Neg logit contributions | |
aro | -0.005 |
beans | -0.005 |
chers | -0.005 |
tickets | -0.005 |
suits | -0.005 |
Token | ily |
Token ID | 813 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
aro | +0.016 |
beans | +0.015 |
chers | +0.015 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
impact | -0.011 |
need | -0.011 |
ivering | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
aro | +0.023 |
beans | +0.021 |
tickets | +0.020 |
chers | +0.020 |
poles | +0.020 |
Neg logit contributions | |
dent | -0.015 |
regret | -0.014 |
sincere | -0.013 |
my | -0.013 |
need | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | -6.14e-04 |
Pos logit contributions | |
aro | +0.040 |
beans | +0.039 |
chers | +0.037 |
cakes | +0.036 |
tickets | +0.035 |
Neg logit contributions | |
dent | -0.040 |
regret | -0.035 |
impact | -0.034 |
need | -0.034 |
ivering | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
dent | +0.001 |
regret | +0.001 |
impact | +0.001 |
need | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
beans | -0.001 |
aro | -0.001 |
chers | -0.001 |
suits | -0.001 |
tickets | -0.001 |
Token | rock |
Token ID | 3881 |
Feature activation | +7.27e-03 |
Pos logit contributions | |
dent | +0.046 |
ivering | +0.045 |
impact | +0.044 |
regret | +0.041 |
need | +0.041 |
Neg logit contributions | |
beans | -0.029 |
da | -0.028 |
poles | -0.028 |
shells | -0.028 |
bags | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.009 |
tickets | +0.009 |
cakes | +0.009 |
Neg logit contributions | |
dent | -0.014 |
impact | -0.012 |
regret | -0.012 |
need | -0.012 |
ivering | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +8.92e-04 |
Pos logit contributions | |
dent | +0.005 |
regret | +0.005 |
need | +0.004 |
impact | +0.004 |
hurting | +0.004 |
Neg logit contributions | |
aro | -0.006 |
beans | -0.005 |
resp | -0.005 |
chers | -0.005 |
suits | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
beans | +0.022 |
aro | +0.022 |
chers | +0.020 |
cakes | +0.019 |
tickets | +0.018 |
Neg logit contributions | |
dent | -0.024 |
regret | -0.021 |
need | -0.020 |
impact | -0.020 |
ivering | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
dent | +0.011 |
regret | +0.008 |
impact | +0.007 |
need | +0.007 |
ivering | +0.006 |
Neg logit contributions | |
beans | -0.041 |
aro | -0.041 |
chers | -0.039 |
suits | -0.038 |
tickets | -0.038 |
Token | would |
Token ID | 561 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
dent | +0.008 |
need | +0.008 |
regret | +0.008 |
my | +0.007 |
ivering | +0.007 |
Neg logit contributions | |
beans | -0.013 |
aro | -0.013 |
resp | -0.012 |
chers | -0.012 |
poles | -0.012 |
Token | always |
Token ID | 1464 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
dent | +0.015 |
impact | +0.012 |
ivering | +0.012 |
regret | +0.012 |
pain | +0.011 |
Neg logit contributions | |
aro | -0.016 |
beans | -0.016 |
tickets | -0.015 |
Off | -0.015 |
da | -0.015 |
Token | tell |
Token ID | 1560 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
dent | +0.037 |
impact | +0.031 |
ivering | +0.030 |
regret | +0.029 |
pain | +0.027 |
Neg logit contributions | |
beans | -0.036 |
aro | -0.036 |
chers | -0.035 |
tickets | -0.035 |
dads | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
dent | +0.017 |
regret | +0.015 |
need | +0.015 |
impact | +0.015 |
pain | +0.014 |
Neg logit contributions | |
beans | -0.016 |
aro | -0.016 |
chers | -0.015 |
suits | -0.015 |
bags | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
rob | +0.039 |
aro | +0.038 |
chers | +0.037 |
beans | +0.036 |
suits | +0.036 |
Neg logit contributions | |
need | -0.023 |
regret | -0.022 |
sad | -0.020 |
anymore | -0.020 |
temptation | -0.019 |
Token | wear |
Token ID | 5806 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
dent | +0.018 |
impact | +0.015 |
regret | +0.014 |
ivering | +0.014 |
need | +0.014 |
Neg logit contributions | |
aro | -0.022 |
beans | -0.022 |
tickets | -0.021 |
chers | -0.021 |
Off | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
dent | +0.004 |
pain | +0.003 |
need | +0.003 |
hurting | +0.003 |
regret | +0.003 |
Neg logit contributions | |
beans | -0.005 |
ista | -0.005 |
aro | -0.005 |
chers | -0.005 |
suits | -0.005 |
Token | colorful |
Token ID | 20239 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
dent | +0.007 |
need | +0.006 |
regret | +0.006 |
pain | +0.006 |
sad | +0.005 |
Neg logit contributions | |
aro | -0.007 |
beans | -0.007 |
chers | -0.006 |
ista | -0.006 |
