Token | � |
Token ID | 95 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ww | +0.018 |
www | +0.016 |
heart | +0.014 |
?" | +0.014 |
mber | +0.014 |
Neg logit contributions | |
bank | -0.015 |
banks | -0.014 |
allowance | -0.013 |
isc | -0.012 |
ro | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ww | +0.052 |
www | +0.045 |
heart | +0.041 |
ons | +0.041 |
mber | +0.040 |
Neg logit contributions | |
bank | -0.043 |
banks | -0.041 |
allowance | -0.038 |
ro | -0.035 |
isc | -0.035 |
Token | � |
Token ID | 129 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bank | +0.043 |
banks | +0.041 |
allowance | +0.039 |
isc | +0.037 |
ro | +0.036 |
Neg logit contributions | |
ww | -0.055 |
www | -0.048 |
heart | -0.047 |
igator | -0.045 |
loo | -0.044 |
Token | � |
Token ID | 241 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
bank | +0.024 |
allowance | +0.023 |
banks | +0.022 |
usual | +0.020 |
isc | +0.019 |
Neg logit contributions | |
ww | -0.028 |
www | -0.026 |
?" | -0.022 |
heart | -0.022 |
mber | -0.022 |
Token | A |
Token ID | 32 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
ons | +0.003 |
heart | +0.003 |
loo | +0.003 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.004 |
allowance | -0.004 |
ro | -0.004 |
isc | -0.004 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
bank | +0.035 |
banks | +0.031 |
allowance | +0.030 |
ro | +0.028 |
ork | +0.028 |
Neg logit contributions | |
ww | -0.041 |
ons | -0.038 |
heart | -0.036 |
www | -0.035 |
loo | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ww | +0.259 |
ull | +0.255 |
loo | +0.243 |
igator | +0.236 |
www | +0.229 |
Neg logit contributions | |
bank | -0.167 |
banks | -0.157 |
allowance | -0.154 |
ro | -0.138 |
isc | -0.137 |
Token | okay |
Token ID | 8788 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
ww | +0.018 |
www | +0.016 |
ons | +0.016 |
loo | +0.015 |
heart | +0.014 |
Neg logit contributions | |
bank | -0.017 |
allowance | -0.016 |
banks | -0.016 |
ro | -0.015 |
isc | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
anymore | +0.017 |
bank | +0.017 |
ro | +0.016 |
yet | +0.016 |
allowance | +0.016 |
Neg logit contributions | |
ons | -0.013 |
ww | -0.013 |
course | -0.011 |
loo | -0.011 |
orn | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
bank | +0.008 |
banks | +0.008 |
allowance | +0.008 |
isc | +0.007 |
ro | +0.007 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
ons | -0.007 |
heart | -0.007 |
loo | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ww | +0.077 |
www | +0.066 |
ons | +0.065 |
heart | +0.064 |
ins | +0.063 |
Neg logit contributions | |
bank | -0.049 |
banks | -0.046 |
ro | -0.040 |
allowance | -0.039 |
symp | -0.037 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
ww | +0.019 |
www | +0.017 |
mber | +0.017 |
heart | +0.017 |
very | +0.016 |
Neg logit contributions | |
bank | -0.016 |
find | -0.015 |
banks | -0.014 |
ro | -0.014 |
anymore | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
ww | +0.024 |
www | +0.021 |
heart | +0.020 |
ons | +0.019 |
loo | +0.019 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.010 |
ro | -0.010 |
symp | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
ww | +0.014 |
www | +0.012 |
heart | +0.011 |
mber | +0.011 |
ons | +0.011 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
symp | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
ww | +0.011 |
www | +0.009 |
heart | +0.009 |
ons | +0.008 |
loo | +0.008 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.012 |
ro | -0.011 |
allowance | -0.010 |
tted | -0.010 |
Token | A |
Token ID | 32 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
heart | +0.007 |
ons | +0.007 |
loo | +0.007 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
ro | -0.007 |
allowance | -0.006 |
symp | -0.006 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
bank | +0.017 |
ro | +0.015 |
allowance | +0.014 |
banks | +0.014 |
long | +0.014 |
Neg logit contributions | |
ons | -0.035 |
ries | -0.035 |
ins | -0.032 |
loo | -0.032 |
ions | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ww | +0.290 |
ull | +0.288 |
igator | +0.280 |
Charlie | +0.275 |
John | +0.275 |
Neg logit contributions | |
bank | -0.120 |
banks | -0.108 |
allowance | -0.102 |
isc | -0.095 |
ro | -0.091 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ww | +0.024 |
www | +0.021 |
heart | +0.020 |
ons | +0.019 |
loo | +0.019 |
Neg logit contributions | |
bank | -0.019 |
banks | -0.018 |
allowance | -0.018 |
ro | -0.016 |
symp | -0.015 |
Token | says |
Token ID | 1139 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
ww | +0.019 |
www | +0.016 |
loo | +0.015 |
heart | +0.014 |
ons | +0.013 |
Neg logit contributions | |
bank | -0.022 |
banks | -0.022 |
allowance | -0.019 |
ro | -0.019 |
symp | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
ww | +0.005 |
?" | +0.004 |
www | +0.004 |
? | +0.004 |
heart | +0.004 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
isc | -0.004 |
uries | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
heart | +0.009 |
ons | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.006 |
ro | -0.006 |
symp | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-03 |
Pos logit contributions | |
ww | +0.018 |
www | +0.017 |
mber | +0.016 |
heart | +0.016 |
very | +0.016 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.006 |
ro | -0.005 |
allowance | -0.005 |
until | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.14e-04 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.002 |
isc | +0.002 |
Neg logit contributions | |
ww | -0.005 |
www | -0.005 |
heart | -0.005 |
ons | -0.004 |
loo | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-04 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.001 |
mber | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
ww | +0.000 |
heart | +0.000 |
www | +0.000 |
loo | +0.000 |
mber | +0.000 |
Neg logit contributions | |
banks | -0.000 |
bank | -0.000 |
allowance | -0.000 |
ro | -0.000 |
side | -0.000 |
Token | A |
Token ID | 32 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.002 |
symp | +0.002 |
Neg logit contributions | |
ww | -0.002 |
heart | -0.002 |
www | -0.002 |
ons | -0.002 |
loo | -0.002 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.020 |
allowance | +0.020 |
ro | +0.019 |
long | +0.019 |
Neg logit contributions | |
ons | -0.045 |
ries | -0.044 |
loo | -0.043 |
ins | -0.042 |
ined | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
ww | +0.287 |
igator | +0.278 |
ull | +0.278 |
mber | +0.275 |
www | +0.273 |
Neg logit contributions | |
bank | -0.108 |
banks | -0.100 |
allowance | -0.090 |
isc | -0.082 |
ro | -0.080 |
Token | it |
Token ID | 340 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
heart | +0.011 |
ons | +0.011 |
ins | +0.010 |
Neg logit contributions | |
bank | -0.009 |
allowance | -0.008 |
banks | -0.008 |
seem | -0.007 |
symp | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ww | +0.008 |
www | +0.008 |
heart | +0.007 |
mber | +0.007 |
very | +0.007 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.007 |
allowance | -0.006 |
seem | -0.006 |
ro | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
ww | +0.038 |
www | +0.035 |
heart | +0.034 |
loo | +0.032 |
mber | +0.032 |
Neg logit contributions | |
bank | -0.025 |
banks | -0.024 |
allowance | -0.022 |
usual | -0.020 |
isc | -0.019 |
Token | cute |
Token ID | 13779 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
heart | +0.014 |
ww | +0.013 |
ons | +0.013 |
www | +0.013 |
course | +0.012 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.005 |
allowance | -0.005 |
usual | -0.005 |
ro | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ww | +0.012 |
www | +0.010 |
heart | +0.009 |
ons | +0.009 |
mber | +0.009 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | ground |
Token ID | 2323 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
ww | +0.022 |
www | +0.019 |
onion | +0.017 |
?" | +0.017 |
my | +0.017 |
Neg logit contributions | |
allowance | -0.021 |
bank | -0.019 |
banks | -0.019 |
symp | -0.019 |
isc | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-04 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
symp | +0.005 |
Neg logit contributions | |
ww | -0.012 |
www | -0.010 |
heart | -0.009 |
mber | -0.009 |
ons | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
ons | -0.001 |
heart | -0.001 |
loo | -0.001 |
Token | E |
Token ID | 36 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
bank | +0.036 |
banks | +0.034 |
allowance | +0.032 |
ro | +0.031 |
symp | +0.030 |
Neg logit contributions | |
ww | -0.037 |
www | -0.032 |
loo | -0.031 |
ons | -0.030 |
?" | -0.030 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.003 |
symp | +0.003 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
loo | -0.001 |
?" | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
ww | +0.255 |
ull | +0.234 |
www | +0.232 |
loo | +0.224 |
mber | +0.222 |
Neg logit contributions | |
bank | -0.162 |
banks | -0.153 |
allowance | -0.144 |
isc | -0.125 |
ro | -0.118 |
Token | what |
Token ID | 644 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ww | +0.014 |
www | +0.012 |
ons | +0.011 |
ins | +0.011 |
heart | +0.011 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.011 |
symp | -0.010 |
buy | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
ww | +0.068 |
www | +0.063 |
loo | +0.059 |
heart | +0.058 |
very | +0.058 |
Neg logit contributions | |
seem | -0.029 |
allowance | -0.028 |
bank | -0.028 |
usual | -0.024 |
banks | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
bank | +0.004 |
allowance | +0.004 |
banks | +0.004 |
usual | +0.003 |
any | +0.003 |
Neg logit contributions | |
ww | -0.006 |
www | -0.006 |
mber | -0.006 |
heart | -0.005 |
loo | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
bank | +0.022 |
banks | +0.020 |
allowance | +0.018 |
seem | +0.018 |
isc | +0.017 |
Neg logit contributions | |
ww | -0.015 |
www | -0.013 |
ons | -0.013 |
loo | -0.012 |
mber | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
bank | +0.005 |
allowance | +0.005 |
banks | +0.005 |
isc | +0.005 |
urd | +0.005 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
heart | -0.004 |
?" | -0.004 |
ons | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
heart | +0.004 |
loo | +0.004 |
mber | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.004 |
ro | -0.003 |
symp | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.004 |
allowance | +0.003 |
ro | +0.003 |
symp | +0.003 |
Neg logit contributions | |
ww | -0.005 |
www | -0.005 |
heart | -0.004 |
mber | -0.004 |
ons | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
?" | +0.006 |
heart | +0.006 |
mber | +0.006 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.008 |
allowance | -0.007 |
isc | -0.007 |
ro | -0.007 |
Token | E |
Token ID | 36 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
bank | +0.037 |
banks | +0.036 |
allowance | +0.035 |
isc | +0.032 |
ro | +0.031 |
Neg logit contributions | |
ww | -0.035 |
www | -0.030 |
heart | -0.026 |
mber | -0.025 |
ons | -0.025 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.004 |
www | -0.004 |
heart | -0.004 |
mber | -0.003 |
ons | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
ww | +0.272 |
www | +0.250 |
mber | +0.237 |
heart | +0.230 |
ull | +0.229 |
Neg logit contributions | |
bank | -0.159 |
banks | -0.153 |
allowance | -0.145 |
isc | -0.127 |
ro | -0.124 |
Token | Bruno |
Token ID | 31045 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.005 |
ons | +0.005 |
mber | +0.005 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
bank | +0.022 |
banks | +0.020 |
allowance | +0.018 |
ro | +0.016 |
isc | +0.016 |
Neg logit contributions | |
ww | -0.040 |
www | -0.036 |
heart | -0.034 |
mber | -0.034 |
ons | -0.033 |
Token | You |
Token ID | 921 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.013 |
allowance | +0.013 |
isc | +0.012 |
ro | +0.012 |
Neg logit contributions | |
ww | -0.014 |
www | -0.012 |
mber | -0.011 |
heart | -0.011 |
ons | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ww | +0.017 |
www | +0.015 |
?" | +0.014 |
ons | +0.014 |
heart | +0.014 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.011 |
allowance | -0.010 |
symp | -0.009 |
ro | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ww | +0.073 |
www | +0.065 |
?" | +0.060 |
heart | +0.059 |
ons | +0.057 |
Neg logit contributions | |
bank | -0.047 |
banks | -0.045 |
allowance | -0.042 |
isc | -0.039 |
symp | -0.038 |
Token | bitter |
Token ID | 12922 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.017 |
allowance | +0.017 |
ro | +0.015 |
usual | +0.015 |
Neg logit contributions | |
ww | -0.024 |
www | -0.022 |
loo | -0.019 |
mber | -0.019 |
heart | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.013 |
allowance | +0.012 |
isc | +0.011 |
symp | +0.011 |
Neg logit contributions | |
ww | -0.022 |
www | -0.019 |
?" | -0.018 |
heart | -0.018 |
ons | -0.017 |
Token | like |
Token ID | 588 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.001 |
isc | +0.001 |
ro | +0.001 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
heart | -0.002 |
?" | -0.002 |
ons | -0.002 |
Token | e |
Token ID | 304 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
bank | +0.051 |
allowance | +0.049 |
banks | +0.048 |
usual | +0.045 |
ro | +0.043 |
Neg logit contributions | |
ww | -0.054 |
www | -0.049 |
mber | -0.044 |
heart | -0.044 |
loo | -0.042 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
bank | +0.032 |
banks | +0.031 |
allowance | +0.029 |
symp | +0.028 |
ro | +0.027 |
Neg logit contributions | |
ww | -0.023 |
www | -0.020 |
mber | -0.018 |
loo | -0.017 |
igator | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
ww | +0.246 |
www | +0.220 |
mber | +0.199 |
heart | +0.199 |
loo | +0.194 |
Neg logit contributions | |
bank | -0.193 |
banks | -0.186 |
allowance | -0.177 |
ro | -0.157 |
isc | -0.152 |
Token | Do |
Token ID | 2141 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.004 |
allowance | +0.004 |
isc | +0.004 |
ro | +0.004 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
heart | -0.004 |
ons | -0.004 |
mber | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -5.51e-03 |
Pos logit contributions | |
ww | +0.036 |
www | +0.030 |
heart | +0.027 |
loo | +0.027 |
mber | +0.025 |
Neg logit contributions | |
bank | -0.064 |
allowance | -0.062 |
banks | -0.061 |
usual | -0.057 |
seem | -0.057 |
Token | want |
Token ID | 765 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.006 |
isc | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.012 |
www | -0.011 |
?" | -0.010 |
heart | -0.010 |
ons | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
ww | +0.026 |
www | +0.024 |
heart | +0.023 |
mber | +0.022 |
loo | +0.022 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.007 |
allowance | -0.007 |
usual | -0.006 |
ro | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.019 |
www | -0.017 |
heart | -0.016 |
?" | -0.016 |
ons | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
ww | +0.052 |
www | +0.046 |
mber | +0.042 |
heart | +0.041 |
ons | +0.040 |
Neg logit contributions | |
bank | -0.034 |
banks | -0.032 |
allowance | -0.030 |
usual | -0.026 |
ro | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ww | +0.005 |
www | +0.005 |
heart | +0.004 |
mber | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.002 |
ro | -0.002 |
usual | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.018 |
allowance | +0.017 |
ro | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.023 |
www | -0.021 |
heart | -0.018 |
ons | -0.018 |
mber | -0.018 |
Token | ew |
Token ID | 413 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
bank | +0.038 |
banks | +0.036 |
allowance | +0.034 |
ro | +0.031 |
isc | +0.031 |
Neg logit contributions | |
ww | -0.044 |
www | -0.039 |
heart | -0.035 |
ons | -0.034 |
mber | -0.034 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ww | +0.012 |
www | +0.010 |
loo | +0.010 |
mber | +0.009 |
heart | +0.009 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.012 |
ro | -0.010 |
allowance | -0.010 |
symp | -0.010 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
ww | +0.203 |
www | +0.180 |
loo | +0.171 |
heart | +0.166 |
ull | +0.162 |
Neg logit contributions | |
bank | -0.220 |
banks | -0.216 |
allowance | -0.197 |
ro | -0.184 |
isc | -0.183 |
Token | |
Token ID | 220 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ww | +0.018 |
www | +0.016 |
heart | +0.015 |
ons | +0.015 |
mber | +0.015 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.008 |
ro | -0.007 |
symp | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
bank | +0.031 |
banks | +0.030 |
allowance | +0.028 |
ro | +0.025 |
isc | +0.025 |
Neg logit contributions | |
ww | -0.039 |
www | -0.034 |
heart | -0.031 |
ons | -0.031 |
?" | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
ww | +0.003 |
www | +0.003 |
heart | +0.003 |
loo | +0.002 |
ons | +0.002 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.001 |
ro | -0.001 |
usual | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
heart | +0.004 |
loo | +0.004 |
ons | +0.003 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
ro | -0.002 |
side | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.011 |
isc | +0.009 |
ro | +0.009 |
Neg logit contributions | |
ww | -0.017 |
www | -0.015 |
heart | -0.014 |
ons | -0.014 |
?" | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
ww | +0.014 |
www | +0.012 |
loo | +0.011 |
ons | +0.011 |
mber | +0.010 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.010 |
allowance | -0.010 |
symp | -0.009 |
usual | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
heart | +0.004 |
?" | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.004 |
isc | -0.004 |
ro | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ww | +0.020 |
www | +0.018 |
heart | +0.016 |
ons | +0.016 |
mber | +0.015 |
Neg logit contributions | |
bank | -0.017 |
banks | -0.016 |
allowance | -0.015 |
ro | -0.014 |
isc | -0.014 |
Token | A |
Token ID | 32 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
bank | +0.025 |
banks | +0.024 |
allowance | +0.023 |
ro | +0.021 |
isc | +0.021 |
Neg logit contributions | |
ww | -0.023 |
www | -0.020 |
ons | -0.018 |
heart | -0.018 |
loo | -0.017 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bank | +0.033 |
banks | +0.032 |
allowance | +0.030 |
ro | +0.027 |
isc | +0.027 |
Neg logit contributions | |
ww | -0.046 |
www | -0.041 |
ons | -0.040 |
heart | -0.039 |
mber | -0.038 |
Token | www |
Token ID | 2503 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
ww | +0.244 |
ull | +0.232 |
igator | +0.225 |
www | +0.222 |
loo | +0.218 |
Neg logit contributions | |
bank | -0.150 |
banks | -0.146 |
allowance | -0.139 |
ro | -0.130 |
isc | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
ww | +0.111 |
www | +0.098 |
mber | +0.091 |
loo | +0.088 |
igator | +0.087 |
Neg logit contributions | |
bank | -0.091 |
banks | -0.087 |
allowance | -0.083 |
isc | -0.079 |
ro | -0.078 |
Token | do |
Token ID | 466 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
ons | +0.013 |
ins | +0.013 |
loo | +0.013 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.013 |
allowance | -0.012 |
isc | -0.012 |
symp | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ww | +0.029 |
