TOP ACTIVATIONS
MAX = 11.677

m sorry , honey . I â
, " What 's wrong honey ?" Ana replied , "
be eh ive full of honey ! He was so happy
big bowl of sweet sticky honey . It looked so tasty
" Sure , honey , but be careful .
ing ? Are you tired honey ?" she said , smiling
" Sorry , honey , we can 't .
saw a big cup of yogurt . It was his favorite
be eh ive full of honey . He was so happy
's go have some more yogurt and play together !" Lily
liked to eat y ummy honey . One day , he
I 'm scattering the honey so I can feed the
" Don 't worry , honey ! I 'm going to
and said , " No honey , you can 't catch
said , " Yes , honey , you look very nice
he would turn into delicious honey . One day
replied , " No , honey . Let the flower bloom
sad because he wanted the honey so much , but he
the jar and have some honey ," he said to Lily
the bees started eating more honey too . They all became

MIN ACTIVATIONS
MIN = -16.296

that day on , Mag gy was never fearful of boards
board far away . Mag gy was so relieved , she
After a while , Mag gy and her friend had carried
was a bug named Bug gy . Bug gy had a
wanted to give the pig gy a gift too . But
money away in her pig gy bank every week . This
them safe in her pig gy bank . One day ,
named Bug gy . Bug gy had a lot of friends
body and a w ag gy tail . One day ,
and said , " Dog gy , stop ! You 're
ly said , " Bug gy , today was so much
Tim my had a pig gy bank that was full of
day , a little pig gy named Pe ppa went for
. But when the pig gy looked around , he saw
" The pig gy bank !" said the little
day onwards , the pig gy was thankful and more careful
the raced the s og gy race car around the bowl
a modest dog called Dog gy . One day , Dog
cookies got all s og gy and Jerry was in a
there was a generous pig gy . He wanted to give

INTERVAL 4.684 - 11.677
CONTAINS 2.697%

. Mom and Dad hear them . They are
the city . They say hello to the people and the
're the best at calling birds !" Max bark ed happily
looking . But Tommy caught him and got very upset .
y ummy sugar for the cake . The bear

INTERVAL -2.310 - 4.684
CONTAINS 83.457%

back on the scale . She and her Daddy smiled at
He found a big bowl on the floor . It was
saw a small black thing on the ground . It had
slide , swing and run on the grass . It was
little girl named Lily . Lily loved to pick flowers in

INTERVAL -9.303 - -2.310
CONTAINS 13.788%

. He will look at their eyes and give them stickers
Mom my . " Let 's go and buy another one
L ily and Ben look at each other . They feel
to land but he couldn 't reach it . He got
horse . She did not want to be punished . She

INTERVAL -16.296 - -9.303
CONTAINS 0.058%

that the people in the jet must feel proud too because
rabbit . The rh in oc eros explained his problem .
She pushed the red train and made it go .
and bark ed , but Wh isk ers did not care
, she was the only one rocking . Everyone around her
Token
Token ID26391
Feature activation-1.31e+00

Pos logit contributions
gy+0.519
 bank+0.421
lves+0.366
 station+0.340
zag+0.338
Neg logit contributions
 ey-0.427
ad-0.373
idges-0.358
 yogurt-0.347
ement-0.346
Token
Token ID8151
Feature activation-4.11e+00

Pos logit contributions
gy+0.120
 bank+0.101
lves+0.087
 station+0.082
 argue+0.080
Neg logit contributions
 ey-0.090
ad-0.075
 yogurt-0.074
idges-0.074
ement-0.072
Tokenm
Token ID76
Feature activation+2.39e+00

Pos logit contributions
gy+0.320
 bank+0.251
lves+0.205
 station+0.191
 drown+0.188
Neg logit contributions
 ey-0.354
idges-0.308
 yogurt-0.306
ad-0.302
ement-0.298
Token sorry
Token ID7926
Feature activation+2.23e+00

Pos logit contributions
 ey+0.186
idges+0.156
 yogurt+0.152
 honey+0.149
ement+0.147
Neg logit contributions
gy-0.214
 bank-0.168
lves-0.140
zag-0.138
 drown-0.136
Token,
Token ID11
Feature activation+5.50e-01

Pos logit contributions
 ey+0.183
idges+0.155
 yogurt+0.148
ad+0.148
ement+0.145
Neg logit contributions
gy-0.190
 bank-0.152
lves-0.123
zag-0.121
 station-0.119
Token honey
Token ID12498
Feature activation+1.13e+01

Pos logit contributions
 ey+0.040
idges+0.034
ement+0.032
ad+0.032
 yogurt+0.032
Neg logit contributions
gy-0.051
 bank-0.042
lves-0.035
 station-0.034
 drown-0.034
Token.
Token ID13
Feature activation+4.27e-02