resp | -0.006 |
Token | rain |
Token ID | 6290 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
beans | +0.024 |
aro | +0.024 |
chers | +0.023 |
Fre | +0.022 |
Lucia | +0.022 |
Neg logit contributions | |
dent | -0.026 |
need | -0.022 |
impact | -0.021 |
regret | -0.021 |
pain | -0.021 |
Token | your |
Token ID | 534 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
beans | +0.017 |
aro | +0.016 |
suits | +0.015 |
mons | +0.015 |
chers | +0.015 |
Neg logit contributions | |
dent | -0.012 |
need | -0.010 |
regret | -0.010 |
hurting | -0.010 |
impact | -0.009 |
Token | vacation |
Token ID | 14600 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
aro | +0.017 |
beans | +0.017 |
chers | +0.016 |
mons | +0.016 |
cakes | +0.015 |
Neg logit contributions | |
dent | -0.018 |
need | -0.016 |
impact | -0.015 |
regret | -0.015 |
pain | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
aro | +0.044 |
beans | +0.041 |
Hil | +0.040 |
resp | +0.039 |
Fre | +0.039 |
Neg logit contributions | |
dent | -0.016 |
need | -0.014 |
impact | -0.013 |
regret | -0.012 |
anymore | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
dent | +0.017 |
regret | +0.014 |
ivering | +0.014 |
impact | +0.014 |
need | +0.013 |
Neg logit contributions | |
aro | -0.023 |
beans | -0.022 |
chers | -0.021 |
tickets | -0.021 |
Off | -0.021 |
Token | miss |
Token ID | 2051 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
aro | +0.043 |
beans | +0.043 |
chers | +0.040 |
cakes | +0.039 |
tickets | +0.039 |
Neg logit contributions | |
dent | -0.030 |
regret | -0.025 |
need | -0.025 |
impact | -0.025 |
ivering | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.020 |
suits | +0.019 |
chers | +0.019 |
mons | +0.019 |
Neg logit contributions | |
dent | -0.010 |
need | -0.009 |
regret | -0.008 |
impact | -0.008 |
temptation | -0.008 |
Token | too |
Token ID | 1165 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
aro | +0.043 |
beans | +0.042 |
mons | +0.039 |
chers | +0.039 |
suits | +0.038 |
Neg logit contributions | |
dent | -0.029 |
need | -0.026 |
regret | -0.025 |
impact | -0.024 |
ivering | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
suits | +0.025 |
tickets | +0.024 |
beans | +0.024 |
aro | +0.023 |
together | +0.023 |
Neg logit contributions | |
dent | -0.026 |
impact | -0.023 |
regret | -0.022 |
ivering | -0.021 |
pain | -0.019 |
Token | But |
Token ID | 887 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
dent | +0.021 |
ivering | +0.017 |
regret | +0.017 |
impact | +0.017 |
need | +0.016 |
Neg logit contributions | |
aro | -0.027 |
beans | -0.027 |
chers | -0.025 |
tickets | -0.025 |
Off | -0.025 |
Token | we |
Token ID | 356 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
dent | +0.031 |
regret | +0.027 |
need | +0.027 |
impact | +0.026 |
temptation | +0.024 |
Neg logit contributions | |
beans | -0.048 |
aro | -0.047 |
suits | -0.046 |
chers | -0.045 |
cakes | -0.045 |
Token | can |
Token ID | 460 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.002 |
ivering | -0.002 |
impact | -0.002 |
regret | -0.002 |
temptation | -0.002 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
dent | +0.022 |
impact | +0.019 |
ivering | +0.019 |
regret | +0.018 |
need | +0.018 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.017 |
da | -0.016 |
suits | -0.016 |
chers | -0.016 |
Token | came |
Token ID | 1625 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
dent | +0.045 |
impact | +0.041 |
regret | +0.039 |
ivering | +0.038 |
temptation | +0.038 |
Neg logit contributions | |
aro | -0.030 |
beans | -0.029 |
chers | -0.028 |
suits | -0.027 |
tickets | -0.026 |
Token | up |
Token ID | 510 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.026 |
regret | +0.024 |
ivering | +0.024 |
temptation | +0.023 |
Neg logit contributions | |
aro | -0.012 |
fl | -0.012 |
beans | -0.011 |
together | -0.011 |
chers | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.005 |
chers | +0.005 |
suits | +0.005 |
tickets | +0.005 |
Neg logit contributions | |
dent | -0.007 |
regret | -0.006 |
impact | -0.006 |
need | -0.005 |
ivering | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
dent | +0.019 |
regret | +0.016 |
impact | +0.016 |
need | +0.015 |
ivering | +0.015 |
Neg logit contributions | |
beans | -0.020 |
aro | -0.020 |
chers | -0.018 |
suits | -0.018 |
tickets | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
dent | +0.007 |
impact | +0.006 |
regret | +0.006 |
need | +0.005 |