www | +0.025 |
heart | +0.024 |
loo | +0.024 |
mber | +0.023 |
Neg logit contributions | |
bank | -0.036 |
banks | -0.035 |
allowance | -0.033 |
seem | -0.031 |
usual | -0.030 |
Token | have |
Token ID | 423 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ww | +0.037 |
www | +0.033 |
heart | +0.030 |
?" | +0.030 |
ons | +0.029 |
Neg logit contributions | |
bank | -0.024 |
banks | -0.023 |
allowance | -0.021 |
ro | -0.019 |
isc | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.66e-04 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.020 |
allowance | +0.019 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.031 |
www | -0.027 |
heart | -0.025 |
ons | -0.025 |
?" | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
heart | +0.001 |
ons | +0.001 |
mber | +0.001 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.001 |
ro | -0.001 |
isc | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
ons | +0.007 |
heart | +0.007 |
?" | +0.007 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.006 |
ro | -0.006 |
isc | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
ww | +0.010 |
www | +0.008 |
heart | +0.008 |
ons | +0.007 |
loo | +0.007 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.008 |
ro | -0.007 |
symp | -0.007 |
Token | E |
Token ID | 36 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.002 |
ro | +0.002 |
symp | +0.002 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
loo | -0.002 |
?" | -0.002 |
ons | -0.002 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bank | +0.008 |
banks | +0.007 |
allowance | +0.007 |
ro | +0.007 |
isc | +0.007 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
loo | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
ww | +0.246 |
ull | +0.225 |
www | +0.224 |
loo | +0.222 |
igator | +0.220 |
Neg logit contributions | |
bank | -0.162 |
banks | -0.155 |
allowance | -0.146 |
isc | -0.130 |
ro | -0.126 |
Token | she |
Token ID | 673 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
heart | +0.007 |
loo | +0.007 |
ons | +0.007 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.011 |
ro | -0.010 |
isc | -0.010 |
Token | screamed |
Token ID | 25421 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.015 |
ro | +0.014 |
isc | +0.014 |
Neg logit contributions | |
ww | -0.013 |
www | -0.011 |
loo | -0.010 |
heart | -0.010 |
ons | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
ww | +0.022 |
heart | +0.021 |
?" | +0.021 |
? | +0.021 |
www | +0.019 |
Neg logit contributions | |
bank | -0.030 |
banks | -0.030 |
allowance | -0.028 |
isc | -0.027 |
tted | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.004 |
allowance | +0.004 |
isc | +0.003 |
ro | +0.003 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
heart | -0.004 |
mber | -0.004 |
ons | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
heart | +0.004 |
mber | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
ro | -0.003 |
isc | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
ww | +0.014 |
www | +0.013 |
loo | +0.012 |
heart | +0.012 |
ons | +0.011 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.008 |
ro | -0.008 |
symp | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.002 |
symp | +0.002 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
heart | -0.004 |
mber | -0.004 |
ons | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
heart | +0.009 |
ons | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.008 |
allowance | -0.008 |
ro | -0.007 |
isc | -0.007 |
Token | E |
Token ID | 36 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
bank | +0.036 |
banks | +0.034 |
allowance | +0.031 |
ro | +0.031 |
symp | +0.030 |
Neg logit contributions | |
ww | -0.031 |
www | -0.027 |
loo | -0.025 |
ons | -0.025 |
heart | -0.025 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.003 |
isc | +0.003 |
Neg logit contributions | |
ww | -0.001 |
heart | -0.001 |
www | -0.001 |
mber | -0.001 |
loo | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
ww | +0.270 |
www | +0.255 |
igator | +0.250 |
ull | +0.245 |
mber | +0.245 |
Neg logit contributions | |
bank | -0.127 |
allowance | -0.123 |
banks | -0.119 |
isc | -0.108 |
ro | -0.103 |
Token | disgusting |
Token ID | 23374 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
heart | +0.007 |
mber | +0.007 |
ons | +0.007 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.007 |
symp | -0.006 |
isc | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.49e-03 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
mber | +0.007 |
John | +0.007 |
very | +0.007 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.008 |
ro | -0.007 |
bottom | -0.007 |
anymore | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ww | +0.012 |
www | +0.011 |
heart | +0.010 |
ons | +0.010 |
mber | +0.009 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.010 |
allowance | -0.009 |
ro | -0.009 |
isc | -0.008 |
Token | threw |
Token ID | 9617 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
ww | +0.021 |
www | +0.019 |
loo | +0.018 |
heart | +0.018 |
mber | +0.016 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.013 |
allowance | -0.012 |
ro | -0.012 |
ked | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-04 |
Pos logit contributions | |
ww | +0.029 |
www | +0.026 |
heart | +0.023 |
mber | +0.023 |
ons | +0.023 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.013 |
allowance | -0.011 |
ro | -0.010 |
usual | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
heart | +0.001 |
ons | +0.001 |
loo | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
ro | -0.001 |
isc | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
heart | +0.013 |
ons | +0.013 |
mber | +0.013 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.010 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | -7.57e-04 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
loo | +0.013 |
ons | +0.013 |
heart | +0.013 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.010 |
ro | -0.010 |
symp | -0.010 |
Token | E |
Token ID | 36 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
symp | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.001 |
loo | -0.001 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.003 |
isc | +0.002 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.001 |
mber | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
ww | +0.270 |
www | +0.247 |
ull | +0.240 |
igator | +0.234 |
loo | +0.234 |
Neg logit contributions | |
bank | -0.141 |
banks | -0.135 |
allowance | -0.122 |
isc | -0.108 |
ro | -0.106 |
Token | this |
Token ID | 428 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ww | +0.018 |
www | +0.016 |
ons | +0.015 |
ins | +0.015 |
heart | +0.014 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.012 |
buy | -0.011 |
seem | -0.011 |
Token | fish |
Token ID | 5916 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
bank | +0.061 |
banks | +0.057 |
allowance | +0.048 |
bottom | +0.047 |
ro | +0.045 |
Neg logit contributions | |
ww | -0.051 |
www | -0.046 |
heart | -0.044 |
ons | -0.043 |
imi | -0.043 |
Token | is |
Token ID | 318 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.016 |
find | +0.014 |
allowance | +0.013 |
ro | +0.013 |
Neg logit contributions | |
ww | -0.022 |
www | -0.019 |
mber | -0.019 |
Charlie | -0.019 |
John | -0.018 |
Token | sm |
Token ID | 895 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
ww | +0.039 |
www | +0.036 |
heart | +0.034 |
mber | +0.033 |
ons | +0.033 |
Neg logit contributions | |
bank | -0.024 |
banks | -0.023 |
allowance | -0.020 |
usual | -0.019 |
properly | -0.017 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ww | +0.028 |
www | +0.025 |
heart | +0.023 |
ons | +0.023 |
loo | +0.022 |
Neg logit contributions | |
bank | -0.014 |
allowance | -0.013 |
banks | -0.013 |
isc | -0.011 |
usual | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
ww | +0.060 |
www | +0.052 |
loo | +0.046 |
ons | +0.046 |
heart | +0.045 |
Neg logit contributions | |
bank | -0.047 |
banks | -0.044 |
allowance | -0.039 |
symp | -0.037 |
ro | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
heart | +0.009 |
ons | +0.009 |
?" | +0.009 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.009 |
isc | -0.008 |
ro | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
loo | +0.013 |
ons | +0.013 |
heart | +0.013 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.008 |
allowance | -0.007 |
symp | -0.007 |
ro | -0.007 |
Token | A |
Token ID | 32 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
ro | +0.017 |
bank | +0.017 |
side | +0.016 |
banks | +0.015 |
tted | +0.015 |
Neg logit contributions | |
ww | -0.028 |
?" | -0.026 |
loo | -0.026 |
ons | -0.025 |
www | -0.025 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
bank | +0.031 |
allowance | +0.027 |
ro | +0.026 |
banks | +0.026 |
ork | +0.025 |
Neg logit contributions | |
ons | -0.034 |
ins | -0.033 |
ries | -0.033 |
heart | -0.032 |
ww | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
ww | +0.265 |
www | +0.245 |
mber | +0.238 |
ull | +0.237 |
igator | +0.232 |
Neg logit contributions | |
bank | -0.145 |
banks | -0.134 |
allowance | -0.130 |
ro | -0.117 |
isc | -0.114 |
Token | okay |
Token ID | 8788 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
ons | +0.006 |
ins | +0.006 |
ined | +0.006 |
Neg logit contributions | |
bank | -0.006 |
allowance | -0.005 |
banks | -0.005 |
buy | -0.005 |
ro | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
anymore | +0.016 |
bank | +0.014 |
banks | +0.013 |
any | +0.013 |
properly | +0.013 |
Neg logit contributions | |
ww | -0.037 |
ons | -0.034 |
www | -0.034 |
mber | -0.032 |
orn | -0.031 |
Token | But |
Token ID | 887 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.007 |
ro | +0.007 |
isc | +0.007 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
ons | -0.006 |
heart | -0.006 |
mber | -0.006 |
Token | come |
Token ID | 1282 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
bank | +0.028 |
banks | +0.027 |
allowance | +0.026 |
usual | +0.024 |
ro | +0.023 |
Neg logit contributions | |
ww | -0.036 |
www | -0.032 |
ons | -0.029 |
mber | -0.029 |
heart | -0.028 |
Token | € |
Token ID | 26391 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
ww | +0.078 |
www | +0.069 |
ons | +0.064 |
heart | +0.063 |
mber | +0.063 |
Neg logit contributions | |
bank | -0.051 |
banks | -0.049 |
ro | -0.043 |
allowance | -0.043 |
isc | -0.041 |
Token | ™ |
Token ID | 8151 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
bank | +0.047 |
banks | +0.045 |
allowance | +0.043 |
ro | +0.042 |
isc | +0.041 |
Neg logit contributions | |
ww | -0.060 |
www | -0.053 |
heart | -0.052 |
loo | -0.048 |
ons | -0.048 |
Token | s |
Token ID | 82 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
bank | +0.058 |
banks | +0.055 |
allowance | +0.052 |
ro | +0.046 |
isc | +0.045 |
Neg logit contributions | |
ww | -0.089 |
www | -0.079 |
heart | -0.072 |
ons | -0.071 |
mber | -0.070 |
Token | okay |
Token ID | 8788 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
ons | +0.006 |
mber | +0.006 |
loo | +0.005 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.004 |
ro | -0.004 |
isc | -0.004 |
Token | sweet |
Token ID | 6029 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
symp | +0.005 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
ons | -0.010 |
loo | -0.009 |
course | -0.009 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ww | +0.037 |
www | +0.029 |
ons | +0.029 |
Charlie | +0.027 |
loo | +0.025 |
Neg logit contributions | |
bank | -0.089 |
ro | -0.086 |
banks | -0.085 |
allowance | -0.082 |
isc | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
ww | +0.269 |
www | +0.236 |
loo | +0.223 |
ons | +0.220 |
mber | +0.218 |
Neg logit contributions | |
bank | -0.163 |
banks | -0.146 |
allowance | -0.143 |
ro | -0.134 |
seem | -0.125 |
Token | How |
Token ID | 1374 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.013 |
allowance | +0.012 |
ro | +0.012 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.018 |
www | -0.016 |
ons | -0.015 |
loo | -0.014 |
w | -0.014 |
Token | about |
Token ID | 546 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.009 |
allowance | +0.008 |
isc | +0.008 |
ro | +0.008 |
Neg logit contributions | |
ww | -0.010 |
www | -0.009 |
heart | -0.008 |
?" | -0.008 |
ons | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
loo | +0.005 |
mber | +0.005 |
heart | +0.005 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
usual | -0.004 |
buy | -0.004 |
Token | give |
Token ID | 1577 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ww | +0.038 |
www | +0.034 |
ons | +0.031 |
heart | +0.031 |
mber | +0.031 |
Neg logit contributions | |
bank | -0.021 |
banks | -0.019 |
allowance | -0.018 |
ro | -0.016 |
isc | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
heart | +0.002 |
ons | +0.001 |
loo | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
ro | -0.001 |
isc | -0.001 |
Token | says |
Token ID | 1139 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
ww | +0.012 |
www | +0.010 |
heart | +0.009 |
loo | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.014 |
allowance | -0.013 |
ro | -0.012 |
symp | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
heart | +0.013 |
mber | +0.013 |
loo | +0.012 |
Neg logit contributions | |
bank | -0.008 |
allowance | -0.007 |
banks | -0.007 |
ro | -0.006 |
anymore | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
heart | +0.013 |
ons | +0.013 |
mber | +0.012 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.011 |
ro | -0.010 |
isc | -0.010 |
Token | A |
Token ID | 32 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
bank | +0.034 |
banks | +0.032 |
allowance | +0.031 |
ro | +0.029 |
isc | +0.028 |
Neg logit contributions | |
ww | -0.033 |
www | -0.029 |
heart | -0.027 |
ons | -0.026 |
?" | -0.025 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
bank | +0.038 |
allowance | +0.036 |
ork | +0.033 |
banks | +0.032 |
loudspe | +0.031 |
Neg logit contributions | |
heart | -0.038 |
ww | -0.037 |
www | -0.034 |
loo | -0.034 |
imi | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
ww | +0.256 |
igator | +0.248 |
ull | +0.247 |
mber | +0.246 |
www | +0.242 |
Neg logit contributions | |
bank | -0.125 |
allowance | -0.116 |
banks | -0.111 |
isc | -0.103 |
ro | -0.101 |
Token | this |
Token ID | 428 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
ww | +0.012 |
www | +0.011 |
heart | +0.010 |
mber | +0.009 |
ons | +0.009 |
Neg logit contributions | |
bank | -0.010 |
allowance | -0.010 |
banks | -0.009 |
ro | -0.009 |
symp | -0.009 |
Token | is |
Token ID | 318 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
bank | +0.049 |
allowance | +0.045 |
banks | +0.043 |
ork | +0.040 |
isc | +0.037 |
Neg logit contributions | |
ww | -0.049 |
heart | -0.047 |
www | -0.045 |
mber | -0.043 |
Andy | -0.041 |
Token | from |
Token ID | 422 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ww | +0.036 |
www | +0.033 |
heart | +0.032 |
mber | +0.030 |
loo | +0.029 |
Neg logit contributions | |
bank | -0.033 |
allowance | -0.033 |
banks | -0.030 |
usual | -0.030 |
isc | -0.028 |
Token | Anna |
Token ID | 11735 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
bank | +0.077 |
allowance | +0.073 |
banks | +0.071 |
usual | +0.068 |
ro | +0.065 |
Neg logit contributions | |
ww | -0.053 |
www | -0.045 |
heart | -0.041 |
mber | -0.040 |
loo | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | +4.26e-04 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.002 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
w | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
loo | +0.001 |
heart | +0.001 |
ons | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
widened | -0.001 |
ro | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
bank | +0.011 |
banks | +0.010 |
allowance | +0.010 |
symp | +0.009 |
ro | +0.009 |
Neg logit contributions | |
ww | -0.020 |
www | -0.018 |
heart | -0.017 |
mber | -0.016 |
ons | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
ro | +0.004 |
symp | +0.004 |
Neg logit contributions | |
ww | -0.007 |
www | -0.007 |
heart | -0.006 |
ons | -0.006 |
mber | -0.006 |
Token | E |
Token ID | 36 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
bank | +0.042 |
banks | +0.040 |
ro | +0.038 |
allowance | +0.037 |
side | +0.036 |
Neg logit contributions | |
ww | -0.044 |
www | -0.039 |
loo | -0.039 |
heart | -0.037 |
ons | -0.037 |
Token | ww |
Token ID | 1383 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.016 |
ro | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.008 |
heart | -0.007 |
www | -0.007 |
mber | -0.006 |
?" | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
ww | +0.269 |
www | +0.251 |
igator | +0.248 |
ull | +0.244 |
heart | +0.240 |
Neg logit contributions | |
bank | -0.126 |
allowance | -0.120 |
banks | -0.115 |
isc | -0.102 |
ro | -0.096 |
Token | this |
Token ID | 428 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
bank | +0.006 |
allowance | +0.005 |
buy | +0.005 |
seem | +0.005 |
banks | +0.005 |
Neg logit contributions | |
ww | -0.007 |
www | -0.007 |
heart | -0.006 |
ins | -0.006 |
ined | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
bank | +0.051 |
bottom | +0.043 |
allowance | +0.042 |
banks | +0.041 |
anymore | +0.040 |
Neg logit contributions | |
ww | -0.065 |
www | -0.059 |
heart | -0.058 |
Andy | -0.057 |
imi | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
ww | +0.022 |
www | +0.020 |
loo | +0.019 |
heart | +0.019 |
mber | +0.018 |
Neg logit contributions | |
bank | -0.012 |
allowance | -0.012 |
banks | -0.011 |
usual | -0.011 |
anymore | -0.011 |
Token | worst |
Token ID | 5290 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
heart | +0.010 |
mber | +0.010 |
ons | +0.010 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.011 |
allowance | -0.011 |
usual | -0.011 |
bottom | -0.010 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
bank | +0.043 |
banks | +0.041 |
allowance | +0.040 |
isc | +0.039 |
ro | +0.038 |
Neg logit contributions | |
ww | -0.053 |
www | -0.047 |
heart | -0.046 |
igator | -0.043 |
loo | -0.043 |
Token | s |
Token ID | 82 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
bank | +0.051 |
banks | +0.049 |
allowance | +0.046 |
isc | +0.043 |
ro | +0.042 |
Neg logit contributions | |
ww | -0.067 |
www | -0.059 |
heart | -0.053 |
mber | -0.052 |
loo | -0.052 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ww | +0.005 |
www | +0.005 |
ons | +0.004 |
loo | +0.004 |
mber | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
seem | -0.003 |
isc | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
ww | +0.026 |
ons | +0.024 |
loo | +0.023 |
www | +0.023 |
ined | +0.023 |
Neg logit contributions | |
bank | -0.016 |
allowance | -0.015 |
ro | -0.015 |
banks | -0.014 |
isc | -0.013 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
ww | +0.021 |
www | +0.018 |
ons | +0.018 |
loo | +0.018 |
rooms | +0.017 |
Neg logit contributions | |
bank | -0.016 |
allowance | -0.015 |
banks | -0.015 |
ro | -0.014 |
isc | -0.014 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ww | +0.025 |
ons | +0.019 |
www | +0.018 |
loo | +0.018 |
Charlie | +0.017 |
Neg logit contributions | |
bank | -0.066 |
ro | -0.064 |
banks | -0.064 |
isc | -0.064 |
allowance | -0.061 |
Token | ! |
Token ID | 0 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ww | +0.260 |
www | +0.224 |
loo | +0.214 |
imi | +0.214 |
ons | +0.210 |
Neg logit contributions | |
bank | -0.147 |
banks | -0.134 |
ro | -0.124 |
allowance | -0.122 |
until | -0.116 |
Token | Keep |
Token ID | 9175 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
ww | +0.027 |
www | +0.024 |
ons | +0.023 |
loo | +0.023 |
heart | +0.021 |
Neg logit contributions | |
bank | -0.018 |
banks | -0.017 |
allowance | -0.017 |
isc | -0.017 |
ro | -0.016 |
Token | spring |
Token ID | 6076 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ww | +0.070 |
www | +0.059 |
loo | +0.057 |
heart | +0.054 |
mber | +0.054 |
Neg logit contributions | |
bank | -0.054 |
banks | -0.051 |
allowance | -0.048 |
find | -0.045 |
until | -0.044 |
Token | ing |
Token ID | 278 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
bank | +0.031 |
banks | +0.030 |
allowance | +0.027 |
ro | +0.027 |
side | +0.024 |
Neg logit contributions | |
ww | -0.043 |
www | -0.038 |
mber | -0.034 |
ons | -0.034 |
loo | -0.034 |
Token | around |
Token ID | 1088 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
ww | +0.047 |
www | +0.043 |
mber | +0.039 |
loo | +0.039 |
ons | +0.038 |
Neg logit contributions | |
bank | -0.029 |
banks | -0.028 |
allowance | -0.025 |
ro | -0.024 |
symp | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ww | +0.077 |
ins | +0.066 |
www | +0.066 |
heart | +0.064 |
ons | +0.063 |
Neg logit contributions | |
bank | -0.049 |
banks | -0.045 |
ro | -0.044 |
tted | -0.039 |
allowance | -0.039 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
bank | +0.045 |
banks | +0.043 |
allowance | +0.043 |
isc | +0.041 |
ro | +0.039 |
Neg logit contributions | |
ww | -0.060 |
www | -0.053 |
heart | -0.052 |
igator | -0.049 |
course | -0.048 |
Token | s |
Token ID | 82 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
bank | +0.056 |
banks | +0.053 |
allowance | +0.050 |
isc | +0.045 |
symp | +0.045 |
Neg logit contributions | |
ww | -0.075 |
www | -0.066 |
heart | -0.060 |
mber | -0.058 |
ons | -0.057 |
Token | wrong |
Token ID | 2642 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
ww | +0.004 |
heart | +0.003 |
www | +0.003 |
mber | +0.003 |
ins | +0.003 |
Neg logit contributions | |
allowance | -0.002 |
bank | -0.002 |
banks | -0.002 |
seem | -0.002 |
usual | -0.002 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ww | +0.007 |
ons | +0.006 |
course | +0.006 |
www | +0.006 |
loo | +0.005 |
Neg logit contributions | |
bank | -0.014 |
allowance | -0.014 |
banks | -0.013 |
ro | -0.013 |
isc | -0.013 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ww | +0.041 |
Charlie | +0.038 |
Steve | +0.035 |
www | +0.035 |
Andy | +0.035 |
Neg logit contributions | |
ro | -0.043 |
bank | -0.042 |
isc | -0.042 |
allowance | -0.041 |
seem | -0.038 |
Token | ? |
Token ID | 30 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
ww | +0.155 |
www | +0.115 |
mber | +0.105 |
imi | +0.102 |
ins | +0.102 |
Neg logit contributions | |
bank | -0.244 |
find | -0.229 |
allowance | -0.229 |
seem | -0.227 |
banks | -0.223 |
Token | â |
Token ID | 22940 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ww | +0.075 |
www | +0.066 |
loo | +0.061 |
ons | +0.061 |
heart | +0.060 |
Neg logit contributions | |
bank | -0.051 |
allowance | -0.049 |
banks | -0.048 |
isc | -0.047 |
ro | -0.045 |
Token | € |
Token ID | 26391 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
ww | +0.087 |
www | +0.075 |
ins | +0.075 |
ons | +0.073 |
heart | +0.072 |
Neg logit contributions | |
bank | -0.046 |
banks | -0.043 |
ro | -0.039 |
isc | -0.035 |
symp | -0.035 |
Token | The |
Token ID | 383 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
bank | +0.043 |
banks | +0.041 |
allowance | +0.039 |
isc | +0.036 |
ro | +0.035 |
Neg logit contributions | |
ww | -0.061 |
www | -0.054 |
heart | -0.051 |
loo | -0.048 |
mber | -0.048 |
Token | little |
Token ID | 1310 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
allowance | +0.009 |
usual | +0.008 |
bottom | +0.008 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.009 |
ons | -0.009 |
mber | -0.009 |
Token | wait |
Token ID | 4043 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.004 |
www | -0.004 |
mber | -0.004 |
heart | -0.004 |
ons | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.009 |
allowance | +0.008 |
ro | +0.007 |
usual | +0.007 |
Neg logit contributions | |
ww | -0.018 |
www | -0.016 |
ons | -0.015 |
heart | -0.015 |
mber | -0.015 |
Token | line |
Token ID | 1627 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.006 |
allowance | +0.006 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
heart | -0.007 |
ons | -0.006 |
mber | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.019 |
allowance | +0.018 |
ro | +0.017 |
usual | +0.016 |
Neg logit contributions | |
ww | -0.024 |
www | -0.021 |
heart | -0.019 |
mber | -0.019 |
ons | -0.019 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
ons | +0.012 |
heart | +0.012 |
loo | +0.012 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ww | +0.026 |
www | +0.020 |
loo | +0.019 |
ons | +0.018 |
igator | +0.018 |
Neg logit contributions | |
bank | -0.057 |
banks | -0.056 |
allowance | -0.052 |
ro | -0.050 |
isc | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
ww | +0.236 |
www | +0.202 |
loo | +0.189 |
ons | +0.188 |
mber | +0.188 |
Neg logit contributions | |
bank | -0.171 |
banks | -0.158 |
allowance | -0.152 |
ro | -0.145 |
anymore | -0.138 |
Token | â |
Token ID | 22940 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.007 |
www | -0.006 |
ons | -0.006 |
heart | -0.005 |
loo | -0.005 |
Token | € |
Token ID | 26391 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ww | +0.077 |
www | +0.067 |
heart | +0.063 |
ons | +0.063 |
loo | +0.061 |
Neg logit contributions | |
bank | -0.048 |
banks | -0.046 |
allowance | -0.040 |
ro | -0.039 |
isc | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
bank | +0.046 |
banks | +0.044 |
allowance | +0.041 |
ro | +0.037 |
isc | +0.036 |
Neg logit contributions | |
ww | -0.058 |
www | -0.052 |
ons | -0.046 |
heart | -0.046 |
?" | -0.046 |
Token | then |
Token ID | 788 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
ww | +0.021 |
www | +0.018 |
loo | +0.018 |
heart | +0.017 |
ons | +0.017 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.013 |
allowance | -0.013 |
isc | -0.011 |
ro | -0.011 |
Token | � |
Token ID | 129 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
bank | +0.044 |
banks | +0.042 |
allowance | +0.040 |
isc | +0.038 |
ro | +0.036 |
Neg logit contributions | |
ww | -0.055 |
www | -0.048 |
heart | -0.047 |
igator | -0.043 |
mber | -0.043 |
Token | � |
Token ID | 241 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
bank | +0.025 |
allowance | +0.024 |
banks | +0.023 |
usual | +0.021 |
isc | +0.020 |
Neg logit contributions | |
ww | -0.030 |
www | -0.028 |
?" | -0.024 |
heart | -0.023 |
mber | -0.023 |
Token | Yes |
Token ID | 5297 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
ons | +0.006 |
heart | +0.005 |
loo | +0.005 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.007 |
ro | -0.007 |
usual | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +9.31e-03 |
Pos logit contributions | |
ww | +0.073 |
www | +0.063 |
ons | +0.061 |
loo | +0.059 |
mber | +0.058 |
Neg logit contributions | |
bank | -0.062 |
banks | -0.058 |
allowance | -0.056 |
isc | -0.051 |
ro | -0.051 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.013 |
ons | +0.013 |
loo | +0.013 |
heart | +0.012 |
Neg logit contributions | |
bank | -0.015 |
allowance | -0.015 |
banks | -0.014 |
ro | -0.014 |
isc | -0.013 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ww | +0.030 |
ons | +0.027 |
web | +0.026 |
Charlie | +0.026 |
loo | +0.025 |
Neg logit contributions | |
bank | -0.055 |
isc | -0.054 |
ro | -0.054 |
banks | -0.052 |
allowance | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +7.92e-03 |
Pos logit contributions | |
ww | +0.265 |
www | +0.231 |
mber | +0.228 |
ons | +0.225 |
loo | +0.223 |
Neg logit contributions | |
bank | -0.125 |
banks | -0.108 |
ro | -0.104 |
allowance | -0.103 |
anymore | -0.100 |
Token | it |
Token ID | 340 |
Feature activation | +9.62e-03 |
Pos logit contributions | |
ww | +0.013 |
www | +0.012 |
loo | +0.011 |
ons | +0.011 |
heart | +0.011 |
Neg logit contributions | |
bank | -0.013 |
allowance | -0.012 |
banks | -0.012 |
ro | -0.011 |
isc | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ww | +0.022 |
www | +0.019 |
loo | +0.019 |
mber | +0.018 |
ull | +0.018 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.010 |
seem | -0.009 |
chy | -0.009 |
allowance | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
ww | +0.076 |
ins | +0.067 |
www | +0.067 |
ons | +0.066 |
heart | +0.066 |
Neg logit contributions | |
bank | -0.045 |
banks | -0.040 |
ro | -0.039 |
tted | -0.037 |
isc | -0.035 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
bank | +0.043 |
banks | +0.041 |
allowance | +0.039 |
isc | +0.036 |
ro | +0.035 |
Neg logit contributions | |
ww | -0.062 |
www | -0.055 |
heart | -0.054 |
mber | -0.050 |
igator | -0.050 |
Token | � |
Token ID | 129 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
bank | +0.046 |
banks | +0.044 |
allowance | +0.042 |
ro | +0.038 |
isc | +0.037 |
Neg logit contributions | |
ww | -0.052 |
www | -0.045 |
ons | -0.040 |
?" | -0.040 |
heart | -0.040 |
Token | � |
Token ID | 241 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
allowance | +0.026 |
bank | +0.025 |
banks | +0.024 |
usual | +0.023 |
injuries | +0.023 |
Neg logit contributions | |
ww | -0.030 |
www | -0.028 |
?" | -0.024 |
my | -0.023 |
mber | -0.022 |
Token | No |
Token ID | 2949 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
ons | +0.006 |
heart | +0.006 |
loo | +0.005 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.007 |
allowance | -0.007 |
ro | -0.007 |
isc | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
ww | +0.130 |
www | +0.114 |
loo | +0.114 |
ull | +0.110 |
ons | +0.109 |
Neg logit contributions | |
bank | -0.080 |
allowance | -0.073 |
banks | -0.072 |
isc | -0.064 |
ro | -0.063 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ww | +0.011 |
loo | +0.010 |
ins | +0.010 |
www | +0.009 |
orn | +0.009 |
Neg logit contributions | |
bank | -0.010 |
allowance | -0.010 |
banks | -0.009 |
buy | -0.009 |
seem | -0.009 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ww | +0.023 |
ons | +0.020 |
Charlie | +0.019 |
loo | +0.018 |
igator | +0.018 |
Neg logit contributions | |
isc | -0.051 |
ro | -0.050 |
bank | -0.050 |
banks | -0.046 |
allowance | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
ww | +0.253 |
www | +0.222 |
mber | +0.208 |
ons | +0.206 |
loo | +0.205 |
Neg logit contributions | |
bank | -0.149 |
banks | -0.135 |
allowance | -0.130 |
ro | -0.118 |
isc | -0.114 |
Token | That |
Token ID | 1320 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
ons | +0.003 |
heart | +0.003 |
loo | +0.003 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.004 |
isc | -0.004 |
ro | -0.004 |
Token | dress |
Token ID | 6576 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
ww | +0.029 |
www | +0.026 |
loo | +0.025 |
heart | +0.024 |
ons | +0.024 |
Neg logit contributions | |
bank | -0.017 |
banks | -0.015 |
allowance | -0.014 |
isc | -0.012 |
ro | -0.012 |
Token | is |
Token ID | 318 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
mber | +0.004 |
loo | +0.004 |
ull | +0.004 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
ro | -0.005 |
isc | -0.005 |
Token | too |
Token ID | 1165 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
ww | +0.035 |
www | +0.031 |
loo | +0.030 |
ons | +0.030 |
heart | +0.029 |
Neg logit contributions | |
bank | -0.020 |
allowance | -0.019 |
banks | -0.018 |
usual | -0.017 |
properly | -0.016 |
Token | Sally |
Token ID | 25737 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
bank | +0.044 |
banks | +0.042 |
allowance | +0.040 |
ro | +0.037 |
seem | +0.036 |
Neg logit contributions | |
ww | -0.055 |
www | -0.048 |
mber | -0.043 |
heart | -0.042 |
loo | -0.040 |
Token | told |
Token ID | 1297 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
bank | +0.040 |
banks | +0.038 |
allowance | +0.036 |
ro | +0.032 |
isc | +0.031 |
Neg logit contributions | |
ww | -0.059 |
www | -0.052 |
heart | -0.047 |
mber | -0.046 |
loo | -0.046 |
Token | him |
Token ID | 683 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
bank | +0.011 |
banks | +0.011 |
allowance | +0.010 |
ro | +0.009 |
isc | +0.009 |
Neg logit contributions | |
ww | -0.012 |
www | -0.011 |
heart | -0.010 |
ons | -0.010 |
mber | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bank | +0.037 |
banks | +0.035 |
allowance | +0.034 |
ro | +0.030 |
usual | +0.029 |
Neg logit contributions | |
ww | -0.057 |
www | -0.050 |
heart | -0.045 |
mber | -0.045 |
ons | -0.044 |
Token | Wh |
Token ID | 854 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
bank | +0.019 |
banks | +0.018 |
allowance | +0.017 |
usual | +0.016 |
ro | +0.016 |
Neg logit contributions | |
ww | -0.023 |
www | -0.021 |
loo | -0.018 |
mber | -0.018 |
heart | -0.018 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
bank | +0.075 |
banks | +0.070 |
allowance | +0.063 |
ro | +0.050 |
isc | +0.049 |
Neg logit contributions | |
ww | -0.212 |
www | -0.193 |
heart | -0.180 |
ons | -0.177 |
?" | -0.176 |
Token | ers |
Token ID | 364 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
bank | +0.280 |
banks | +0.268 |
allowance | +0.253 |
ro | +0.239 |
isc | +0.230 |
Neg logit contributions | |
ww | -0.261 |
www | -0.225 |
heart | -0.200 |
mber | -0.191 |
?" | -0.191 |
Token | always |
Token ID | 1464 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
bank | +0.044 |
banks | +0.041 |
allowance | +0.038 |
ro | +0.035 |
isc | +0.034 |
Neg logit contributions | |
ww | -0.059 |
www | -0.052 |
heart | -0.047 |
ons | -0.046 |
mber | -0.046 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
ww | +0.047 |
www | +0.040 |
loo | +0.040 |
mber | +0.037 |
ull | +0.037 |
Neg logit contributions | |
bank | -0.033 |
banks | -0.030 |
allowance | -0.029 |
usual | -0.027 |
seem | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.009 |
heart | +0.009 |
ons | +0.009 |
mber | +0.009 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.004 |
ro | -0.004 |
isc | -0.004 |
Token | help |
Token ID | 1037 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.022 |
allowance | +0.020 |
ro | +0.017 |
buy | +0.017 |
Neg logit contributions | |
ww | -0.049 |
www | -0.044 |
mber | -0.041 |
heart | -0.040 |
loo | -0.040 |
Token | on |
Token ID | 319 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
bank | +0.022 |
banks | +0.020 |
anymore | +0.019 |
allowance | +0.018 |
properly | +0.018 |
Neg logit contributions | |
ww | -0.049 |
www | -0.044 |
mber | -0.042 |
heart | -0.041 |
imi | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.020 |
allowance | +0.019 |
usual | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.034 |
www | -0.030 |
heart | -0.027 |
mber | -0.027 |
loo | -0.026 |
Token | cards |
Token ID | 4116 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.007 |
ro | +0.006 |
isc | +0.006 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.007 |
ons | -0.007 |
mber | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bank | +0.044 |
banks | +0.040 |
allowance | +0.035 |
ro | +0.031 |
anymore | +0.030 |
Neg logit contributions | |
ww | -0.085 |
www | -0.076 |
heart | -0.071 |
mber | -0.070 |
imi | -0.068 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.013 |
allowance | +0.012 |
ro | +0.011 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.028 |
www | -0.025 |
heart | -0.024 |
ons | -0.023 |
w | -0.022 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
bank | +0.073 |
banks | +0.068 |
allowance | +0.062 |
symp | +0.049 |
usual | +0.049 |
Neg logit contributions | |
ww | -0.183 |
www | -0.166 |
heart | -0.156 |
ons | -0.154 |
?" | -0.153 |
Token | ers |
Token ID | 364 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
bank | +0.280 |
banks | +0.270 |
allowance | +0.255 |
ro | +0.237 |
isc | +0.233 |
Neg logit contributions | |
ww | -0.240 |
www | -0.206 |
heart | -0.182 |
mber | -0.174 |
?" | -0.173 |
Token | was |
Token ID | 373 |
Feature activation | +9.04e-05 |
Pos logit contributions | |
bank | +0.030 |
banks | +0.028 |
allowance | +0.026 |
ro | +0.024 |
symp | +0.023 |
Neg logit contributions | |
ww | -0.041 |
www | -0.036 |
heart | -0.033 |
mber | -0.032 |
loo | -0.031 |
Token | hesitant |
Token ID | 32848 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ww | +0.000 |
www | +0.000 |
heart | +0.000 |
loo | +0.000 |
mber | +0.000 |
Neg logit contributions | |
bank | -0.000 |
banks | -0.000 |
allowance | -0.000 |
usual | -0.000 |
ro | -0.000 |
Token | at |
Token ID | 379 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ww | +0.049 |
www | +0.043 |
heart | +0.040 |
?" | +0.038 |
mber | +0.038 |
Neg logit contributions | |
bank | -0.038 |
banks | -0.037 |
allowance | -0.035 |
ro | -0.031 |
isc | -0.031 |
Token | first |
Token ID | 717 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
ww | +0.053 |
www | +0.048 |
heart | +0.044 |
mber | +0.043 |
ons | +0.043 |
Neg logit contributions | |
bank | -0.020 |
banks | -0.018 |
allowance | -0.017 |
usual | -0.016 |
ro | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -9.42e-03 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.014 |
www | -0.013 |
heart | -0.012 |
mber | -0.011 |
ons | -0.011 |
Token | naughty |
Token ID | 45128 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.013 |
allowance | +0.012 |
ro | +0.011 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.019 |
www | -0.017 |
heart | -0.016 |
ons | -0.015 |
mber | -0.015 |
Token | cat |
Token ID | 3797 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
bank | +0.029 |
banks | +0.026 |
allowance | +0.025 |
ro | +0.025 |
isc | +0.024 |
Neg logit contributions | |
ww | -0.033 |
www | -0.029 |
ons | -0.029 |
heart | -0.026 |
ins | -0.025 |
Token | named |
Token ID | 3706 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
bank | +0.033 |
banks | +0.029 |
ro | +0.026 |
allowance | +0.026 |
anymore | +0.025 |
Neg logit contributions | |
ww | -0.043 |
www | -0.038 |
mber | -0.034 |
heart | -0.034 |
very | -0.031 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
?" | +0.005 |
heart | +0.005 |
ons | +0.005 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.008 |
ro | -0.007 |
symp | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
bank | +0.087 |
banks | +0.081 |
allowance | +0.079 |
contain | +0.065 |
symp | +0.063 |
Neg logit contributions | |
ww | -0.163 |
www | -0.146 |
ons | -0.143 |
?" | -0.142 |
imi | -0.141 |
Token | ers |
Token ID | 364 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
bank | +0.271 |
banks | +0.259 |
allowance | +0.244 |
ro | +0.229 |
isc | +0.223 |
Neg logit contributions | |
ww | -0.250 |
www | -0.216 |
heart | -0.194 |
mber | -0.184 |
?" | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
allowance | +0.036 |
banks | +0.035 |
bank | +0.035 |
urd | +0.033 |
ro | +0.032 |
Neg logit contributions | |
?" | -0.026 |
? | -0.026 |
ww | -0.025 |
ons | -0.023 |