ivering | +0.005 |
Neg logit contributions | |
beans | -0.008 |
aro | -0.008 |
chers | -0.007 |
suits | -0.007 |
tickets | -0.007 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
dent | +0.011 |
regret | +0.010 |
need | +0.009 |
impact | +0.009 |
ivering | +0.009 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.011 |
chers | -0.010 |
suits | -0.010 |
tickets | -0.010 |
Token | if |
Token ID | 611 |
Feature activation | +7.03e-04 |
Pos logit contributions | |
dent | +0.038 |
regret | +0.033 |
impact | +0.033 |
need | +0.033 |
ivering | +0.031 |
Neg logit contributions | |
beans | -0.036 |
aro | -0.036 |
chers | -0.033 |
suits | -0.032 |
tickets | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
beans | +0.001 |
aro | +0.001 |
suits | +0.001 |
chers | +0.001 |
Off | +0.001 |
Neg logit contributions | |
dent | -0.001 |
regret | -0.001 |
need | -0.001 |
impact | -0.001 |
temptation | -0.001 |
Token | could |
Token ID | 714 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
dent | +0.031 |
impact | +0.028 |
ivering | +0.027 |
regret | +0.026 |
temptation | +0.026 |
Neg logit contributions | |
beans | -0.021 |
aro | -0.021 |
chers | -0.019 |
suits | -0.019 |
cakes | -0.018 |
Token | borrow |
Token ID | 8804 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
dent | +0.027 |
ivering | +0.023 |
impact | +0.023 |
temptation | +0.021 |
regret | +0.021 |
Neg logit contributions | |
aro | -0.025 |
beans | -0.023 |
chers | -0.023 |
cakes | -0.022 |
tickets | -0.022 |
Token | play |
Token ID | 711 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
dent | +0.022 |
ivering | +0.020 |
temptation | +0.019 |
impact | +0.018 |
pain | +0.018 |
Neg logit contributions | |
together | -0.023 |
aro | -0.023 |
dads | -0.022 |
cakes | -0.022 |
beans | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
aro | +0.012 |
beans | +0.012 |
suits | +0.011 |
Fre | +0.010 |
chers | +0.010 |
Neg logit contributions | |
dent | -0.010 |
impact | -0.008 |
regret | -0.008 |
need | -0.008 |
ivering | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
beans | +0.038 |
aro | +0.036 |
suits | +0.035 |
chers | +0.035 |
cakes | +0.034 |
Neg logit contributions | |
dent | -0.028 |
regret | -0.023 |
need | -0.023 |
impact | -0.022 |
pain | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
aro | +0.051 |
beans | +0.050 |
chers | +0.046 |
suits | +0.046 |
tickets | +0.046 |
Neg logit contributions | |
dent | -0.039 |
need | -0.032 |
impact | -0.032 |
regret | -0.032 |
ivering | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
aro | +0.021 |
beans | +0.020 |
tickets | +0.019 |
chers | +0.019 |
Off | +0.018 |
Neg logit contributions | |
dent | -0.034 |
impact | -0.031 |
regret | -0.031 |
ivering | -0.030 |
need | -0.029 |
Token | minute |
Token ID | 5664 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
dent | +0.008 |
ivering | +0.007 |
regret | +0.007 |
impact | +0.007 |
need | +0.006 |
Neg logit contributions | |
beans | -0.006 |
aro | -0.006 |
suits | -0.005 |
tickets | -0.005 |
chers | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.011 |
impact | +0.011 |
need | +0.011 |
ivering | +0.011 |
Neg logit contributions | |
beans | -0.013 |
aro | -0.013 |
chers | -0.012 |
suits | -0.012 |
tickets | -0.012 |
Token | please |
Token ID | 3387 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
aro | +0.012 |
beans | +0.012 |
suits | +0.012 |
chers | +0.012 |
cakes | +0.011 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.008 |
impact | -0.008 |
need | -0.008 |
pain | -0.007 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.70e-04 |
Pos logit contributions | |
dent | +0.014 |
regret | +0.012 |
impact | +0.012 |
ivering | +0.012 |
need | +0.011 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.010 |
chers | -0.010 |
tickets | -0.010 |
suits | -0.010 |
Token | L |
Token ID | 406 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
dent | +0.001 |
impact | +0.001 |
ivering | +0.001 |
regret | +0.001 |
need | +0.001 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
tickets | -0.001 |
chers | -0.001 |
da | -0.001 |
Token | ila |
Token ID | 10102 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
beans | +0.018 |
suits | +0.016 |
aro | +0.016 |
chers | +0.016 |
poles | +0.016 |
Neg logit contributions | |
dent | -0.020 |
regret | -0.017 |
ivering | -0.017 |
need | -0.017 |
impact | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
beans | +0.044 |
aro | +0.042 |
chers | +0.040 |
suits | +0.040 |
mons | +0.040 |