course | -0.022 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.016 |
allowance | +0.015 |
contain | +0.014 |
ately | +0.014 |
Neg logit contributions | |
ww | -0.020 |
www | -0.017 |
?" | -0.015 |
my | -0.015 |
imi | -0.015 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.078 |
banks | +0.074 |
allowance | +0.071 |
contain | +0.062 |
usual | +0.059 |
Neg logit contributions | |
ww | -0.155 |
www | -0.138 |
ons | -0.134 |
?" | -0.133 |
imi | -0.131 |
Token | ers |
Token ID | 364 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
bank | +0.258 |
banks | +0.247 |
allowance | +0.231 |
ro | +0.218 |
isc | +0.210 |
Neg logit contributions | |
ww | -0.247 |
www | -0.214 |
heart | -0.192 |
mber | -0.183 |
?" | -0.178 |
Token | flew |
Token ID | 13112 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.001 |
heart | +0.001 |
ons | +0.001 |
mber | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
ro | -0.001 |
isc | -0.001 |
Token | down |
Token ID | 866 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
ro | +0.008 |
allowance | +0.008 |
usual | +0.007 |
Neg logit contributions | |
ww | -0.021 |
www | -0.019 |
ons | -0.018 |
mber | -0.017 |
heart | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
bank | +0.025 |
banks | +0.024 |
allowance | +0.022 |
isc | +0.019 |
ro | +0.019 |
Neg logit contributions | |
ww | -0.042 |
www | -0.037 |
heart | -0.034 |
ons | -0.034 |
?" | -0.034 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
loo | +0.004 |
heart | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
ro | -0.003 |
usual | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
ww | +0.033 |
www | +0.029 |
heart | +0.026 |
ons | +0.026 |
mber | +0.026 |
Neg logit contributions | |
bank | -0.024 |
banks | -0.023 |
allowance | -0.022 |
ro | -0.020 |
isc | -0.019 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
bank | +0.084 |
allowance | +0.080 |
banks | +0.078 |
symp | +0.062 |
usual | +0.061 |
Neg logit contributions | |
ww | -0.165 |
www | -0.148 |
heart | -0.142 |
imi | -0.137 |
ons | -0.137 |
Token | ers |
Token ID | 364 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
bank | +0.292 |
banks | +0.283 |
allowance | +0.272 |
symp | +0.249 |
isc | +0.248 |
Neg logit contributions | |
ww | -0.222 |
www | -0.188 |
ons | -0.163 |
heart | -0.162 |
mber | -0.157 |
Token | away |
Token ID | 1497 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
bank | +0.029 |
allowance | +0.029 |
banks | +0.029 |
isc | +0.028 |
symp | +0.026 |
Neg logit contributions | |
ww | -0.033 |
www | -0.029 |
?" | -0.028 |
? | -0.028 |
ons | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -7.44e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.008 |
allowance | +0.008 |
isc | +0.007 |
ro | +0.007 |
Neg logit contributions | |
ww | -0.014 |
www | -0.012 |
heart | -0.011 |
?" | -0.011 |
ons | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
bank | +0.011 |
banks | +0.011 |
allowance | +0.010 |
ro | +0.009 |
isc | +0.009 |
Neg logit contributions | |
ww | -0.015 |
www | -0.013 |
heart | -0.012 |
ons | -0.012 |
mber | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
heart | +0.009 |
ons | +0.009 |
loo | +0.009 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
usual | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.007 |
mber | -0.007 |
loo | -0.007 |
Token | smart |
Token ID | 4451 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
ro | +0.008 |
symp | +0.008 |
Neg logit contributions | |
ww | -0.015 |
www | -0.014 |
heart | -0.013 |
ons | -0.013 |
mber | -0.012 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
bank | +0.045 |
banks | +0.040 |
ro | +0.039 |
allowance | +0.038 |
isc | +0.035 |
Neg logit contributions | |
ww | -0.056 |
ons | -0.050 |
www | -0.050 |
heart | -0.046 |
w | -0.043 |
Token | named |
Token ID | 3706 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
bank | +0.027 |
banks | +0.024 |
ro | +0.021 |
anymore | +0.020 |
allowance | +0.020 |
Neg logit contributions | |
ww | -0.039 |
www | -0.035 |
mber | -0.032 |
heart | -0.032 |
ins | -0.029 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
ww | +0.010 |
www | +0.008 |
heart | +0.007 |
ons | +0.007 |
?" | +0.007 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.012 |
allowance | -0.011 |
ro | -0.011 |
isc | -0.010 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
bank | +0.083 |
banks | +0.078 |
allowance | +0.075 |
symp | +0.060 |
ro | +0.059 |
Neg logit contributions | |
ww | -0.161 |
www | -0.145 |
ons | -0.138 |
?" | -0.137 |
heart | -0.136 |
Token | ers |
Token ID | 364 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
bank | +0.262 |
banks | +0.251 |
allowance | +0.235 |
ro | +0.222 |
isc | +0.215 |
Neg logit contributions | |
ww | -0.250 |
www | -0.216 |
heart | -0.195 |
mber | -0.185 |
?" | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
allowance | +0.027 |
bank | +0.027 |
banks | +0.027 |
urd | +0.025 |
ro | +0.024 |
Neg logit contributions | |
ww | -0.022 |
?" | -0.021 |
? | -0.021 |
ons | -0.019 |
course | -0.019 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.010 |
contain | +0.010 |
symp | +0.010 |
Neg logit contributions | |
ww | -0.014 |
www | -0.012 |
?" | -0.011 |
my | -0.011 |
ons | -0.011 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
bank | +0.069 |
banks | +0.064 |
allowance | +0.061 |
symp | +0.048 |
usual | +0.048 |
Neg logit contributions | |
ww | -0.164 |
www | -0.148 |
ons | -0.140 |
?" | -0.138 |
heart | -0.138 |
Token | ers |
Token ID | 364 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bank | +0.251 |
banks | +0.240 |
allowance | +0.222 |
ro | +0.212 |
tted | +0.203 |
Neg logit contributions | |
ww | -0.249 |
www | -0.216 |
heart | -0.195 |
mber | -0.185 |
?" | -0.181 |
Token | j |
Token ID | 474 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
allowance | +0.008 |
ro | +0.008 |
isc | +0.007 |
Neg logit contributions | |
ww | -0.014 |
www | -0.013 |
heart | -0.012 |
ons | -0.011 |
mber | -0.011 |
Token | olly |
Token ID | 5098 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.023 |
allowance | +0.022 |
ro | +0.021 |
isc | +0.021 |
Neg logit contributions | |
ww | -0.018 |
www | -0.015 |
heart | -0.013 |
ons | -0.013 |
mber | -0.013 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
ons | +0.011 |
heart | +0.011 |
loo | +0.010 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
ro | -0.009 |
isc | -0.008 |
Token | named |
Token ID | 3706 |
Feature activation | +8.28e-03 |
Pos logit contributions | |
bank | +0.026 |
banks | +0.023 |
ro | +0.020 |
allowance | +0.020 |
symp | +0.019 |
Neg logit contributions | |
ww | -0.033 |
www | -0.030 |
mber | -0.027 |
heart | -0.026 |
loo | -0.024 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
?" | +0.010 |
heart | +0.010 |
ons | +0.010 |
Neg logit contributions | |
bank | -0.016 |
banks | -0.015 |
allowance | -0.015 |
ro | -0.014 |
isc | -0.013 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
bank | +0.083 |
banks | +0.078 |
allowance | +0.075 |
contain | +0.061 |
symp | +0.058 |
Neg logit contributions | |
ww | -0.159 |
www | -0.142 |
ons | -0.138 |
imi | -0.137 |
?" | -0.135 |
Token | ers |
Token ID | 364 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bank | +0.263 |
banks | +0.252 |
allowance | +0.236 |
ro | +0.223 |
isc | +0.217 |
Neg logit contributions | |
ww | -0.248 |
www | -0.214 |
heart | -0.193 |
mber | -0.183 |
?" | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
allowance | +0.029 |
banks | +0.028 |
bank | +0.028 |
urd | +0.026 |
asy | +0.026 |
Neg logit contributions | |
? | -0.019 |
?" | -0.019 |
ww | -0.018 |
course | -0.016 |
ons | -0.016 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.012 |
allowance | +0.011 |
contain | +0.011 |
ately | +0.010 |
Neg logit contributions | |
ww | -0.015 |
www | -0.013 |
?" | -0.012 |
imi | -0.011 |
my | -0.011 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.075 |
banks | +0.070 |
allowance | +0.067 |
contain | +0.055 |
usual | +0.055 |
Neg logit contributions | |
ww | -0.156 |
www | -0.140 |
ons | -0.134 |
?" | -0.131 |
heart | -0.131 |
Token | ers |
Token ID | 364 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
bank | +0.249 |
banks | +0.238 |
allowance | +0.220 |
ro | +0.211 |
tted | +0.202 |
Neg logit contributions | |
ww | -0.251 |
www | -0.219 |
heart | -0.198 |
mber | -0.187 |
?" | -0.185 |
Token | was |
Token ID | 373 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
bank | +0.037 |
banks | +0.036 |
allowance | +0.034 |
isc | +0.031 |
ro | +0.031 |
Neg logit contributions | |
ww | -0.036 |
www | -0.031 |
?" | -0.029 |
ons | -0.028 |
heart | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -9.05e-03 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.011 |
usual | +0.009 |
isc | +0.009 |
Neg logit contributions | |
ww | -0.016 |
www | -0.015 |
heart | -0.013 |
mber | -0.013 |
ons | -0.013 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.011 |
ro | +0.010 |
symp | +0.010 |
Neg logit contributions | |
ww | -0.019 |
www | -0.017 |
heart | -0.016 |
ons | -0.016 |
mber | -0.015 |
Token | named |
Token ID | 3706 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
bank | +0.029 |
banks | +0.026 |
allowance | +0.023 |
ro | +0.023 |
symp | +0.022 |
Neg logit contributions | |
ww | -0.035 |
www | -0.031 |
heart | -0.028 |
mber | -0.028 |
loo | -0.026 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
heart | +0.007 |
ons | +0.007 |
?" | +0.007 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.012 |
allowance | -0.011 |
ro | -0.010 |
symp | -0.010 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bank | +0.086 |
banks | +0.082 |
allowance | +0.079 |
contain | +0.067 |
symp | +0.062 |
Neg logit contributions | |
ww | -0.146 |
www | -0.130 |
ons | -0.129 |
imi | -0.127 |
?" | -0.125 |
Token | ers |
Token ID | 364 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
bank | +0.280 |
banks | +0.271 |
allowance | +0.258 |
ro | +0.237 |
isc | +0.236 |
Neg logit contributions | |
ww | -0.228 |
www | -0.195 |
heart | -0.171 |
ons | -0.166 |
mber | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
allowance | +0.022 |
banks | +0.022 |
bank | +0.021 |
isc | +0.020 |
urd | +0.020 |
Neg logit contributions | |
?" | -0.015 |
? | -0.015 |
ww | -0.015 |
ons | -0.013 |
course | -0.013 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
ately | +0.005 |
contain | +0.005 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
?" | -0.005 |
ons | -0.004 |
my | -0.004 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.077 |
banks | +0.073 |
allowance | +0.070 |
contain | +0.061 |
usual | +0.059 |
Neg logit contributions | |
ww | -0.153 |
www | -0.137 |
ons | -0.133 |
?" | -0.129 |
heart | -0.128 |
Token | ers |
Token ID | 364 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
bank | +0.260 |
banks | +0.249 |
allowance | +0.232 |
ro | +0.219 |
isc | +0.213 |
Neg logit contributions | |
ww | -0.246 |
www | -0.213 |
heart | -0.190 |
mber | -0.182 |
?" | -0.179 |
Token | that |
Token ID | 326 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.014 |
usual | +0.013 |
until | +0.013 |
Neg logit contributions | |
ww | -0.031 |
www | -0.028 |
ins | -0.027 |
heart | -0.027 |
ons | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
bank | +0.015 |
allowance | +0.014 |
banks | +0.014 |
usual | +0.013 |
ro | +0.012 |
Neg logit contributions | |
ww | -0.013 |
www | -0.012 |
heart | -0.011 |
ins | -0.011 |
mber | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
ons | -0.006 |
?" | -0.005 |
heart | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.003 |
heart | +0.003 |
mber | +0.003 |
ons | +0.003 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.002 |
ro | -0.002 |
isc | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
ww | +0.012 |
www | +0.010 |
ons | +0.009 |
course | +0.009 |
my | +0.009 |
Neg logit contributions | |
banks | -0.009 |
bank | -0.008 |
symp | -0.008 |
allowance | -0.007 |
spine | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bank | +0.085 |
banks | +0.083 |
allowance | +0.077 |
contain | +0.074 |
usual | +0.071 |
Neg logit contributions | |
ww | -0.150 |
www | -0.132 |
ons | -0.125 |
heart | -0.123 |
imi | -0.121 |
Token | ers |
Token ID | 364 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
bank | +0.274 |
banks | +0.265 |
allowance | +0.251 |
ro | +0.232 |
isc | +0.229 |
Neg logit contributions | |
ww | -0.231 |
www | -0.198 |
heart | -0.175 |
mber | -0.168 |
ons | -0.168 |
Token | was |
Token ID | 373 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.015 |
allowance | +0.014 |
isc | +0.013 |
ro | +0.013 |
Neg logit contributions | |
ww | -0.022 |
www | -0.019 |
ons | -0.017 |
heart | -0.017 |
?" | -0.017 |
Token | no |
Token ID | 645 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.005 |
loo | +0.005 |
ons | +0.005 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
usual | -0.003 |
symp | -0.002 |
Token | longer |
Token ID | 2392 |
Feature activation | +3.18e-04 |
Pos logit contributions | |
ww | +0.046 |
www | +0.042 |
heart | +0.040 |
?" | +0.037 |
course | +0.037 |
Neg logit contributions | |
bank | -0.025 |
banks | -0.025 |
allowance | -0.020 |
isc | -0.020 |
symp | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
heart | +0.001 |
ons | +0.001 |
mber | +0.001 |
Neg logit contributions | |
bank | -0.000 |
banks | -0.000 |
allowance | -0.000 |
ro | -0.000 |
isc | -0.000 |
Token | everyone |
Token ID | 2506 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
ww | +0.075 |
www | +0.067 |
?" | +0.060 |
heart | +0.059 |
ons | +0.059 |
Neg logit contributions | |
bank | -0.061 |
banks | -0.059 |
allowance | -0.055 |
symp | -0.049 |
ro | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.005 |
mber | +0.005 |
loo | +0.005 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
ro | -0.002 |
usual | -0.002 |
Token | surprise |
Token ID | 5975 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.002 |
isc | +0.002 |
Neg logit contributions | |
ww | -0.003 |
www | -0.003 |
heart | -0.002 |
mber | -0.002 |
ons | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
ww | +0.052 |
www | +0.046 |
heart | +0.041 |
mber | +0.041 |
ons | +0.040 |
Neg logit contributions | |
bank | -0.038 |
banks | -0.036 |
allowance | -0.034 |
isc | -0.031 |
ro | -0.030 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
heart | +0.009 |
ons | +0.009 |
mber | +0.009 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bank | +0.080 |
banks | +0.077 |
allowance | +0.073 |
contain | +0.065 |
usual | +0.062 |
Neg logit contributions | |
ww | -0.155 |
www | -0.138 |
heart | -0.131 |
ons | -0.131 |
imi | -0.128 |
Token | ers |
Token ID | 364 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bank | +0.252 |
banks | +0.240 |
allowance | +0.223 |
ro | +0.213 |
tted | +0.206 |
Neg logit contributions | |
ww | -0.254 |
www | -0.220 |
heart | -0.198 |
?" | -0.190 |
mber | -0.187 |
Token | turned |
Token ID | 2900 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
bank | +0.019 |
banks | +0.018 |
allowance | +0.017 |
ro | +0.016 |
isc | +0.016 |
Neg logit contributions | |
ww | -0.022 |
www | -0.020 |
heart | -0.018 |
ons | -0.018 |
?" | -0.017 |
Token | out |
Token ID | 503 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
bank | +0.022 |
banks | +0.021 |
allowance | +0.019 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.033 |
www | -0.029 |
heart | -0.027 |
ons | -0.027 |
?" | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -6.96e-03 |
Pos logit contributions | |
bank | +0.069 |
banks | +0.067 |
allowance | +0.063 |
isc | +0.057 |
ro | +0.057 |
Neg logit contributions | |
ww | -0.078 |
www | -0.068 |
heart | -0.062 |
ons | -0.061 |
?" | -0.059 |
Token | be |
Token ID | 307 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.010 |
symp | +0.009 |
isc | +0.009 |
Neg logit contributions | |
ww | -0.013 |
www | -0.012 |
heart | -0.011 |
?" | -0.011 |
ons | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
bank | +0.008 |
banks | +0.008 |
allowance | +0.007 |
ro | +0.006 |
isc | +0.006 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
heart | -0.013 |
ons | -0.012 |
loo | -0.012 |
Token | After |
Token ID | 3260 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.005 |
allowance | +0.005 |
tted | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
heart | -0.007 |
loo | -0.007 |
ons | -0.007 |
Token | Mr |
Token ID | 1770 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
heart | +0.008 |
mber | +0.007 |
ins | +0.007 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.006 |
allowance | -0.006 |
usual | -0.005 |
until | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
bank | +0.059 |
banks | +0.057 |
allowance | +0.053 |
ro | +0.046 |
symp | +0.046 |
Neg logit contributions | |
ww | -0.086 |
www | -0.075 |
heart | -0.069 |
?" | -0.068 |
mber | -0.067 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.010 |
ro | +0.010 |
isc | +0.010 |
Neg logit contributions | |
ww | -0.016 |
www | -0.015 |
heart | -0.013 |
ons | -0.013 |
mber | -0.013 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.075 |
banks | +0.071 |
allowance | +0.066 |
usual | +0.051 |
contain | +0.051 |
Neg logit contributions | |
ww | -0.169 |
www | -0.153 |
heart | -0.145 |
ons | -0.141 |
?" | -0.139 |
Token | ers |
Token ID | 364 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bank | +0.263 |
banks | +0.252 |
allowance | +0.237 |
ro | +0.223 |
isc | +0.216 |
Neg logit contributions | |
ww | -0.241 |
www | -0.208 |
heart | -0.186 |
?" | -0.180 |
mber | -0.177 |
Token | was |
Token ID | 373 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.020 |
allowance | +0.019 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.025 |
www | -0.022 |
heart | -0.020 |
ons | -0.020 |
mber | -0.020 |
Token | done |
Token ID | 1760 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ww | +0.006 |
www | +0.006 |
heart | +0.005 |
mber | +0.005 |
ons | +0.005 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.003 |
allowance | -0.003 |
usual | -0.003 |
symp | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +7.63e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.018 |
allowance | +0.018 |
ro | +0.016 |
symp | +0.016 |
Neg logit contributions | |
ww | -0.027 |
www | -0.024 |
heart | -0.021 |
mber | -0.021 |
ons | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | -3.54e-04 |
Pos logit contributions | |
ww | +0.010 |
www | +0.008 |
my | +0.008 |
course | +0.008 |
heart | +0.008 |
Neg logit contributions | |
banks | -0.015 |
bank | -0.015 |
ro | -0.014 |
allowance | -0.014 |
tted | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.006 |
allowance | +0.006 |
usual | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.008 |
mber | -0.007 |
ons | -0.007 |
Token | lazy |
Token ID | 16931 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
allowance | +0.009 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.014 |
www | -0.013 |
heart | -0.012 |
ons | -0.012 |
mber | -0.011 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
bank | +0.019 |
banks | +0.017 |
ro | +0.017 |
allowance | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.026 |
ons | -0.024 |
www | -0.023 |
ins | -0.022 |
heart | -0.022 |
Token | named |
Token ID | 3706 |
Feature activation | +8.08e-03 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.021 |