Neg logit contributions | |
dent | -0.036 |
regret | -0.031 |
need | -0.030 |
impact | -0.030 |
ivering | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.027 |
resp | +0.025 |
mons | +0.025 |
suits | +0.025 |
Neg logit contributions | |
dent | -0.027 |
regret | -0.024 |
need | -0.024 |
impact | -0.023 |
pain | -0.022 |
Token | police |
Token ID | 1644 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
aro | +0.004 |
tickets | +0.003 |
beans | +0.003 |
chers | +0.003 |
dads | +0.003 |
Neg logit contributions | |
dent | -0.004 |
ivering | -0.003 |
impact | -0.003 |
regret | -0.003 |
iver | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.023 |
chers | +0.021 |
suits | +0.021 |
tickets | +0.020 |
Neg logit contributions | |
dent | -0.026 |
regret | -0.023 |
impact | -0.023 |
need | -0.022 |
ivering | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
beans | +0.023 |
aro | +0.022 |
suits | +0.021 |
chers | +0.021 |
cakes | +0.020 |
Neg logit contributions | |
dent | -0.019 |
regret | -0.017 |
need | -0.016 |
impact | -0.015 |
pain | -0.015 |
Token | take |
Token ID | 1011 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
aro | +0.007 |
beans | +0.007 |
chers | +0.006 |
tickets | +0.006 |
suits | +0.006 |
Neg logit contributions | |
dent | -0.005 |
impact | -0.004 |
regret | -0.004 |
ivering | -0.004 |
need | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.012 |
chers | +0.011 |
resp | +0.011 |
mons | +0.011 |
Neg logit contributions | |
dent | -0.013 |
need | -0.011 |
regret | -0.011 |
impact | -0.011 |
pain | -0.011 |
Token | away |
Token ID | 1497 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
beans | +0.034 |
aro | +0.034 |
chers | +0.031 |
cakes | +0.030 |
suits | +0.030 |
Neg logit contributions | |
dent | -0.036 |
regret | -0.032 |
need | -0.032 |
impact | -0.032 |
pain | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.019 |
chers | +0.018 |
mons | +0.018 |
cakes | +0.018 |
Neg logit contributions | |
dent | -0.013 |
regret | -0.011 |
need | -0.011 |
impact | -0.010 |
pain | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
aro | +0.006 |
Off | +0.006 |
suits | +0.006 |
tickets | +0.006 |
chers | +0.006 |
Neg logit contributions | |
dent | -0.008 |
ivering | -0.007 |
impact | -0.007 |
regret | -0.007 |
pain | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
aro | +0.002 |
chers | +0.002 |
Off | +0.002 |
beans | +0.002 |
tickets | +0.002 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
ivering | -0.002 |
regret | -0.002 |
temptation | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
aro | +0.008 |
suits | +0.008 |
beans | +0.008 |
chers | +0.008 |
bags | +0.008 |
Neg logit contributions | |
regret | -0.006 |
need | -0.006 |
dent | -0.006 |
impact | -0.005 |
pain | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
dent | +0.007 |
regret | +0.007 |
need | +0.006 |
impact | +0.006 |
pain | +0.006 |
Neg logit contributions | |
aro | -0.008 |
beans | -0.008 |
chers | -0.007 |
tickets | -0.007 |
suits | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.005 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.004 |
impact | -0.004 |
need | -0.004 |
ivering | -0.004 |
Token | |
Token ID | 220 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.027 |
chers | +0.026 |
suits | +0.025 |
cakes | +0.025 |
Neg logit contributions | |
dent | -0.025 |
regret | -0.021 |
impact | -0.021 |
ivering | -0.020 |
need | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
beans | +0.019 |
aro | +0.018 |
chers | +0.017 |
suits | +0.017 |
tickets | +0.017 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.010 |
impact | -0.010 |
need | -0.010 |
ivering | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
aro | +0.015 |
beans | +0.015 |
chers | +0.014 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.010 |
impact | -0.010 |
need | -0.010 |
ivering | -0.010 |
Token | Em |
Token ID | 10161 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
chers | +0.002 |
tickets | +0.002 |
suits | +0.002 |
Neg logit contributions | |
dent | -0.003 |
regret | -0.002 |
impact | -0.002 |
need | -0.002 |
ivering | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
beans | +0.020 |
aro | +0.020 |
chers | +0.019 |
suits | +0.018 |
tickets | +0.018 |
Neg logit contributions | |
dent | -0.020 |
regret | -0.017 |
impact | -0.017 |
need | -0.017 |
ivering | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
beans | +0.010 |
aro | +0.010 |
chers | +0.009 |
suits | +0.009 |
tickets | +0.009 |
Neg logit contributions | |
dent | -0.015 |
impact | -0.013 |
regret | -0.013 |
need | -0.013 |
ivering | -0.013 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.60e-03 |
Pos logit contributions | |
dent | +0.025 |
regret | +0.022 |
impact | +0.021 |
need | +0.021 |
ivering | +0.020 |
Neg logit contributions | |
beans | -0.028 |
aro | -0.028 |
chers | -0.026 |
suits | -0.026 |
mons | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
dent | +0.012 |
impact | +0.010 |
ivering | +0.010 |
regret | +0.010 |
need | +0.010 |
Neg logit contributions | |
beans | -0.009 |
aro | -0.009 |
chers | -0.009 |
tickets | -0.008 |
cakes | -0.008 |
Token | lot |
Token ID | 1256 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
aro | +0.010 |
beans | +0.010 |
chers | +0.009 |
cakes | +0.009 |
mons | +0.009 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.009 |
impact | -0.008 |
need | -0.008 |
ivering | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
beans | +0.021 |
aro | +0.021 |
chers | +0.020 |
suits | +0.020 |
mons | +0.020 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.008 |
need | -0.008 |
impact | -0.008 |
ivering | -0.007 |
Token | fun |
Token ID | 1257 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
beans | +0.053 |
aro | +0.053 |
chers | +0.049 |
tickets | +0.048 |
suits | +0.048 |
Neg logit contributions | |
dent | -0.060 |
regret | -0.052 |
impact | -0.052 |
ivering | -0.050 |
need | -0.050 |
Token | today |
Token ID | 1909 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
beans | +0.008 |
aro | +0.008 |
chers | +0.007 |
suits | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
dent | -0.007 |
impact | -0.006 |
regret | -0.006 |
need | -0.006 |
ivering | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
aro | +0.007 |
beans | +0.007 |
chers | +0.007 |
suits | +0.007 |
tickets | +0.006 |
Neg logit contributions | |
dent | -0.006 |
impact | -0.005 |
regret | -0.005 |
need | -0.005 |
ivering | -0.005 |
Token | Will |
Token ID | 2561 |
Feature activation | -1.95e-04 |
Pos logit contributions | |
dent | +0.016 |
need | +0.013 |
regret | +0.013 |
impact | +0.013 |
He | +0.011 |
Neg logit contributions | |
aro | -0.038 |
beans | -0.038 |
chers | -0.037 |
bags | -0.036 |
kins | -0.036 |
Token | you |
Token ID | 345 |
Feature activation | +6.37e-03 |
Pos logit contributions | |
dent | +0.000 |
need | +0.000 |
regret | +0.000 |
impact | +0.000 |
ivering | +0.000 |
Neg logit contributions | |
aro | -0.000 |
beans | -0.000 |
mons | -0.000 |
bags | -0.000 |
apr | -0.000 |
Token | welcome |
Token ID | 7062 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
aro | +0.012 |
beans | +0.012 |
mons | +0.011 |
cakes | +0.011 |
resp | +0.011 |
Neg logit contributions | |
dent | -0.009 |
need | -0.008 |
regret | -0.008 |
impact | -0.007 |
ivering | -0.007 |
Token | me |
Token ID | 502 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
dent | +0.012 |
need | +0.011 |
regret | +0.011 |
impact | +0.011 |
ivering | +0.010 |
Neg logit contributions | |
beans | -0.022 |
aro | -0.021 |
mons | -0.021 |
suits | -0.020 |
cakes | -0.020 |
Token | back |
Token ID | 736 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
dent | +0.002 |
need | +0.002 |
regret | +0.002 |
impact | +0.002 |
ivering | +0.002 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.002 |
mons | -0.002 |
chers | -0.002 |
cakes | -0.002 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
aro | +0.040 |
beans | +0.040 |
mons | +0.037 |
chers | +0.036 |
cakes | +0.036 |
Neg logit contributions | |
dent | -0.033 |
need | -0.030 |
regret | -0.030 |
impact | -0.029 |
ivering | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
dent | +0.042 |
regret | +0.036 |
impact | +0.035 |
ivering | +0.035 |
need | +0.033 |
Neg logit contributions | |
aro | -0.051 |
beans | -0.050 |
chers | -0.048 |
suits | -0.047 |
tickets | -0.047 |
Token | M |
Token ID | 44 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
dent | +0.010 |
regret | +0.008 |
impact | +0.008 |
need | +0.008 |
ivering | +0.008 |
Neg logit contributions | |
beans | -0.006 |
aro | -0.006 |
chers | -0.006 |
suits | -0.005 |
tickets | -0.005 |
Token | ira |
Token ID | 8704 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
dent | +0.009 |
impact | +0.008 |
regret | +0.008 |
ivering | +0.007 |
pain | +0.007 |
Neg logit contributions | |
aro | -0.004 |
beans | -0.004 |
tickets | -0.004 |
da | -0.004 |
cakes | -0.004 |
Token | loves |