ro | +0.019 |
anymore | +0.018 |
allowance | +0.018 |
Neg logit contributions | |
ww | -0.033 |
www | -0.030 |
mber | -0.027 |
heart | -0.026 |
ins | -0.024 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
?" | +0.009 |
heart | +0.009 |
my | +0.009 |
Neg logit contributions | |
bank | -0.016 |
banks | -0.015 |
allowance | -0.015 |
ro | -0.013 |
symp | -0.013 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.083 |
banks | +0.077 |
allowance | +0.075 |
contain | +0.060 |
symp | +0.058 |
Neg logit contributions | |
ww | -0.154 |
www | -0.139 |
ons | -0.135 |
imi | -0.133 |
?" | -0.131 |
Token | ers |
Token ID | 364 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
bank | +0.264 |
banks | +0.253 |
allowance | +0.238 |
ro | +0.223 |
isc | +0.219 |
Neg logit contributions | |
ww | -0.242 |
www | -0.209 |
heart | -0.187 |
mber | -0.178 |
?" | -0.177 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
allowance | +0.019 |
banks | +0.019 |
bank | +0.019 |
urd | +0.018 |
ro | +0.017 |
Neg logit contributions | |
? | -0.014 |
?" | -0.014 |
ww | -0.013 |
course | -0.012 |
ons | -0.012 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
bank | +0.008 |
banks | +0.008 |
allowance | +0.008 |
contain | +0.007 |
ately | +0.007 |
Neg logit contributions | |
ww | -0.010 |
www | -0.008 |
?" | -0.008 |
my | -0.007 |
imi | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
bank | +0.072 |
banks | +0.067 |
allowance | +0.064 |
usual | +0.051 |
contain | +0.051 |
Neg logit contributions | |
ww | -0.158 |
www | -0.143 |
ons | -0.136 |
heart | -0.134 |
?" | -0.133 |
Token | ers |
Token ID | 364 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
bank | +0.248 |
banks | +0.238 |
allowance | +0.219 |
ro | +0.209 |
tted | +0.202 |
Neg logit contributions | |
ww | -0.249 |
www | -0.217 |
heart | -0.195 |
mber | -0.186 |
?" | -0.183 |
Token | dream |
Token ID | 4320 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ww | +0.004 |
my | +0.003 |
www | +0.003 |
imi | +0.003 |
? | +0.002 |
Neg logit contributions | |
banks | -0.004 |
bank | -0.004 |
ked | -0.004 |
contain | -0.004 |
ured | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.72e-04 |
Pos logit contributions | |
bank | +0.026 |
banks | +0.026 |
allowance | +0.024 |
symp | +0.022 |
isc | +0.021 |
Neg logit contributions | |
ww | -0.024 |
www | -0.020 |
heart | -0.018 |
mber | -0.018 |
?" | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
heart | +0.000 |
ons | +0.000 |
?" | +0.000 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
ro | -0.001 |
symp | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
bank | +0.019 |
banks | +0.019 |
allowance | +0.017 |
isc | +0.015 |
ro | +0.015 |
Neg logit contributions | |
ww | -0.025 |
www | -0.022 |
heart | -0.020 |
?" | -0.020 |
ons | -0.020 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
symp | +0.005 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
ons | -0.004 |
heart | -0.004 |
?" | -0.004 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.085 |
banks | +0.079 |
allowance | +0.077 |
contain | +0.060 |
symp | +0.060 |
Neg logit contributions | |
ww | -0.152 |
www | -0.137 |
heart | -0.130 |
imi | -0.128 |
ons | -0.126 |
Token | ers |
Token ID | 364 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
bank | +0.284 |
banks | +0.275 |
allowance | +0.263 |
isc | +0.240 |
ro | +0.240 |
Neg logit contributions | |
ww | -0.220 |
www | -0.187 |
heart | -0.163 |
ons | -0.162 |
mber | -0.157 |
Token | walking |
Token ID | 6155 |
Feature activation | +4.42e-03 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.017 |
allowance | +0.017 |
isc | +0.015 |
ro | +0.015 |
Neg logit contributions | |
ww | -0.017 |
www | -0.015 |
ons | -0.014 |
heart | -0.014 |
?" | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
heart | +0.007 |
ons | +0.007 |
mber | +0.007 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |
Token | talking |
Token ID | 3375 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.003 |
allowance | +0.003 |
usual | +0.003 |
ro | +0.003 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
heart | -0.004 |
loo | -0.003 |
ons | -0.003 |
Token | like |
Token ID | 588 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.002 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
mber | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
?" | +0.005 |
heart | +0.005 |
ons | +0.005 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.008 |
ro | -0.007 |
symp | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
bank | +0.087 |
banks | +0.081 |
allowance | +0.079 |
contain | +0.065 |
symp | +0.063 |
Neg logit contributions | |
ww | -0.163 |
www | -0.146 |
ons | -0.143 |
?" | -0.142 |
imi | -0.141 |
Token | ers |
Token ID | 364 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
bank | +0.271 |
banks | +0.259 |
allowance | +0.244 |
ro | +0.229 |
isc | +0.223 |
Neg logit contributions | |
ww | -0.250 |
www | -0.216 |
heart | -0.194 |
mber | -0.184 |
?" | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
allowance | +0.036 |
banks | +0.035 |
bank | +0.035 |
urd | +0.033 |
ro | +0.032 |
Neg logit contributions | |
?" | -0.026 |
? | -0.026 |
ww | -0.025 |
ons | -0.023 |
course | -0.022 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.016 |
allowance | +0.015 |
contain | +0.014 |
ately | +0.014 |
Neg logit contributions | |
ww | -0.020 |
www | -0.017 |
?" | -0.015 |
my | -0.015 |
imi | -0.015 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
bank | +0.078 |
banks | +0.074 |
allowance | +0.071 |
contain | +0.062 |
usual | +0.059 |
Neg logit contributions | |
ww | -0.155 |
www | -0.138 |
ons | -0.134 |
?" | -0.133 |
imi | -0.131 |
Token | ers |
Token ID | 364 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
bank | +0.258 |
banks | +0.247 |
allowance | +0.231 |
ro | +0.218 |
isc | +0.210 |
Neg logit contributions | |
ww | -0.247 |
www | -0.214 |
heart | -0.192 |
mber | -0.183 |
?" | -0.178 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
bank | +0.028 |
banks | +0.027 |
allowance | +0.026 |
isc | +0.024 |
ro | +0.024 |
Neg logit contributions | |
ww | -0.029 |
www | -0.025 |
?" | -0.022 |
ons | -0.022 |
heart | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ww | +0.018 |
www | +0.017 |
heart | +0.016 |
mber | +0.016 |
loo | +0.015 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
usual | -0.003 |
ro | -0.002 |
Token | play |
Token ID | 711 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.014 |
allowance | +0.012 |
ro | +0.011 |
usual | +0.010 |
Neg logit contributions | |
ww | -0.033 |
www | -0.030 |
mber | -0.028 |
heart | -0.028 |
ins | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
ww | +0.013 |
www | +0.011 |
ons | +0.010 |
heart | +0.010 |
?" | +0.010 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.011 |
allowance | -0.010 |
isc | -0.009 |
ro | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -4.61e-03 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
ins | +0.001 |
heart | +0.001 |
ons | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
bottom | -0.001 |
symp | -0.001 |
Token | fat |
Token ID | 3735 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.005 |
allowance | +0.005 |
symp | +0.005 |
isc | +0.004 |
Neg logit contributions | |
ww | -0.010 |
www | -0.009 |
heart | -0.009 |
ons | -0.008 |
ins | -0.008 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
bank | +0.038 |
banks | +0.033 |
ro | +0.032 |
allowance | +0.029 |
isc | +0.028 |
Neg logit contributions | |
ww | -0.054 |
www | -0.048 |
heart | -0.045 |
ons | -0.045 |
ins | -0.043 |
Token | named |
Token ID | 3706 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
bank | +0.027 |
banks | +0.024 |
ro | +0.022 |
allowance | +0.021 |
symp | +0.020 |
Neg logit contributions | |
ww | -0.035 |
www | -0.031 |
heart | -0.028 |
mber | -0.028 |
loo | -0.025 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
?" | +0.006 |
ons | +0.006 |
heart | +0.005 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
symp | -0.008 |
ro | -0.008 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.084 |
banks | +0.078 |
allowance | +0.076 |
contain | +0.061 |
symp | +0.058 |
Neg logit contributions | |
ww | -0.154 |
www | -0.138 |
ons | -0.135 |
imi | -0.133 |
?" | -0.132 |
Token | ers |
Token ID | 364 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
bank | +0.269 |
banks | +0.259 |
allowance | +0.245 |
ro | +0.228 |
isc | +0.225 |
Neg logit contributions | |
ww | -0.234 |
www | -0.201 |
heart | -0.178 |
mber | -0.171 |
?" | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
allowance | +0.023 |
banks | +0.023 |
bank | +0.023 |
isc | +0.021 |
urd | +0.021 |
Neg logit contributions | |
?" | -0.017 |
ww | -0.017 |
? | -0.017 |
ons | -0.015 |
course | -0.015 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.009 |
allowance | +0.008 |
ately | +0.008 |
contain | +0.008 |
Neg logit contributions | |
ww | -0.010 |
www | -0.008 |
?" | -0.008 |
my | -0.007 |
ons | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.079 |
banks | +0.075 |
allowance | +0.072 |
contain | +0.063 |
usual | +0.061 |
Neg logit contributions | |
ww | -0.154 |
www | -0.137 |
ons | -0.133 |
?" | -0.130 |
imi | -0.128 |
Token | ers |
Token ID | 364 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
bank | +0.256 |
banks | +0.245 |
allowance | +0.228 |
ro | +0.216 |
isc | +0.209 |
Neg logit contributions | |
ww | -0.244 |
www | -0.212 |
heart | -0.190 |
mber | -0.182 |
?" | -0.179 |
Token | that |
Token ID | 326 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
heart | +0.008 |
ins | +0.008 |
ons | +0.008 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.004 |
usual | -0.004 |
symp | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.014 |
allowance | +0.014 |
usual | +0.013 |
symp | +0.013 |
Neg logit contributions | |
ww | -0.014 |
www | -0.012 |
heart | -0.012 |
ins | -0.012 |
mber | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.020 |
allowance | +0.018 |
ro | +0.017 |
isc | +0.017 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
ons | -0.012 |
?" | -0.012 |
heart | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.002 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
mber | -0.002 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
ww | +0.010 |
ons | +0.008 |
www | +0.008 |
course | +0.008 |
my | +0.008 |
Neg logit contributions | |
banks | -0.010 |
bank | -0.009 |
spine | -0.009 |
contain | -0.009 |
symp | -0.008 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.081 |
banks | +0.078 |
allowance | +0.070 |
contain | +0.063 |
usual | +0.063 |
Neg logit contributions | |
ww | -0.158 |
www | -0.139 |
heart | -0.132 |
ons | -0.132 |
imi | -0.128 |
Token | ers |
Token ID | 364 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
bank | +0.285 |
banks | +0.276 |
allowance | +0.265 |
isc | +0.242 |
ro | +0.241 |
Neg logit contributions | |
ww | -0.218 |
www | -0.185 |
heart | -0.160 |
ons | -0.160 |
mber | -0.155 |
Token | was |
Token ID | 373 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.019 |
allowance | +0.018 |
ro | +0.016 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.030 |
www | -0.027 |
heart | -0.025 |
ons | -0.024 |
mber | -0.024 |
Token | no |
Token ID | 645 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
usual | +0.001 |
symp | +0.001 |
Neg logit contributions | |
ww | -0.002 |
www | -0.002 |
heart | -0.002 |
mber | -0.002 |
ons | -0.002 |
Token | longer |
Token ID | 2392 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
ww | +0.045 |
www | +0.040 |
heart | +0.038 |
course | +0.037 |
?" | +0.036 |
Neg logit contributions | |
bank | -0.024 |
banks | -0.024 |
allowance | -0.020 |
isc | -0.020 |
symp | -0.018 |
Token | lazy |
Token ID | 16931 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.002 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
mber | -0.002 |
Token | got |
Token ID | 1392 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
banks | +0.022 |
bank | +0.021 |
allowance | +0.020 |
ro | +0.020 |
uries | +0.019 |
Neg logit contributions | |
ww | -0.019 |
ons | -0.016 |
www | -0.016 |
?" | -0.015 |
course | -0.015 |
Token | back |
Token ID | 736 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
ons | +0.002 |
?" | +0.001 |
heart | +0.001 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.001 |
ro | -0.001 |
isc | -0.001 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.019 |
allowance | +0.018 |
ro | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.032 |
www | -0.028 |
heart | -0.026 |
mber | -0.026 |
ons | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
bank | +0.040 |
banks | +0.039 |
allowance | +0.036 |
isc | +0.033 |
ro | +0.033 |
Neg logit contributions | |
ww | -0.037 |
www | -0.032 |
heart | -0.030 |
ons | -0.030 |
?" | -0.029 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
ww | +0.002 |
www | +0.001 |
ons | +0.001 |
my | +0.001 |
?" | +0.001 |
Neg logit contributions | |
banks | -0.002 |
bank | -0.002 |
allowance | -0.002 |
ro | -0.002 |
tted | -0.002 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.088 |
banks | +0.087 |
contain | +0.083 |
allowance | +0.079 |
usual | +0.074 |
Neg logit contributions | |
ww | -0.138 |
www | -0.118 |
ons | -0.116 |
imi | -0.114 |
ins | -0.113 |
Token | ers |
Token ID | 364 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
bank | +0.266 |
banks | +0.255 |
allowance | +0.241 |
ro | +0.225 |
isc | +0.221 |
Neg logit contributions | |
ww | -0.236 |
www | -0.203 |
heart | -0.180 |
?" | -0.172 |
mber | -0.172 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.89e-04 |
Pos logit contributions | |
banks | +0.021 |
allowance | +0.021 |
bank | +0.021 |
ro | +0.020 |
isc | +0.020 |
Neg logit contributions | |
ww | -0.018 |
ons | -0.017 |
www | -0.016 |
?" | -0.016 |
course | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
isc | +0.001 |
ro | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
mber | -0.001 |
?" | -0.001 |
Token | teaspoon |
Token ID | 22326 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.012 |
allowance | +0.012 |
ro | +0.010 |
usual | +0.010 |
Neg logit contributions | |
ww | -0.017 |
www | -0.015 |
heart | -0.014 |
ons | -0.013 |
loo | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +5.53e-04 |
Pos logit contributions | |
ww | +0.029 |
www | +0.026 |
mber | +0.024 |
heart | +0.023 |
ons | +0.022 |
Neg logit contributions | |
bank | -0.018 |
banks | -0.017 |
allowance | -0.015 |
ro | -0.014 |
symp | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
ww | +0.055 |
www | +0.051 |
ons | +0.047 |
loo | +0.047 |
heart | +0.046 |
Neg logit contributions | |
bank | -0.033 |
allowance | -0.031 |
banks | -0.030 |
isc | -0.027 |
anymore | -0.026 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
ons | +0.003 |
heart | +0.003 |
loo | +0.003 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
isc | -0.003 |
usual | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
ons | +0.003 |
loo | +0.003 |
mber | +0.003 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.004 |
isc | -0.004 |
ro | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.016 |
isc | +0.015 |
loudspe | +0.014 |
Neg logit contributions | |
ww | -0.023 |
www | -0.020 |
loo | -0.019 |
heart | -0.018 |
ins | -0.018 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
banks | +0.025 |
bank | +0.025 |
allowance | +0.022 |
ro | +0.021 |
symp | +0.020 |
Neg logit contributions | |
ww | -0.021 |
www | -0.017 |
?" | -0.016 |
heart | -0.015 |
ons | -0.015 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.081 |
banks | +0.077 |
allowance | +0.071 |
ro | +0.061 |
isc | +0.061 |
Neg logit contributions | |
ww | -0.153 |
www | -0.137 |
heart | -0.126 |
ons | -0.124 |
mber | -0.123 |
Token | ers |
Token ID | 364 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
bank | +0.245 |
banks | +0.233 |
allowance | +0.215 |
ro | +0.211 |
tted | +0.203 |
Neg logit contributions | |
ww | -0.250 |
www | -0.216 |
heart | -0.194 |
?" | -0.189 |
mber | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
allowance | +0.020 |
banks | +0.019 |
bank | +0.019 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.015 |
?" | -0.013 |
ons | -0.013 |
? | -0.013 |
www | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
heart | +0.004 |
ons | +0.004 |
loo | +0.004 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.002 |
symp | -0.002 |
ro | -0.002 |
Token | Do |
Token ID | 5211 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
bank | +0.040 |
banks | +0.037 |
ro | +0.037 |
allowance | +0.034 |
side | +0.034 |
Neg logit contributions | |
ww | -0.051 |
www | -0.046 |
ons | -0.043 |
loo | -0.041 |
heart | -0.041 |
Token | you |
Token ID | 345 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.020 |
allowance | +0.019 |
usual | +0.018 |
isc | +0.018 |
Neg logit contributions | |
ww | -0.009 |
www | -0.007 |
heart | -0.006 |
ons | -0.006 |
loo | -0.006 |
Token | From |
Token ID | 3574 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.011 |
usual | +0.010 |
contain | +0.010 |
Neg logit contributions | |
ww | -0.013 |
www | -0.011 |
ons | -0.010 |
?" | -0.010 |
mber | -0.010 |
Token | then |
Token ID | 788 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
heart | +0.009 |
ins | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
usual | -0.004 |
late | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
bank | +0.109 |
banks | +0.105 |
allowance | +0.100 |
ro | +0.091 |
isc | +0.091 |
Neg logit contributions | |
ww | -0.100 |
www | -0.087 |
heart | -0.077 |
ons | -0.075 |
mber | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +4.30e-03 |
Pos logit contributions | |
ww | +0.003 |
www | +0.003 |
ons | +0.002 |
?" | +0.002 |
my | +0.002 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
isc | -0.003 |
ro | -0.003 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ww | +0.007 |
ons | +0.006 |
www | +0.005 |
my | +0.005 |
course | +0.005 |
Neg logit contributions | |
banks | -0.008 |
bank | -0.007 |
contain | -0.007 |
spine | -0.007 |
ured | -0.007 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
banks | +0.085 |
bank | +0.085 |
contain | +0.077 |
allowance | +0.074 |
usual | +0.071 |
Neg logit contributions | |
ww | -0.142 |
www | -0.122 |
ons | -0.118 |
heart | -0.115 |
ins | -0.114 |
Token | ers |
Token ID | 364 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
bank | +0.277 |
banks | +0.267 |
allowance | +0.255 |
ro | +0.234 |
isc | +0.233 |
Neg logit contributions | |
ww | -0.225 |
www | -0.192 |
heart | -0.168 |
ons | -0.164 |
mber | -0.162 |
Token | tried |
Token ID | 3088 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
banks | +0.019 |
bank | +0.019 |
allowance | +0.018 |
isc | +0.016 |
spine | +0.016 |
Neg logit contributions | |
ww | -0.022 |
ons | -0.019 |
www | -0.019 |
?" | -0.018 |
course | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
ww | +0.038 |
www | +0.034 |
ons | +0.032 |
heart | +0.032 |
?" | +0.031 |
Neg logit contributions | |
bank | -0.023 |
banks | -0.023 |
allowance | -0.021 |
isc | -0.020 |
ro | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.006 |
isc | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.013 |
www | -0.012 |
heart | -0.011 |
ons | -0.011 |
?" | -0.011 |
Token | less |