Token ID | 10408 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
dent | +0.025 |
need | +0.022 |
regret | +0.022 |
ivering | +0.020 |
impact | +0.020 |
Neg logit contributions | |
aro | -0.042 |
beans | -0.040 |
chers | -0.039 |
cakes | -0.039 |
tickets | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -9.19e-03 |
Pos logit contributions | |
beans | +0.013 |
aro | +0.013 |
chers | +0.012 |
suits | +0.012 |
bags | +0.012 |
Neg logit contributions | |
dent | -0.014 |
regret | -0.013 |
need | -0.013 |
impact | -0.013 |
temptation | -0.012 |
Token | sing |
Token ID | 1702 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
dent | +0.012 |
regret | +0.010 |
need | +0.010 |
impact | +0.010 |
ivering | +0.009 |
Neg logit contributions | |
beans | -0.017 |
aro | -0.017 |
chers | -0.017 |
suits | -0.016 |
cakes | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
dent | +0.020 |
need | +0.016 |
impact | +0.016 |
regret | +0.015 |
ivering | +0.015 |
Neg logit contributions | |
aro | -0.065 |
beans | -0.062 |
chers | -0.060 |
mons | -0.059 |
bags | -0.058 |
Token | She |
Token ID | 1375 |
Feature activation | -1.18e-03 |
Pos logit contributions | |
dent | +0.029 |
regret | +0.022 |
impact | +0.022 |
ivering | +0.022 |
pain | +0.019 |
Neg logit contributions | |
aro | -0.057 |
beans | -0.057 |
Fre | -0.054 |
suits | -0.054 |
Off | -0.053 |
Token | sings |
Token ID | 33041 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
dent | +0.002 |
need | +0.002 |
regret | +0.002 |
impact | +0.001 |
pain | +0.001 |
Neg logit contributions | |
aro | -0.002 |
beans | -0.002 |
chers | -0.002 |
cakes | -0.002 |
mons | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
dent | +0.030 |
need | +0.027 |
regret | +0.026 |
impact | +0.026 |
sad | +0.026 |
Neg logit contributions | |
aro | -0.046 |
beans | -0.043 |
mons | -0.041 |
suits | -0.040 |
chers | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
dent | +0.036 |
ivering | +0.032 |
regret | +0.031 |
impact | +0.031 |
need | +0.029 |
Neg logit contributions | |
beans | -0.015 |
tickets | -0.015 |
da | -0.015 |
aro | -0.015 |
apr | -0.014 |
Token | bottle |
Token ID | 9294 |
Feature activation | -7.94e-04 |
Pos logit contributions | |
dent | +0.034 |
ivering | +0.031 |
regret | +0.030 |
impact | +0.028 |
need | +0.028 |
Neg logit contributions | |
beans | -0.024 |
tickets | -0.022 |
da | -0.021 |
chers | -0.021 |
cakes | -0.021 |
Token | after |
Token ID | 706 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
dent | +0.001 |
impact | +0.001 |
regret | +0.001 |
need | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
aro | -0.001 |
beans | -0.001 |
chers | -0.001 |
suits | -0.001 |
tickets | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
beans | +0.005 |
aro | +0.005 |
chers | +0.005 |
suits | +0.005 |
tickets | +0.005 |
Neg logit contributions | |
dent | -0.007 |
regret | -0.006 |
impact | -0.006 |
need | -0.006 |
ivering | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
dent | +0.022 |
regret | +0.019 |
impact | +0.019 |
ivering | +0.018 |
need | +0.018 |
Neg logit contributions | |
aro | -0.025 |
beans | -0.025 |
chers | -0.023 |
tickets | -0.023 |
cakes | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.010 |
impact | +0.010 |
ivering | +0.010 |
need | +0.010 |
Neg logit contributions | |
aro | -0.019 |
beans | -0.019 |
chers | -0.018 |
suits | -0.018 |
tickets | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
aro | +0.005 |
beans | +0.005 |
mons | +0.005 |
suits | +0.005 |
chers | +0.005 |
Neg logit contributions | |
dent | -0.004 |
regret | -0.004 |
need | -0.003 |
impact | -0.003 |
pain | -0.003 |
Token | no |
Token ID | 645 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
dent | +0.043 |
regret | +0.037 |
impact | +0.036 |
need | +0.036 |
ivering | +0.034 |
Neg logit contributions | |
beans | -0.048 |
aro | -0.048 |
chers | -0.045 |
suits | -0.045 |
tickets | -0.044 |
Token | longer |
Token ID | 2392 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
beans | +0.006 |
tickets | +0.006 |
together | +0.006 |
aro | +0.006 |
da | +0.006 |
Neg logit contributions | |
dent | -0.005 |
ivering | -0.005 |
impact | -0.004 |
iver | -0.004 |
bleeding | -0.004 |
Token | selfish |
Token ID | 20363 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
dent | +0.021 |
impact | +0.017 |
ivering | +0.016 |
regret | +0.016 |
need | +0.015 |
Neg logit contributions | |
beans | -0.032 |
aro | -0.032 |
chers | -0.030 |
tickets | -0.030 |
suits | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
dent | +0.019 |
impact | +0.016 |
regret | +0.016 |
ivering | +0.016 |
need | +0.015 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
chers | -0.017 |
tickets | -0.017 |
suits | -0.017 |
Token | shared |
Token ID | 4888 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
dent | +0.017 |
regret | +0.016 |
need | +0.015 |
impact | +0.015 |
pain | +0.014 |
Neg logit contributions | |
beans | -0.022 |
aro | -0.021 |
suits | -0.021 |
chers | -0.020 |
tickets | -0.020 |
Token | nose |
Token ID | 9686 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
dent | +0.019 |
regret | +0.018 |
impact | +0.018 |
need | +0.017 |
ivering | +0.017 |
Neg logit contributions | |
beans | -0.018 |
aro | -0.018 |
suits | -0.016 |
poles | -0.016 |
tickets | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
dent | +0.054 |
impact | +0.052 |
regret | +0.051 |
temptation | +0.048 |
need | +0.047 |
Neg logit contributions | |
aro | -0.038 |
beans | -0.038 |
bags | -0.035 |
cr | -0.035 |
chers | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
dent | +0.022 |
need | +0.019 |
pain | +0.019 |
regret | +0.018 |
bleeding | +0.017 |
Neg logit contributions | |
aro | -0.021 |
chers | -0.020 |
beans | -0.020 |
cakes | -0.019 |
ela | -0.019 |
Token | lot |
Token ID | 1256 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
dent | +0.032 |
impact | +0.030 |
regret | +0.029 |
ivering | +0.029 |
need | +0.028 |
Neg logit contributions | |
beans | -0.029 |
aro | -0.028 |
da | -0.027 |
suits | -0.027 |
tickets | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
dent | +0.007 |
regret | +0.006 |
impact | +0.006 |
need | +0.006 |
ivering | +0.005 |
Neg logit contributions | |
beans | -0.012 |
aro | -0.012 |
chers | -0.012 |
suits | -0.011 |
tickets | -0.011 |
Token | teeth |
Token ID | 9941 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
aro | +0.025 |
beans | +0.025 |
tickets | +0.023 |
chers | +0.022 |
suits | +0.022 |
Neg logit contributions | |
dent | -0.037 |
impact | -0.033 |
ivering | -0.032 |
regret | -0.032 |
need | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +6.49e-03 |
Pos logit contributions | |
dent | +0.038 |
impact | +0.035 |
regret | +0.033 |
ivering | +0.031 |
need | +0.031 |
Neg logit contributions | |
beans | -0.043 |
aro | -0.042 |
chers | -0.039 |
tickets | -0.039 |
suits | -0.039 |
Token | It |
Token ID | 632 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
aro | +0.012 |
beans | +0.012 |
chers | +0.011 |
tickets | +0.010 |
suits | +0.010 |
Neg logit contributions | |
dent | -0.010 |
regret | -0.008 |
impact | -0.008 |
need | -0.008 |
ivering | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
chers | +0.002 |
tickets | +0.002 |
mons | +0.002 |
Neg logit contributions | |
dent | -0.002 |
regret | -0.001 |
need | -0.001 |
pain | -0.001 |
ivering | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.012 |
impact | +0.012 |
need | +0.011 |
ivering | +0.011 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.011 |
chers | -0.010 |
suits | -0.010 |
tickets | -0.010 |
Token | crocod |
Token ID | 37565 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
dent | +0.014 |
impact | +0.012 |
regret | +0.012 |
ivering | +0.012 |
need | +0.012 |
Neg logit contributions | |
beans | -0.011 |
aro | -0.011 |
chers | -0.010 |
suits | -0.010 |
tickets | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -9.15e-03 |
Pos logit contributions | |
dent | +0.028 |
impact | +0.023 |
regret | +0.022 |
ivering | +0.022 |
need | +0.021 |
Neg logit contributions | |
aro | -0.034 |
beans | -0.034 |
chers | -0.032 |
cr | -0.031 |
tickets | -0.031 |
Token | soared |
Token ID | 35292 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
dent | +0.013 |
regret | +0.011 |
impact | +0.011 |
need | +0.011 |
ivering | +0.010 |
Neg logit contributions | |
beans | -0.017 |
aro | -0.017 |
chers | -0.016 |
suits | -0.015 |
tickets | -0.015 |
Token | high |
Token ID | 1029 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
dent | +0.019 |
regret | +0.016 |
impact | +0.016 |
need | +0.016 |
ivering | +0.015 |
Neg logit contributions | |
aro | -0.020 |
beans | -0.019 |
chers | -0.018 |
mons | -0.018 |
cakes | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
aro | +0.020 |
beans | +0.020 |
chers | +0.019 |
tickets | +0.018 |
suits | +0.018 |
Neg logit contributions | |
dent | -0.024 |
impact | -0.020 |
regret | -0.020 |
need | -0.020 |