Token ID | 1342 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.020 |
allowance | +0.019 |
injuries | +0.016 |
usual | +0.016 |
Neg logit contributions | |
ww | -0.031 |
www | -0.028 |
heart | -0.025 |
mber | -0.025 |
loo | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -8.15e-03 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
heart | +0.012 |
ons | +0.012 |
?" | +0.012 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.013 |
allowance | -0.013 |
ro | -0.011 |
isc | -0.011 |
Token | long |
Token ID | 890 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
banks | +0.012 |
bank | +0.011 |
allowance | +0.010 |
isc | +0.010 |
symp | +0.010 |
Neg logit contributions | |
ww | -0.017 |
www | -0.014 |
mber | -0.013 |
heart | -0.012 |
?" | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
bank | +0.028 |
banks | +0.026 |
allowance | +0.025 |
ro | +0.023 |
isc | +0.022 |
Neg logit contributions | |
ww | -0.034 |
www | -0.030 |
heart | -0.027 |
mber | -0.026 |
ons | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.014 |
allowance | +0.013 |
ro | +0.011 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.026 |
www | -0.023 |
heart | -0.021 |
mber | -0.021 |
ons | -0.021 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
banks | +0.008 |
bank | +0.008 |
allowance | +0.008 |
usual | +0.007 |
contain | +0.007 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
?" | -0.007 |
ons | -0.007 |
my | -0.006 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.080 |
banks | +0.078 |
allowance | +0.073 |
contain | +0.069 |
usual | +0.069 |
Neg logit contributions | |
ww | -0.149 |
www | -0.131 |
ons | -0.124 |
heart | -0.124 |
ins | -0.120 |
Token | ers |
Token ID | 364 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
bank | +0.279 |
banks | +0.270 |
allowance | +0.258 |
ro | +0.236 |
isc | +0.236 |
Neg logit contributions | |
ww | -0.222 |
www | -0.189 |
heart | -0.165 |
ons | -0.162 |
mber | -0.159 |
Token | learned |
Token ID | 4499 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
banks | +0.019 |
bank | +0.018 |
allowance | +0.018 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.020 |
www | -0.018 |
ons | -0.017 |
?" | -0.017 |
heart | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
bank | +0.068 |
banks | +0.067 |
allowance | +0.063 |
ro | +0.058 |
isc | +0.058 |
Neg logit contributions | |
ww | -0.061 |
www | -0.052 |
heart | -0.046 |
?" | -0.045 |
ons | -0.045 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.017 |
allowance | +0.017 |
usual | +0.015 |
ro | +0.015 |
Neg logit contributions | |
ww | -0.023 |
www | -0.021 |
heart | -0.019 |
mber | -0.019 |
ons | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
ww | +0.035 |
www | +0.031 |
mber | +0.028 |
heart | +0.027 |
loo | +0.027 |
Neg logit contributions | |
bank | -0.035 |
banks | -0.033 |
allowance | -0.033 |
seem | -0.029 |
usual | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -6.70e-04 |
Pos logit contributions | |
ww | +0.007 |
www | +0.007 |
ins | +0.007 |
heart | +0.006 |
mber | +0.006 |
Neg logit contributions | |
bank | -0.005 |
allowance | -0.005 |
banks | -0.005 |
isc | -0.004 |
symp | -0.004 |
Token | fluffy |
Token ID | 39145 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.001 |
mber | -0.001 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ww | +0.031 |
www | +0.028 |
ons | +0.026 |
ins | +0.026 |
heart | +0.026 |
Neg logit contributions | |
bank | -0.019 |
banks | -0.017 |
allowance | -0.016 |
ro | -0.015 |
isc | -0.014 |
Token | named |
Token ID | 3706 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
bank | +0.027 |
banks | +0.025 |
allowance | +0.023 |
ro | +0.022 |
isc | +0.021 |
Neg logit contributions | |
ww | -0.029 |
www | -0.026 |
heart | -0.024 |
mber | -0.023 |
loo | -0.022 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
heart | +0.012 |
?" | +0.012 |
mber | +0.012 |
Neg logit contributions | |
bank | -0.016 |
banks | -0.015 |
allowance | -0.014 |
symp | -0.013 |
ro | -0.012 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
bank | +0.083 |
banks | +0.077 |
allowance | +0.076 |
contain | +0.059 |
urd | +0.058 |
Neg logit contributions | |
ww | -0.146 |
www | -0.132 |
heart | -0.127 |
imi | -0.124 |
?" | -0.123 |
Token | ers |
Token ID | 364 |
Feature activation | -9.23e-03 |
Pos logit contributions | |
bank | +0.277 |
banks | +0.268 |
allowance | +0.255 |
ro | +0.234 |
isc | +0.234 |
Neg logit contributions | |
ww | -0.224 |
www | -0.191 |
heart | -0.167 |
ons | -0.163 |
mber | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-03 |
Pos logit contributions | |
banks | +0.015 |
bank | +0.015 |
allowance | +0.014 |
urd | +0.013 |
isc | +0.013 |
Neg logit contributions | |
ww | -0.014 |
?" | -0.013 |
? | -0.013 |
www | -0.012 |
ons | -0.012 |
Token | who |
Token ID | 508 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.002 |
isc | +0.002 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
mber | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ww | +0.019 |
www | +0.017 |
heart | +0.016 |
mber | +0.015 |
loo | +0.015 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.012 |
isc | -0.010 |
ro | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -8.18e-03 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.015 |
allowance | +0.013 |
ro | +0.011 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.033 |
www | -0.030 |
heart | -0.027 |
ons | -0.027 |
?" | -0.027 |
Token | looks |
Token ID | 3073 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.003 |
seem | +0.003 |
allowance | +0.002 |
find | +0.002 |
Neg logit contributions | |
ww | -0.018 |
loo | -0.017 |
www | -0.017 |
ull | -0.016 |
mber | -0.016 |
Token | very |
Token ID | 845 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
ww | +0.034 |
www | +0.030 |
heart | +0.027 |
?" | +0.027 |
ons | +0.027 |
Neg logit contributions | |
bank | -0.022 |
banks | -0.021 |
allowance | -0.019 |
ro | -0.017 |
isc | -0.017 |
Token | nice |
Token ID | 3621 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
ww | +0.007 |
www | +0.007 |
ons | +0.006 |
heart | +0.006 |
loo | +0.006 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
usual | -0.005 |
ro | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
loo | +0.006 |
imi | +0.006 |
Charlie | +0.006 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
ro | -0.003 |
until | -0.003 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
loo | +0.010 |
ons | +0.010 |
P | +0.009 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.008 |
allowance | -0.008 |
ro | -0.008 |
symp | -0.007 |
Token | heart |
Token ID | 11499 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ww | +0.025 |
www | +0.020 |
loo | +0.020 |
ined | +0.019 |
Charlie | +0.019 |
Neg logit contributions | |
bank | -0.046 |
banks | -0.044 |
ro | -0.043 |
isc | -0.041 |
anymore | -0.041 |
Token | ," |
Token ID | 553 |
Feature activation | -1.16e-04 |
Pos logit contributions | |
ww | +0.245 |
www | +0.216 |
mber | +0.203 |
ons | +0.202 |
loo | +0.201 |
Neg logit contributions | |
bank | -0.132 |
banks | -0.117 |
allowance | -0.115 |
anymore | -0.103 |
ro | -0.102 |
Token | she |
Token ID | 673 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
allowance | +0.000 |
bank | +0.000 |
buy | +0.000 |
tum | +0.000 |
until | +0.000 |
Neg logit contributions | |
ww | -0.000 |
loo | -0.000 |
ile | -0.000 |
asc | -0.000 |
www | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.013 |
allowance | +0.012 |
isc | +0.012 |
symp | +0.011 |
Neg logit contributions | |
ww | -0.014 |
www | -0.011 |
loo | -0.011 |
ons | -0.010 |
course | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
banks | +0.008 |
bank | +0.008 |
allowance | +0.007 |
isc | +0.006 |
ro | +0.006 |
Neg logit contributions | |
ww | -0.006 |
heart | -0.006 |
?" | -0.006 |
www | -0.006 |
? | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
loo | +0.004 |
heart | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
ro | -0.002 |
isc | -0.002 |
Token | says |
Token ID | 1139 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.020 |
allowance | +0.019 |
ro | +0.018 |
symp | +0.017 |
Neg logit contributions | |
ww | -0.013 |
www | -0.010 |
heart | -0.008 |
loo | -0.008 |
mber | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
isc | +0.004 |
allowance | +0.004 |
urd | +0.004 |
Neg logit contributions | |
ww | -0.003 |
? | -0.003 |
?" | -0.003 |
ons | -0.003 |
heart | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.63e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.003 |
heart | +0.003 |
ons | +0.003 |
mber | +0.003 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
ro | -0.003 |
isc | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
?" | +0.008 |
ons | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.008 |
isc | -0.007 |
ro | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
heart | +0.006 |
ons | +0.006 |
loo | +0.006 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.012 |
ro | -0.011 |
isc | -0.011 |
Token | No |
Token ID | 2949 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.006 |
ro | +0.006 |
symp | +0.005 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
heart | -0.005 |
ons | -0.005 |
loo | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
ww | +0.148 |
www | +0.132 |
mber | +0.129 |
ins | +0.127 |
loo | +0.127 |
Neg logit contributions | |
bank | -0.072 |
banks | -0.066 |
allowance | -0.064 |
anymore | -0.058 |
bottom | -0.053 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ww | +0.009 |
www | +0.008 |
heart | +0.007 |
ons | +0.007 |
mber | +0.007 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.008 |
allowance | -0.008 |
ro | -0.007 |
isc | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.011 |
allowance | +0.010 |
isc | +0.009 |
ro | +0.009 |
Neg logit contributions | |
ww | -0.023 |
www | -0.021 |
mber | -0.021 |
loo | -0.020 |
heart | -0.019 |
Token | This |
Token ID | 770 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
heart | +0.012 |
ons | +0.012 |
mber | +0.012 |
Neg logit contributions | |
bank | -0.015 |
banks | -0.015 |
allowance | -0.014 |
ro | -0.013 |
isc | -0.013 |
Token | is |
Token ID | 318 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ww | +0.032 |
heart | +0.030 |
www | +0.029 |
mber | +0.027 |
ins | +0.027 |
Neg logit contributions | |
bank | -0.027 |
allowance | -0.024 |
banks | -0.023 |
ork | -0.022 |
ro | -0.021 |
Token | find |
Token ID | 1064 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.013 |
allowance | +0.012 |
ro | +0.011 |
usual | +0.011 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
heart | -0.012 |
mber | -0.012 |
ons | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
bank | +0.026 |
banks | +0.024 |
allowance | +0.024 |
any | +0.023 |
find | +0.022 |
Neg logit contributions | |
ww | -0.023 |
www | -0.020 |
mber | -0.019 |
loo | -0.017 |
heart | -0.017 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ww | +0.003 |
www | +0.002 |
heart | +0.001 |
mber | +0.001 |
ons | +0.001 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.014 |
allowance | -0.013 |
ro | -0.012 |
usual | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ww | +0.064 |
www | +0.057 |
heart | +0.052 |
ons | +0.051 |
loo | +0.051 |
Neg logit contributions | |
bank | -0.039 |
banks | -0.037 |
allowance | -0.034 |
ro | -0.031 |
symp | -0.030 |
Token | all |
Token ID | 477 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.014 |
bottom | +0.011 |
allowance | +0.011 |
anymore | +0.010 |
Neg logit contributions | |
ww | -0.022 |
www | -0.019 |
ons | -0.018 |
heart | -0.017 |
mber | -0.017 |
Token | igator |
Token ID | 23823 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
ww | +0.023 |
www | +0.019 |
prise | +0.018 |
corn | +0.017 |
ins | +0.016 |
Neg logit contributions | |
bank | -0.035 |
banks | -0.032 |
contain | -0.030 |
ro | -0.030 |
tered | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
ww | +0.138 |
www | +0.118 |
heart | +0.104 |
ons | +0.101 |
mber | +0.100 |
Neg logit contributions | |
bank | -0.158 |
banks | -0.151 |
allowance | -0.143 |
ro | -0.132 |
symp | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
isc | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
heart | -0.004 |
?" | -0.004 |
ons | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.005 |
ons | +0.005 |
mber | +0.005 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
isc | -0.004 |
ro | -0.004 |
Token | Yes |
Token ID | 5297 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
bank | +0.030 |
banks | +0.029 |
allowance | +0.028 |
ro | +0.025 |
isc | +0.025 |
Neg logit contributions | |
ww | -0.028 |
www | -0.024 |
heart | -0.022 |
ons | -0.021 |
?" | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
ww | +0.076 |
www | +0.067 |
mber | +0.062 |
ons | +0.061 |
loo | +0.061 |
Neg logit contributions | |
bank | -0.048 |
banks | -0.045 |
allowance | -0.043 |
symp | -0.038 |
isc | -0.038 |
Token | Then |
Token ID | 6423 |
Feature activation | +9.97e-04 |
Pos logit contributions | |
ww | +0.005 |
www | +0.005 |
heart | +0.004 |
ons | +0.004 |
?" | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.003 |
ro | -0.003 |
isc | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
heart | +0.002 |
mber | +0.002 |
ins | +0.002 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
usual | -0.001 |
symp | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
ww | +0.013 |
www | +0.012 |
heart | +0.011 |
ons | +0.011 |
mber | +0.011 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
usual | -0.008 |
ro | -0.007 |
Token | kind |
Token ID | 1611 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.002 |
allowance | +0.002 |
usual | +0.002 |
ro | +0.002 |
Neg logit contributions | |
ww | -0.004 |
www | -0.003 |
ons | -0.003 |
heart | -0.003 |
ins | -0.003 |
Token | mail |
Token ID | 6920 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
bank | +0.014 |
ro | +0.012 |
banks | +0.012 |
allowance | +0.012 |
isc | +0.012 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
ons | -0.013 |
ins | -0.012 |
heart | -0.012 |
Token | man |
Token ID | 805 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
bank | +0.023 |
allowance | +0.021 |
banks | +0.021 |
isc | +0.020 |
ro | +0.020 |
Neg logit contributions | |
ww | -0.015 |
www | -0.013 |
heart | -0.011 |
mber | -0.010 |
imi | -0.010 |
Token | came |
Token ID | 1625 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
ww | +0.139 |
www | +0.125 |
mber | +0.112 |
heart | +0.109 |
imi | +0.108 |
Neg logit contributions | |
bank | -0.101 |
banks | -0.088 |
allowance | -0.086 |
ked | -0.076 |
buy | -0.076 |
Token | by |
Token ID | 416 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
isc | +0.004 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.009 |
mber | -0.009 |
ons | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
bank | +0.049 |
banks | +0.047 |
allowance | +0.044 |
isc | +0.041 |
ro | +0.038 |
Neg logit contributions | |
ww | -0.063 |
www | -0.056 |
?" | -0.052 |
heart | -0.052 |
ons | -0.051 |
Token | The |
Token ID | 383 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.005 |
ons | +0.004 |
mber | +0.004 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
ro | -0.003 |
isc | -0.003 |
Token | mail |
Token ID | 6920 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.018 |
allowance | +0.017 |
ro | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.017 |
www | -0.014 |
heart | -0.013 |
ons | -0.012 |
mber | -0.012 |
Token | Andy |
Token ID | 12382 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
isc | +0.008 |
ro | +0.008 |
Neg logit contributions | |
ww | -0.013 |
www | -0.011 |
heart | -0.011 |
?" | -0.011 |
ons | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | +3.95e-03 |
Pos logit contributions | |
ww | +0.062 |
www | +0.055 |
heart | +0.052 |
ons | +0.052 |
?" | +0.050 |
Neg logit contributions | |
bank | -0.048 |
banks | -0.048 |
allowance | -0.046 |
isc | -0.041 |
ro | -0.040 |
Token | picture |
Token ID | 4286 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ww | +0.007 |
www | +0.006 |
heart | +0.006 |
ons | +0.005 |
?" | +0.005 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ww | +0.043 |
www | +0.039 |
mber | +0.035 |
heart | +0.035 |
?" | +0.034 |
Neg logit contributions | |
bank | -0.025 |
banks | -0.023 |
allowance | -0.022 |
ro | -0.020 |
isc | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
ww | +0.028 |
www | +0.025 |
w | +0.024 |
course | +0.024 |
ons | +0.023 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.010 |
isc | -0.010 |
ro | -0.008 |
urd | -0.008 |
Token | Andy |
Token ID | 35314 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
tted | +0.003 |
banks | +0.003 |
bank | +0.003 |
side | +0.003 |
urd | +0.003 |
Neg logit contributions | |
ww | -0.003 |
heart | -0.003 |
yours | -0.003 |
www | -0.003 |
ries | -0.003 |
Token | looked |
Token ID | 3114 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
ww | +0.138 |
www | +0.121 |
heart | +0.109 |
loo | +0.109 |
mber | +0.107 |
Neg logit contributions | |
bank | -0.100 |
banks | -0.094 |
allowance | -0.086 |
ro | -0.079 |
symp | -0.078 |
Token | at |
Token ID | 379 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.009 |
allowance | +0.008 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.009 |
?" | -0.009 |
ons | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ww | +0.045 |
www | +0.040 |
heart | +0.036 |
ons | +0.035 |
?" | +0.035 |
Neg logit contributions | |
bank | -0.042 |
banks | -0.040 |
allowance | -0.038 |
ro | -0.034 |
isc | -0.034 |
Token | freshly |
Token ID | 29026 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ww | +0.022 |
www | +0.019 |
heart | +0.017 |
ons | +0.017 |
?" | +0.016 |
Neg logit contributions | |
bank | -0.023 |
banks | -0.022 |
allowance | -0.021 |
ro | -0.019 |
isc | -0.019 |
Token | printed |
Token ID | 10398 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
bank | +0.048 |
banks | +0.045 |
allowance | +0.042 |
ro | +0.038 |
usual | +0.037 |
Neg logit contributions | |
ww | -0.055 |
www | -0.048 |
heart | -0.045 |
mber | -0.043 |
?" | -0.041 |
Token | believe |
Token ID | 1975 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
?" | +0.020 |
? | +0.019 |
ww | +0.019 |
www | +0.018 |
ull | +0.017 |
Neg logit contributions | |
banks | -0.019 |
bank | -0.019 |
isc | -0.017 |
allowance | -0.017 |
side | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ww | +0.012 |
www | +0.011 |
ons | +0.009 |
mber | +0.009 |
heart | +0.009 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.010 |
allowance | -0.010 |
symp | -0.010 |
ro | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
ww | +0.021 |
www | +0.019 |
heart | +0.017 |
ons | +0.017 |
?" | +0.017 |
Neg logit contributions | |
bank | -0.015 |
banks | -0.014 |
allowance | -0.013 |
isc | -0.012 |
ro | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
heart | +0.004 |
ons | +0.004 |
mber | +0.003 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
ro | -0.003 |
symp | -0.003 |
Token | took |
Token ID | 1718 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
ww | +0.017 |
www | +0.015 |
heart | +0.014 |
loo | +0.013 |
ons | +0.013 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.010 |
ro | -0.010 |
symp | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.009 |