ivering | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
aro | +0.003 |
beans | +0.002 |
tickets | +0.002 |
poles | +0.002 |
Off | +0.002 |
Neg logit contributions | |
dent | -0.005 |
ivering | -0.005 |
impact | -0.005 |
regret | -0.005 |
need | -0.005 |
Token | sky |
Token ID | 6766 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
dent | +0.008 |
regret | +0.007 |
ivering | +0.007 |
impact | +0.007 |
hurting | +0.006 |
Neg logit contributions | |
da | -0.009 |
suits | -0.009 |
fl | -0.009 |
poles | -0.009 |
tickets | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
dent | +0.049 |
regret | +0.042 |
impact | +0.041 |
need | +0.039 |
ivering | +0.039 |
Neg logit contributions | |
beans | -0.055 |
aro | -0.053 |
chers | -0.050 |
cr | -0.050 |
fl | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | +7.20e-03 |
Pos logit contributions | |
dent | +0.007 |
impact | +0.006 |
ivering | +0.006 |
regret | +0.006 |
need | +0.006 |
Neg logit contributions | |
aro | -0.010 |
beans | -0.010 |
chers | -0.009 |
Off | -0.009 |
suits | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
beans | +0.012 |
aro | +0.011 |
cakes | +0.011 |
mons | +0.011 |
resp | +0.011 |
Neg logit contributions | |
dent | -0.012 |
regret | -0.011 |
need | -0.010 |
impact | -0.010 |
pain | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
dent | +0.037 |
impact | +0.033 |
regret | +0.031 |
ivering | +0.031 |
need | +0.031 |
Neg logit contributions | |
aro | -0.033 |
beans | -0.033 |
chers | -0.031 |
tickets | -0.030 |
Off | -0.029 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
aro | +0.002 |
beans | +0.002 |
chers | +0.002 |
Off | +0.002 |
suits | +0.002 |
Neg logit contributions | |
dent | -0.002 |
impact | -0.002 |
regret | -0.002 |
ivering | -0.002 |
need | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
beans | +0.004 |
aro | +0.004 |
chers | +0.004 |
suits | +0.004 |
tickets | +0.004 |
Neg logit contributions | |
dent | -0.003 |
impact | -0.003 |
regret | -0.003 |
need | -0.002 |
ivering | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
beans | +0.027 |
aro | +0.026 |
chers | +0.024 |
suits | +0.024 |
cakes | +0.024 |
Neg logit contributions | |
dent | -0.016 |
regret | -0.013 |
need | -0.013 |
impact | -0.013 |
ivering | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
dent | +0.002 |
regret | +0.001 |
impact | +0.001 |
need | +0.001 |
ivering | +0.001 |
Neg logit contributions | |
beans | -0.003 |
aro | -0.003 |
chers | -0.003 |
suits | -0.003 |
tickets | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
dent | +0.021 |
regret | +0.018 |
impact | +0.017 |
need | +0.017 |
ivering | +0.017 |
Neg logit contributions | |
beans | -0.031 |
suits | -0.030 |
aro | -0.030 |
mons | -0.029 |
bags | -0.029 |
Token | End |
Token ID | 5268 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
beans | +0.016 |
aro | +0.016 |
chers | +0.015 |
suits | +0.014 |
tickets | +0.014 |
Neg logit contributions | |
dent | -0.023 |
regret | -0.020 |
impact | -0.020 |
need | -0.020 |
ivering | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
beans | +0.016 |
aro | +0.016 |
chers | +0.015 |
mons | +0.015 |
bags | +0.015 |
Neg logit contributions | |
dent | -0.007 |
need | -0.006 |
regret | -0.006 |
impact | -0.006 |
pain | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
dent | +0.035 |
regret | +0.029 |
impact | +0.029 |
need | +0.028 |
ivering | +0.027 |
Neg logit contributions | |
beans | -0.049 |
aro | -0.049 |
chers | -0.046 |
suits | -0.045 |
tickets | -0.045 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
dent | +0.006 |
regret | +0.005 |
impact | +0.005 |
need | +0.005 |
ivering | +0.005 |
Neg logit contributions | |
beans | -0.004 |
aro | -0.004 |
chers | -0.004 |
suits | -0.004 |
tickets | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
aro | +0.009 |
beans | +0.009 |
chers | +0.008 |
tickets | +0.008 |
suits | +0.008 |
Neg logit contributions | |
dent | -0.011 |
impact | -0.010 |
regret | -0.010 |
ivering | -0.010 |
need | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
beans | +0.012 |
aro | +0.012 |
chers | +0.011 |
tickets | +0.011 |
suits | +0.011 |
Neg logit contributions | |
dent | -0.022 |
impact | -0.020 |
regret | -0.020 |
need | -0.019 |
ivering | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
beans | +0.042 |
suits | +0.040 |
aro | +0.040 |
apr | +0.039 |
tickets | +0.039 |
Neg logit contributions | |
dent | -0.028 |
regret | -0.021 |
impact | -0.021 |
ivering | -0.020 |
need | -0.019 |