heart | +0.008 |
ons | +0.008 |
?" | +0.008 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.009 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | ring |
Token ID | 5858 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ww | +0.026 |
www | +0.022 |
heart | +0.020 |
mber | +0.019 |
ons | +0.019 |
Neg logit contributions | |
bank | -0.030 |
banks | -0.029 |
allowance | -0.027 |
ro | -0.025 |
isc | -0.025 |
Token | from |
Token ID | 422 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
heart | +0.012 |
ons | +0.012 |
?" | +0.012 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.010 |
allowance | -0.009 |
isc | -0.008 |
ro | -0.008 |
Token | Anna |
Token ID | 11735 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
bank | +0.067 |
banks | +0.064 |
allowance | +0.061 |
ro | +0.056 |
usual | +0.056 |
Neg logit contributions | |
ww | -0.066 |
www | -0.057 |
heart | -0.050 |
ons | -0.048 |
mber | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
ww | +0.017 |
www | +0.015 |
ons | +0.015 |
?" | +0.014 |
heart | +0.014 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.014 |
allowance | -0.013 |
urd | -0.012 |
isc | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
ww | +0.014 |
www | +0.013 |
heart | +0.012 |
loo | +0.011 |
mber | +0.011 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.010 |
allowance | -0.010 |
ro | -0.009 |
ked | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
?" | +0.009 |
ons | +0.009 |
? | +0.008 |
Neg logit contributions | |
bank | -0.009 |
banks | -0.009 |
allowance | -0.008 |
symp | -0.008 |
ro | -0.008 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
bank | +0.014 |
allowance | +0.013 |
banks | +0.013 |
properly | +0.011 |
usual | +0.011 |
Neg logit contributions | |
ww | -0.024 |
www | -0.022 |
heart | -0.021 |
mber | -0.021 |
loo | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.023 |
allowance | +0.022 |
ro | +0.019 |
anymore | +0.018 |
Neg logit contributions | |
ww | -0.033 |
www | -0.029 |
mber | -0.027 |
heart | -0.027 |
ons | -0.026 |
Token | You |
Token ID | 921 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
bank | +0.026 |
banks | +0.025 |
allowance | +0.023 |
ro | +0.022 |
isc | +0.022 |
Neg logit contributions | |
ww | -0.017 |
www | -0.014 |
heart | -0.012 |
?" | -0.012 |
ons | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ww | +0.016 |
www | +0.014 |
heart | +0.013 |
ons | +0.013 |
mber | +0.013 |
Neg logit contributions | |
bank | -0.010 |
banks | -0.010 |
allowance | -0.009 |
ro | -0.008 |
isc | -0.008 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
bank | +0.014 |
allowance | +0.013 |
banks | +0.012 |
usual | +0.011 |
properly | +0.011 |
Neg logit contributions | |
ww | -0.024 |
heart | -0.021 |
www | -0.021 |
mber | -0.020 |
loo | -0.019 |
Token | ." |
Token ID | 526 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
ww | +0.059 |
www | +0.054 |
mber | +0.050 |
ons | +0.048 |
heart | +0.048 |
Neg logit contributions | |
bank | -0.028 |
banks | -0.027 |
allowance | -0.025 |
anymore | -0.024 |
ro | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
bank | +0.027 |
banks | +0.026 |
allowance | +0.024 |
isc | +0.022 |
ro | +0.022 |
Neg logit contributions | |
ww | -0.027 |
www | -0.024 |
?" | -0.022 |
ons | -0.021 |
mber | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
bank | +0.008 |
banks | +0.008 |
allowance | +0.007 |
ro | +0.006 |
isc | +0.006 |
Neg logit contributions | |
ww | -0.010 |
www | -0.008 |
ons | -0.008 |
?" | -0.008 |
heart | -0.008 |
Token | Max |
Token ID | 11518 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
ro | +0.004 |
tted | +0.004 |
Neg logit contributions | |
ww | -0.007 |
heart | -0.006 |
www | -0.006 |
loo | -0.006 |
mber | -0.006 |
Token | cannot |
Token ID | 2314 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
bank | +0.028 |
banks | +0.027 |
allowance | +0.025 |
ro | +0.023 |
symp | +0.023 |
Neg logit contributions | |
ww | -0.028 |
www | -0.024 |
heart | -0.022 |
mber | -0.021 |
ons | -0.021 |
Token | I |
Token ID | 314 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ww | +0.005 |
ons | +0.004 |
www | +0.004 |
w | +0.004 |
loo | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.003 |
isc | -0.003 |
allowance | -0.003 |
ro | -0.003 |
Token | wish |
Token ID | 4601 |
Feature activation | -6.10e-04 |
Pos logit contributions | |
ww | +0.043 |
www | +0.039 |
heart | +0.035 |
?" | +0.035 |
ons | +0.034 |
Neg logit contributions | |
bank | -0.028 |
banks | -0.027 |
allowance | -0.025 |
ro | -0.022 |
isc | -0.022 |
Token | I |
Token ID | 314 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
usual | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
mber | -0.001 |
heart | -0.001 |
ons | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
ww | +0.046 |
www | +0.041 |
heart | +0.038 |
ons | +0.037 |
?" | +0.037 |
Neg logit contributions | |
bank | -0.024 |
banks | -0.023 |
allowance | -0.021 |
ro | -0.018 |
isc | -0.018 |
Token | some |
Token ID | 617 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.006 |
allowance | +0.006 |
usual | +0.006 |
injuries | +0.005 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.010 |
loo | -0.009 |
mber | -0.009 |
Token | juice |
Token ID | 13135 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.006 |
usual | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.007 |
www | -0.007 |
mber | -0.006 |
heart | -0.006 |
very | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
usual | +0.005 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.009 |
ons | -0.009 |
mber | -0.009 |
Token | â |
Token ID | 22940 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
isc | +0.002 |
ro | +0.002 |
Neg logit contributions | |
ww | -0.003 |
ons | -0.002 |
www | -0.002 |
loo | -0.002 |
ins | -0.002 |
Token | € |
Token ID | 26391 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ww | +0.076 |
www | +0.067 |
heart | +0.062 |
ons | +0.062 |
mber | +0.061 |
Neg logit contributions | |
bank | -0.049 |
banks | -0.047 |
allowance | -0.041 |
ro | -0.040 |
isc | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
bank | +0.045 |
banks | +0.043 |
allowance | +0.040 |
isc | +0.037 |
ro | +0.036 |
Neg logit contributions | |
ww | -0.058 |
www | -0.051 |
heart | -0.049 |
mber | -0.046 |
loo | -0.045 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
ww | +0.024 |
www | +0.020 |
loo | +0.019 |
ons | +0.018 |
heart | +0.018 |
Neg logit contributions | |
bank | -0.019 |
banks | -0.017 |
allowance | -0.016 |
isc | -0.015 |
ro | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.006 |
ro | +0.006 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
heart | -0.009 |
ons | -0.009 |
mber | -0.009 |
Token | You |
Token ID | 921 |
Feature activation | +8.68e-03 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.017 |
allowance | +0.016 |
isc | +0.016 |
ro | +0.016 |
Neg logit contributions | |
ww | -0.015 |
www | -0.013 |
heart | -0.012 |
ons | -0.011 |
mber | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ww | +0.017 |
www | +0.015 |
?" | +0.014 |
ons | +0.014 |
heart | +0.014 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.011 |
symp | -0.010 |
ro | -0.010 |
Token | making |
Token ID | 1642 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.012 |
allowance | +0.012 |
usual | +0.011 |
find | +0.010 |
Neg logit contributions | |
ww | -0.030 |
www | -0.027 |
heart | -0.027 |
loo | -0.025 |
mber | -0.025 |
Token | me |
Token ID | 502 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
ww | +0.016 |
www | +0.015 |
loo | +0.013 |
mber | +0.013 |
heart | +0.012 |
Neg logit contributions | |
bank | -0.015 |
banks | -0.015 |
allowance | -0.014 |
symp | -0.012 |
usual | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.02e-03 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.005 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.008 |
ons | -0.007 |
mber | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
anymore | +0.005 |
allowance | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.015 |
www | -0.014 |
mber | -0.013 |
ons | -0.012 |
Charlie | -0.012 |
Token | And |
Token ID | 843 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
bank | +0.020 |
allowance | +0.019 |
banks | +0.019 |
isc | +0.019 |
ro | +0.018 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
heart | -0.013 |
ons | -0.012 |
mber | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.003 |
loo | +0.003 |
ons | +0.003 |
heart | +0.003 |
Neg logit contributions | |
bank | -0.006 |
allowance | -0.006 |
banks | -0.006 |
ro | -0.005 |
usual | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.007 |
symp | +0.006 |
isc | +0.006 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
?" | -0.007 |
ons | -0.007 |
heart | -0.007 |
Token | making |
Token ID | 1642 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
bank | +0.012 |
allowance | +0.010 |
banks | +0.010 |
find | +0.010 |
usual | +0.010 |
Neg logit contributions | |
ww | -0.031 |
www | -0.029 |
heart | -0.028 |
loo | -0.027 |
mber | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
bank | +0.000 |
allowance | +0.000 |
banks | +0.000 |
symp | +0.000 |
until | +0.000 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
ons | -0.001 |
mber | -0.001 |
heart | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ww | +0.031 |
www | +0.028 |
heart | +0.028 |
mber | +0.027 |
loo | +0.025 |
Neg logit contributions | |
bank | -0.021 |
injuries | -0.019 |
banks | -0.019 |
allowance | -0.018 |
separate | -0.018 |
Token | fun |
Token ID | 1257 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
ww | +0.020 |
www | +0.018 |
mber | +0.017 |
heart | +0.016 |
ons | +0.016 |
Neg logit contributions | |
bank | -0.016 |
banks | -0.015 |
allowance | -0.015 |
usual | -0.013 |
bottom | -0.013 |
Token | ," |
Token ID | 553 |
Feature activation | -5.13e-04 |
Pos logit contributions | |
ww | +0.012 |
mber | +0.012 |
www | +0.011 |
P | +0.011 |
Charlie | +0.011 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.007 |
anymore | -0.007 |
allowance | -0.007 |
until | -0.006 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
allowance | +0.001 |
bank | +0.001 |
banks | +0.001 |
usual | +0.001 |
symp | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
mber | -0.001 |
ons | -0.001 |
Token | says |
Token ID | 1139 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
ww | +0.028 |
www | +0.024 |
loo | +0.020 |
heart | +0.020 |
mber | +0.019 |
Neg logit contributions | |
bank | -0.029 |
banks | -0.028 |
allowance | -0.026 |
find | -0.023 |
symp | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
bank | +0.013 |
banks | +0.013 |
allowance | +0.011 |
isc | +0.010 |
ro | +0.010 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
?" | -0.013 |
ons | -0.013 |
heart | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.004 |
allowance | +0.004 |
ro | +0.004 |
until | +0.004 |
Neg logit contributions | |
ww | -0.014 |
www | -0.013 |
heart | -0.013 |
ons | -0.012 |
w | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.004 |
allowance | +0.003 |
ro | +0.003 |
symp | +0.003 |
Neg logit contributions | |
ww | -0.008 |
www | -0.008 |
heart | -0.007 |
mber | -0.007 |
ons | -0.007 |
Token | They |
Token ID | 2990 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
ro | +0.004 |
allowance | +0.004 |
tted | +0.004 |
Neg logit contributions | |
ww | -0.004 |
www | -0.004 |
heart | -0.004 |
mber | -0.003 |
ons | -0.003 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
?" | +0.009 |
heart | +0.009 |
ons | +0.009 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.007 |
ro | -0.006 |
isc | -0.006 |
Token | will |
Token ID | 481 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
ww | +0.028 |
www | +0.024 |
?" | +0.023 |
? | +0.021 |
heart | +0.021 |
Neg logit contributions | |
banks | -0.025 |
bank | -0.025 |
allowance | -0.023 |
symp | -0.021 |
usual | -0.021 |
Token | teach |
Token ID | 4545 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
bank | +0.024 |
banks | +0.022 |
allowance | +0.021 |
ro | +0.018 |
isc | +0.017 |
Neg logit contributions | |
ww | -0.042 |
www | -0.037 |
heart | -0.035 |
mber | -0.034 |
ons | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
bank | +0.037 |
allowance | +0.036 |
banks | +0.036 |
anymore | +0.033 |
usual | +0.033 |
Neg logit contributions | |
ww | -0.028 |
www | -0.024 |
loo | -0.021 |
mber | -0.021 |
aver | -0.020 |
Token | some |
Token ID | 617 |
Feature activation | -8.59e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.008 |
allowance | +0.008 |
ro | +0.007 |
usual | +0.007 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
mber | -0.009 |
heart | -0.009 |
ons | -0.008 |
Token | songs |
Token ID | 7259 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
bank | +0.013 |
allowance | +0.012 |
banks | +0.012 |
ro | +0.011 |
usual | +0.010 |
Neg logit contributions | |
ww | -0.017 |
www | -0.015 |
mber | -0.014 |
heart | -0.014 |
very | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ww | +0.019 |
www | +0.018 |
heart | +0.016 |
mber | +0.016 |
ons | +0.015 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.008 |
allowance | -0.007 |
ro | -0.007 |
anymore | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
bank | +0.012 |
banks | +0.012 |
allowance | +0.011 |
ro | +0.010 |
symp | +0.010 |
Neg logit contributions | |
ww | -0.024 |
www | -0.022 |
heart | -0.020 |
ons | -0.019 |
loo | -0.019 |
Token | lifts |
Token ID | 27103 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.004 |
heart | +0.003 |
mber | +0.003 |
ons | +0.003 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.004 |
ro | -0.003 |
isc | -0.003 |
Token | Anna |
Token ID | 11735 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.008 |
allowance | +0.008 |
isc | +0.007 |
ro | +0.007 |
Neg logit contributions | |
ww | -0.007 |
www | -0.006 |
?" | -0.005 |
heart | -0.005 |
ons | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
ww | +0.005 |
www | +0.004 |
ons | +0.004 |
?" | +0.004 |
my | +0.004 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.004 |
allowance | -0.004 |
isc | -0.003 |
usual | -0.003 |
Token | puts |
Token ID | 7584 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
heart | +0.002 |
mber | +0.002 |
loo | +0.002 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
ro | -0.002 |
symp | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ww | +0.004 |
ons | +0.004 |
www | +0.004 |
heart | +0.003 |
ins | +0.003 |
Neg logit contributions | |
bank | -0.004 |
banks | -0.003 |
ro | -0.003 |
allowance | -0.003 |
symp | -0.003 |
Token | named |
Token ID | 3706 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
ww | +0.017 |
www | +0.014 |
heart | +0.012 |
ons | +0.012 |
?" | +0.011 |
Neg logit contributions | |
bank | -0.025 |
banks | -0.024 |
allowance | -0.023 |
ro | -0.021 |
isc | -0.021 |
Token | Av |
Token ID | 5184 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ww | +0.011 |
www | +0.010 |
?" | +0.009 |
heart | +0.008 |
ons | +0.008 |
Neg logit contributions | |
bank | -0.014 |
banks | -0.014 |
allowance | -0.013 |
isc | -0.012 |
ro | -0.012 |
Token | a |
Token ID | 64 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
bank | +0.047 |
banks | +0.046 |
allowance | +0.043 |
isc | +0.039 |
injuries | +0.039 |
Neg logit contributions | |
ww | -0.034 |
www | -0.028 |
?" | -0.027 |
mber | -0.026 |
ons | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
bank | +0.034 |
banks | +0.033 |
allowance | +0.032 |
isc | +0.028 |
ro | +0.028 |
Neg logit contributions | |
ww | -0.040 |
?" | -0.035 |
www | -0.035 |
? | -0.033 |
ons | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
bank | +0.022 |
banks | +0.021 |
allowance | +0.020 |
injuries | +0.020 |
isc | +0.018 |
Neg logit contributions | |
ww | -0.020 |
www | -0.017 |
?" | -0.017 |
mber | -0.016 |
heart | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.014 |
allowance | +0.013 |
ro | +0.012 |
isc | +0.012 |
Neg logit contributions | |
ww | -0.019 |
www | -0.017 |
heart | -0.015 |
ons | -0.015 |
mber | -0.015 |
Token | only |
Token ID | 691 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
ww | +0.003 |
www | +0.003 |
heart | +0.002 |
?" | +0.002 |
ons | +0.002 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
ro | -0.002 |
isc | -0.002 |
Token | three |
Token ID | 1115 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
bank | +0.039 |
banks | +0.039 |
allowance | +0.033 |
side | +0.032 |
symp | +0.031 |
Neg logit contributions | |
ww | -0.050 |
www | -0.043 |
heart | -0.040 |
my | -0.040 |
mber | -0.039 |
Token | years |
Token ID | 812 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
bank | +0.053 |
banks | +0.051 |
allowance | +0.048 |
isc | +0.045 |
ro | +0.045 |
Neg logit contributions | |
ww | -0.045 |
www | -0.039 |
heart | -0.035 |
ons | -0.034 |
?" | -0.034 |
Token | old |
Token ID | 1468 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
bank | +0.030 |
banks | +0.029 |
allowance | +0.027 |
ro | +0.024 |
isc | +0.024 |
Neg logit contributions | |
ww | -0.040 |
www | -0.036 |
heart | -0.032 |
ons | -0.032 |
mber | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
bank | +0.023 |
banks | +0.023 |
allowance | +0.021 |
isc | +0.020 |
tted | +0.019 |
Neg logit contributions | |
ww | -0.023 |
www | -0.020 |
?" | -0.019 |
heart | -0.019 |
? | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -4.00e-04 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
contain | +0.004 |
injuries | +0.004 |
Neg logit contributions | |
ww | -0.004 |
www | -0.004 |
heart | -0.003 |
?" | -0.003 |
mber | -0.003 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.46e-03 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.000 |
ro | +0.000 |
isc | +0.000 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.001 |
mber | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.006 |
allowance | +0.006 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.007 |
?" | -0.007 |
ons | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ww | +0.048 |
www | +0.042 |
heart | +0.038 |
ons | +0.037 |
?" | +0.037 |
Neg logit contributions | |
bank | -0.046 |
banks | -0.044 |
allowance | -0.042 |
ro | -0.038 |
isc | -0.038 |
Token | mark |
Token ID | 1317 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ww | +0.021 |
www | +0.019 |
heart | +0.016 |
ons | +0.016 |
mber | +0.016 |
Neg logit contributions | |
bank | -0.023 |
banks | -0.022 |
allowance | -0.021 |
ro | -0.019 |
isc | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.014 |
allowance | +0.013 |
ro | +0.012 |
symp | +0.011 |
Neg logit contributions | |
ww | -0.021 |
www | -0.019 |
heart | -0.017 |
mber | -0.016 |
ons | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
ww | +0.005 |
www | +0.005 |
heart | +0.004 |
?" | +0.004 |
ons | +0.004 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.005 |
isc | -0.005 |
ro | -0.005 |
Token | knee |
Token ID | 10329 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ww | +0.004 |
?" | +0.003 |
? | +0.003 |
my | +0.003 |
www | +0.003 |
Neg logit contributions | |
bank | -0.003 |
banks | -0.003 |
allowance | -0.003 |
urd | -0.003 |
tted | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +9.29e-04 |
Pos logit contributions | |
banks | +0.061 |
bank | +0.061 |
allowance | +0.059 |
isc | +0.053 |
symp | +0.052 |
Neg logit contributions | |
ww | -0.063 |
www | -0.054 |
?" | -0.050 |
ons | -0.050 |
heart | -0.050 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
ww | +0.002 |
www | +0.002 |
loo | +0.002 |
heart | +0.002 |
ons | +0.002 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
usual | -0.001 |
ro | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +5.49e-04 |
Pos logit contributions | |
bank | +0.018 |
banks | +0.018 |
allowance | +0.017 |
ro | +0.015 |
isc | +0.015 |
Neg logit contributions | |
ww | -0.025 |
www | -0.022 |
heart | -0.021 |
ons | -0.020 |
mber | -0.020 |
Token | going |
Token ID | 1016 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
heart | +0.001 |
ons | +0.001 |
mber | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
usual | -0.001 |
isc | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.002 |
isc | +0.002 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
heart | -0.006 |
mber | -0.006 |
ons | -0.006 |
Token | meet |
Token ID | 1826 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.006 |
ro | +0.005 |
isc | +0.005 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
heart | -0.007 |
ons | -0.007 |
mber | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
bank | +0.023 |
banks | +0.022 |
allowance | +0.021 |
isc | +0.018 |
ro | +0.018 |
Neg logit contributions | |
ww | -0.028 |
www | -0.024 |
heart | -0.022 |
ons | -0.021 |
mber | -0.021 |
Token | prince |
Token ID | 19716 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.007 |
usual | +0.006 |
isc | +0.006 |
Neg logit contributions | |
ww | -0.010 |
www | -0.009 |
heart | -0.009 |
ons | -0.009 |
loo | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-05 |
Pos logit contributions | |
bank | +0.011 |
banks | +0.010 |
allowance | +0.010 |
ro | +0.008 |
isc | +0.008 |
Neg logit contributions | |
ww | -0.021 |
www | -0.019 |
heart | -0.017 |
mber | -0.017 |
ons | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
bank | +0.000 |
banks | +0.000 |
allowance | +0.000 |
injuries | +0.000 |
ro | +0.000 |
Neg logit contributions | |
ww | -0.000 |
www | -0.000 |
?" | -0.000 |
heart | -0.000 |
mber | -0.000 |
Token | put |
Token ID | 1234 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
bank | +0.002 |
banks | +0.002 |
allowance | +0.002 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.003 |
www | -0.002 |
heart | -0.002 |
ons | -0.002 |
loo | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
ww | +0.018 |
www | +0.017 |
heart | +0.015 |
loo | +0.015 |
mber | +0.015 |
Neg logit contributions | |
bank | -0.010 |
allowance | -0.009 |
banks | -0.009 |
usual | -0.008 |
isc | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +3.76e-03 |
Pos logit contributions | |
ww | +0.006 |
www | +0.005 |
heart | +0.004 |
ons | +0.004 |
mber | +0.004 |
Neg logit contributions | |
bank | -0.006 |
banks | -0.006 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
bank | +0.003 |
until | +0.002 |
anymore | +0.002 |
banks | +0.002 |
after | +0.002 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
igator | -0.008 |
loo | -0.008 |
rooms | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
bank | +0.020 |
banks | +0.019 |
allowance | +0.018 |
ro | +0.017 |
isc | +0.017 |
Neg logit contributions | |
ww | -0.015 |
www | -0.012 |
heart | -0.011 |
ons | -0.010 |
mber | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | -6.86e-03 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.014 |
allowance | +0.013 |
ro | +0.011 |
isc | +0.011 |
Neg logit contributions | |
ww | -0.025 |
www | -0.022 |
heart | -0.020 |
ons | -0.020 |
loo | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.010 |
allowance | +0.009 |
ro | +0.008 |
usual | +0.008 |
Neg logit contributions | |
ww | -0.013 |
www | -0.012 |
heart | -0.011 |
ons | -0.010 |
loo | -0.010 |
Token | clean |
Token ID | 3424 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
bank | +0.015 |
banks | +0.014 |
allowance | +0.014 |
ro | +0.012 |
isc | +0.012 |
Neg logit contributions | |
ww | -0.018 |
www | -0.015 |
heart | -0.014 |
ons | -0.014 |
mber | -0.013 |
Token | plate |
Token ID | 7480 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
bank | +0.034 |
banks | +0.032 |
allowance | +0.030 |
ro | +0.027 |
isc | +0.027 |
Neg logit contributions | |
ww | -0.043 |
www | -0.038 |
heart | -0.034 |
ons | -0.034 |
mber | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.019 |
allowance | +0.018 |
ro | +0.017 |
usual | +0.016 |
Neg logit contributions | |
ww | -0.037 |
www | -0.033 |
heart | -0.030 |
mber | -0.030 |
ons | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
bank | +0.006 |
allowance | +0.005 |
banks | +0.005 |
usual | +0.005 |
ro | +0.004 |
Neg logit contributions | |
ww | -0.008 |
www | -0.007 |
heart | -0.007 |
mber | -0.007 |
loo | -0.007 |
Token | full |
Token ID | 1336 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.015 |
allowance | +0.015 |
ro | +0.013 |
isc | +0.013 |
Neg logit contributions | |
ww | -0.019 |
www | -0.017 |
heart | -0.016 |
ons | -0.015 |
mber | -0.015 |
Token | tum |
Token ID | 11814 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
allowance | +0.008 |
usual | +0.007 |
ro | +0.007 |
Neg logit contributions | |
ww | -0.017 |
www | -0.015 |
ons | -0.014 |
heart | -0.014 |
ins | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
bank | +0.035 |
banks | +0.034 |
allowance | +0.032 |
ro | +0.031 |
isc | +0.031 |
Neg logit contributions | |
ww | -0.019 |
www | -0.015 |
mber | -0.012 |
heart | -0.011 |
ons | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -7.90e-04 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.005 |
allowance | +0.005 |
ro | +0.004 |
isc | +0.004 |
Neg logit contributions | |
ww | -0.011 |
www | -0.010 |
mber | -0.010 |
heart | -0.010 |
ons | -0.009 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
isc | +0.001 |
ro | +0.001 |
Neg logit contributions | |
ww | -0.002 |
www | -0.001 |
?" | -0.001 |
heart | -0.001 |
ons | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
bank | +0.025 |
banks | +0.024 |
allowance | +0.023 |
ro | +0.022 |
isc | +0.021 |
Neg logit contributions | |
ww | -0.020 |
www | -0.017 |
loo | -0.015 |
mber | -0.015 |
heart | -0.014 |
Token | make |
Token ID | 787 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
ro | +0.002 |
buy | +0.002 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
mber | -0.005 |
heart | -0.005 |
loo | -0.005 |
Token | grow |
Token ID | 1663 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
symp | +0.003 |
isc | +0.003 |
Neg logit contributions | |
ww | -0.002 |
www | -0.002 |
mber | -0.002 |
loo | -0.002 |
heart | -0.002 |
Token | l |
Token ID | 75 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.015 |
ro | +0.014 |
isc | +0.014 |
Neg logit contributions | |
ww | -0.020 |
www | -0.018 |
heart | -0.016 |
?" | -0.016 |
ons | -0.016 |
Token | grow |
Token ID | 1663 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
bank | +0.123 |
banks | +0.118 |
allowance | +0.109 |
ro | +0.098 |
isc | +0.096 |
Neg logit contributions | |
ww | -0.181 |
www | -0.162 |
heart | -0.146 |
mber | -0.145 |
ons | -0.143 |
Token | l |
Token ID | 75 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
bank | +0.017 |
banks | +0.016 |
allowance | +0.015 |
ro | +0.014 |
isc | +0.014 |
Neg logit contributions | |
ww | -0.020 |
www | -0.017 |
heart | -0.016 |
?" | -0.015 |
ons | -0.015 |
Token | sounds |
Token ID | 5238 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
bank | +0.126 |
banks | +0.120 |
allowance | +0.113 |
ro | +0.100 |
isc | +0.100 |
Neg logit contributions | |
ww | -0.178 |
www | -0.157 |
heart | -0.143 |
ons | -0.141 |
?" | -0.140 |
Token | ," |
Token ID | 553 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
ww | +0.064 |
www | +0.059 |
loo | +0.054 |
mber | +0.054 |
ons | +0.054 |
Neg logit contributions | |
bank | -0.032 |
banks | -0.030 |
allowance | -0.028 |
until | -0.026 |
anymore | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
loo | +0.008 |
ons | +0.008 |
heart | +0.008 |
Neg logit contributions | |
bank | -0.006 |
allowance | -0.006 |
banks | -0.006 |
ro | -0.005 |
usual | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.008 |
allowance | +0.008 |
ro | +0.007 |
isc | +0.007 |
Neg logit contributions | |
ww | -0.011 |
www | -0.009 |
heart | -0.008 |
ons | -0.008 |
?" | -0.008 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
bank | +0.004 |
banks | +0.004 |
allowance | +0.004 |
usual | +0.003 |
ro | +0.003 |
Neg logit contributions | |
ww | -0.006 |
www | -0.005 |
heart | -0.005 |
ons | -0.005 |
mber | -0.005 |
Token | tum |
Token ID | 11814 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.019 |
allowance | +0.019 |
ro | +0.017 |
isc | +0.016 |
Neg logit contributions | |
ww | -0.026 |
www | -0.023 |
heart | -0.021 |
ons | -0.021 |
mber | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
bank | +0.021 |
banks | +0.021 |
allowance | +0.020 |
ro | +0.019 |
isc | +0.019 |
Neg logit contributions | |
ww | -0.012 |
www | -0.009 |
mber | -0.007 |
heart | -0.007 |
ons | -0.006 |
Token | ac |
Token ID | 936 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
ww | +0.015 |
www | +0.013 |
?" | +0.012 |
ons | +0.012 |
heart | +0.012 |
Neg logit contributions | |
bank | -0.011 |
banks | -0.011 |
allowance | -0.010 |
isc | -0.010 |
urd | -0.009 |
Token | he |
Token ID | 258 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
bank | +0.054 |
banks | +0.052 |
allowance | +0.048 |
ro | +0.043 |
isc | +0.043 |
Neg logit contributions | |
ww | -0.075 |
www | -0.066 |
heart | -0.060 |
ons | -0.059 |
mber | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
bank | +0.139 |
banks | +0.130 |
allowance | +0.123 |
ro | +0.113 |
usual | +0.109 |
Neg logit contributions | |
ww | -0.184 |
www | -0.162 |
heart | -0.145 |
mber | -0.142 |
ons | -0.140 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
usual | +0.002 |
ro | +0.002 |
Neg logit contributions | |
ww | -0.004 |
www | -0.004 |
heart | -0.003 |
mber | -0.003 |
loo | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
bank | +0.019 |
banks | +0.018 |
allowance | +0.017 |
isc | +0.017 |
ro | +0.017 |
Neg logit contributions | |
ww | -0.024 |
www | -0.021 |
?" | -0.021 |
my | -0.020 |
heart | -0.020 |
Token | sick |
Token ID | 6639 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
ww | +0.004 |
www | +0.003 |
heart | +0.003 |
?" | +0.003 |
ons | +0.003 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
isc | -0.002 |
ro | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
bank | +0.009 |
banks | +0.008 |
allowance | +0.008 |
isc | +0.007 |
symp | +0.007 |
Neg logit contributions | |
ww | -0.011 |
www | -0.009 |
?" | -0.009 |
heart | -0.009 |
ons | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-05 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
?" | +0.001 |
unt | +0.001 |
ons | +0.001 |
Neg logit contributions | |
bank | -0.002 |
banks | -0.002 |
allowance | -0.002 |
contain | -0.001 |
symp | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-04 |
Pos logit contributions | |
ww | +0.000 |
www | +0.000 |
?" | +0.000 |
ons | +0.000 |
mber | +0.000 |
Neg logit contributions | |
bank | -0.000 |
banks | -0.000 |
allowance | -0.000 |
ro | -0.000 |
isc | -0.000 |
Token | Spot |
Token ID | 32565 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
ww | +0.001 |
www | +0.001 |
?" | +0.001 |
ons | +0.001 |
mber | +0.001 |
Neg logit contributions | |
bank | -0.001 |
banks | -0.001 |
allowance | -0.001 |
symp | -0.001 |
isc | -0.001 |
Token | found |
Token ID | 1043 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
bank | +0.043 |
banks | +0.041 |
allowance | +0.039 |
ro | +0.035 |
isc | +0.035 |
Neg logit contributions | |
ww | -0.052 |
www | -0.046 |
heart | -0.041 |
ons | -0.041 |
?" | -0.040 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
bank | +0.006 |
banks | +0.006 |
allowance | +0.006 |
symp | +0.005 |
ro | +0.005 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
my | -0.004 |
ons | -0.004 |
?" | -0.004 |
Token | isk |
Token ID | 1984 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
bank | +0.074 |
banks | +0.069 |
allowance | +0.068 |
symp | +0.053 |
contain | +0.053 |
Neg logit contributions | |
ww | -0.145 |
www | -0.131 |
ons | -0.124 |
imi | -0.122 |
heart | -0.121 |
Token | ers |
Token ID | 364 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
bank | +0.241 |
banks | +0.229 |
allowance | +0.212 |
ro | +0.206 |
tted | +0.199 |
Neg logit contributions | |
ww | -0.246 |
www | -0.214 |
heart | -0.195 |
?" | -0.188 |
mber | -0.183 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
bank | +0.010 |
banks | +0.009 |
allowance | +0.009 |
isc | +0.009 |
ro | +0.008 |
Neg logit contributions | |
ww | -0.009 |
www | -0.008 |
ons | -0.008 |
?" | -0.008 |
? | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
ww | +0.006 |
www | +0.006 |
heart | +0.005 |
loo | +0.005 |
mber | +0.005 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.005 |
allowance | -0.005 |
ro | -0.004 |
isc | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
bank | +0.005 |
banks | +0.005 |
allowance | +0.005 |
ro | +0.004 |
isc | +0.004 |
Neg logit contributions | |
ww | -0.006 |
www | -0.006 |
heart | -0.005 |
ons | -0.005 |
mber | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ww | +0.010 |
www | +0.009 |
heart | +0.008 |
ons | +0.008 |
mber | +0.008 |
Neg logit contributions | |
bank | -0.008 |
banks | -0.008 |
allowance | -0.007 |
ro | -0.007 |
isc | -0.007 |
Token | book |
Token ID | 1492 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
bank | +0.014 |
banks | +0.013 |
allowance | +0.013 |
ro | +0.012 |
isc | +0.012 |
Neg logit contributions | |
ww | -0.010 |
www | -0.008 |
heart | -0.007 |
ons | -0.007 |
mber | -0.007 |
Token | falls |
Token ID | 8953 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
ww | +0.042 |
www | +0.037 |
heart | +0.033 |
mber | +0.032 |
ons | +0.032 |
Neg logit contributions | |
bank | -0.042 |
banks | -0.040 |
allowance | -0.039 |
ro | -0.035 |
isc | -0.034 |
Token | off |
Token ID | 572 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ww | +0.014 |
www | +0.012 |
heart | +0.011 |
?" | +0.011 |
ons | +0.011 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.012 |
allowance | -0.011 |
isc | -0.010 |
symp | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ww | +0.030 |
www | +0.027 |
heart | +0.024 |
ons | +0.024 |
?" | +0.024 |
Neg logit contributions | |
bank | -0.025 |
banks | -0.024 |
allowance | -0.023 |
isc | -0.021 |
symp | -0.020 |
Token | books |
Token ID | 3835 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
ww | +0.028 |
www | +0.024 |
my | +0.023 |
?" | +0.023 |
ons | +0.022 |
Neg logit contributions | |
banks | -0.026 |
bank | -0.025 |
allowance | -0.023 |
isc | -0.022 |
symp | -0.022 |
Token | he |
Token ID | 258 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
bank | +0.003 |
banks | +0.003 |
allowance | +0.003 |
isc | +0.003 |
symp | +0.003 |
Neg logit contributions | |
ww | -0.005 |
www | -0.004 |
ons | -0.004 |
?" | -0.004 |
loo | -0.004 |
Token | lf |
Token ID | 1652 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
bank | +0.208 |
banks | +0.197 |
allowance | +0.194 |
ro | +0.189 |
usual | +0.178 |
Neg logit contributions | |
ww | -0.106 |
www | -0.084 |
heart | -0.069 |
mber | -0.064 |
ins | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
ww | +0.092 |
www | +0.082 |
ons | +0.078 |
?" | +0.076 |
loo | +0.075 |
Neg logit contributions | |
bank | -0.074 |
banks | -0.074 |
allowance | -0.069 |
isc | -0.065 |
symp | -0.062 |
Token | It |
Token ID | 632 |
Feature activation | -4.29e-04 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
?" | +0.006 |
ons | +0.006 |
mber | +0.006 |
Neg logit contributions | |
bank | -0.012 |
banks | -0.011 |
allowance | -0.011 |
uries | -0.010 |
isc | -0.010 |
Token | makes |
Token ID | 1838 |
Feature activation | -6.95e-04 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
ro | +0.001 |
isc | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
heart | -0.001 |
ons | -0.000 |
?" | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e-03 |
Pos logit contributions | |
bank | +0.001 |
banks | +0.001 |
allowance | +0.001 |
isc | +0.001 |
ro | +0.001 |
Neg logit contributions | |
ww | -0.001 |
www | -0.001 |
ons | -0.001 |
heart | -0.001 |
my | -0.001 |
Token | strange |
Token ID | 6283 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
ww | +0.031 |
www | +0.028 |
ons | +0.026 |
ins | +0.026 |
loo | +0.025 |
Neg logit contributions | |
bank | -0.017 |
banks | -0.015 |
allowance | -0.014 |
usual | -0.014 |
seem | -0.012 |
Token | happened |
Token ID | 3022 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ww | +0.014 |
www | +0.012 |
mber | +0.011 |
ins | +0.010 |
P | +0.010 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.011 |
usual | -0.011 |
ro | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ww | +0.072 |
www | +0.065 |
mber | +0.058 |
heart | +0.058 |
ons | +0.057 |
Neg logit contributions | |
bank | -0.036 |
banks | -0.034 |
allowance | -0.030 |
ro | -0.028 |
symp | -0.027 |
Token | The |
Token ID | 383 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
ww | +0.008 |
www | +0.007 |
ons | +0.006 |
heart | +0.006 |
loo | +0.006 |
Neg logit contributions | |
bank | -0.005 |
banks | -0.004 |
allowance | -0.004 |
ro | -0.004 |
isc | -0.004 |
Token | books |
Token ID | 3835 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
bank | +0.016 |
banks | +0.015 |
allowance | +0.014 |
usual | +0.013 |
ro | +0.013 |
Neg logit contributions | |
ww | -0.016 |
www | -0.014 |
ons | -0.013 |
heart | -0.013 |
mber | -0.012 |
Token | he |
Token ID | 258 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
bank | +0.007 |
banks | +0.007 |
allowance | +0.006 |
ro | +0.005 |
symp | +0.005 |
Neg logit contributions | |
ww | -0.012 |
www | -0.011 |
heart | -0.010 |
mber | -0.010 |
ons | -0.010 |
Token | lf |
Token ID | 1652 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
bank | +0.204 |
banks | +0.191 |
allowance | +0.188 |
ro | +0.183 |
usual | +0.178 |
Neg logit contributions | |
ww | -0.118 |
www | -0.093 |
heart | -0.074 |
mber | -0.065 |
yours | -0.065 |
Token | became |
Token ID | 2627 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
ww | +0.111 |
www | +0.099 |
heart | +0.088 |
mber | +0.087 |
ons | +0.086 |
Neg logit contributions | |
bank | -0.076 |
banks | -0.071 |
allowance | -0.066 |
ro | -0.059 |
symp | -0.057 |
Token | restless |
Token ID | 42537 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
ww | +0.067 |
www | +0.060 |
heart | +0.054 |
ons | +0.053 |
mber | +0.053 |
Neg logit contributions | |
bank | -0.045 |
banks | -0.043 |
allowance | -0.040 |
ro | -0.036 |
isc | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
ww | +0.018 |
www | +0.016 |
heart | +0.014 |
ons | +0.014 |
?" | +0.014 |
Neg logit contributions | |
bank | -0.013 |
banks | -0.012 |
allowance | -0.012 |
isc | -0.010 |
ro | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | -5.65e-04 |
Pos logit contributions | |
ww | +0.012 |
www | +0.011 |
heart | +0.010 |
ons | +0.009 |
mber | +0.009 |
Neg logit contributions | |
bank | -0.007 |
banks | -0.007 |
allowance | -0.006 |
ro | -0.005 |
isc | -0.005 |