Pos logit contributions
 ey+0.826
idges+0.697
 yogurt+0.695
 honey+0.684
ad+0.680
Neg logit contributions
gy-1.025
 bank-0.838
lves-0.731
zag-0.667
 station-0.664
Token I
Token ID314
Feature activation+3.87e+00

Pos logit contributions
 ey+0.003
idges+0.002
ad+0.002
 yogurt+0.002
ement+0.002
Neg logit contributions
gy-0.004
 bank-0.004
lves-0.003
 station-0.003
 drown-0.003
Tokenâ
Token ID22940
Feature activation-5.53e+00

Pos logit contributions
 ey+0.294
 yogurt+0.254
ad+0.252
idges+0.248
 honey+0.247
Neg logit contributions
gy-0.333
 bank-0.264
lves-0.234
zag-0.213
 station-0.210
Token
Token ID26391
Feature activation-1.59e+00

Pos logit contributions
gy+0.505
 bank+0.410
lves+0.346
zag+0.329
 station+0.328
Neg logit contributions
 ey-0.416
idges-0.349
 yogurt-0.342
ad-0.335
 honey-0.334
Token
Token ID8151
Feature activation-4.79e+00

Pos logit contributions
gy+0.133
 bank+0.114
lves+0.097
 station+0.089
 drown+0.086
Neg logit contributions
 ey-0.115
 yogurt-0.101
 goodness-0.101
idges-0.099
ad-0.098
Token,
Token ID11
Feature activation+5.89e-01

Pos logit contributions
 ey+0.024
idges+0.020
ement+0.019
ad+0.019
 yogurt+0.019
Neg logit contributions
gy-0.036
 bank-0.029
 station-0.025
lves-0.024
zag-0.024
Token "
Token ID366
Feature activation+2.74e+00

Pos logit contributions
 ey+0.044
idges+0.037
ad+0.036
ement+0.036
 yogurt+0.035
Neg logit contributions
gy-0.053
 bank-0.044
lves-0.036
 station-0.035
 drown-0.034
TokenWhat
Token ID2061
Feature activation+7.28e+00

Pos logit contributions
 ey+0.167
idges+0.133
 yogurt+0.130
 honey+0.126
ad+0.126
Neg logit contributions
gy-0.290
 bank-0.243
lves-0.212
 station-0.203
zag-0.202
Token's
Token ID338
Feature activation-5.60e+00

Pos logit contributions
 ey+0.630
idges+0.533
ement+0.521
ad+0.519
 yogurt+0.500
Neg logit contributions
gy-0.581
 bank-0.457
 fight-0.361
 argue-0.359
 station-0.358
Token wrong
Token ID2642
Feature activation-2.72e-01

Pos logit contributions
gy+0.505
 bank+0.409
lves+0.344
 station+0.326
zag+0.324
Neg logit contributions
 ey-0.433
idges-0.363
ad-0.351
 yogurt-0.350
ement-0.346
Token honey
Token ID12498
Feature activation+1.12e+01

Pos logit contributions
gy+0.027
 bank+0.022
lves+0.018
 station+0.018
zag+0.018
Neg logit contributions
 ey-0.019
idges-0.016
ad-0.015
 yogurt-0.015
ement-0.015
Token?"
Token ID1701
Feature activation+1.24e+00

Pos logit contributions
 ey+0.739
idges+0.599
 yogurt+0.580
ad+0.578
ement+0.559
Neg logit contributions
gy-1.122
 bank-0.926
lves-0.791
zag-0.768
 station-0.765
Token Ana
Token ID17639
Feature activation+1.46e+00

Pos logit contributions
 ey+0.086
idges+0.072
 yogurt+0.069
ad+0.068
 honey+0.067
Neg logit contributions
gy-0.120
 bank-0.099
lves-0.084
 station-0.080
zag-0.080
Token replied
Token ID8712
Feature activation+1.60e+00

Pos logit contributions
 ey+0.115
idges+0.098
 yogurt+0.096
ad+0.093
 honey+0.093
Neg logit contributions
gy-0.127
 bank-0.103
lves-0.084
 station-0.081
 argue-0.080
Token,
Token ID11
Feature activation+8.22e-01

Pos logit contributions
 ey+0.152
idges+0.127
 yogurt+0.121
ad+0.121
ango+0.118
Neg logit contributions
gy-0.123
 bank-0.091
 neither-0.071
zag-0.069
 station-0.068
Token "
Token ID366
Feature activation+2.55e+00

Pos logit contributions
 ey+0.057
idges+0.046
 yogurt+0.044
ad+0.043
 honey+0.042
Neg logit contributions
gy-0.083
 bank-0.067
lves-0.056
 station-0.055
zag-0.055
Token be
Token ID307
Feature activation+9.14e-01

Pos logit contributions
 ey+0.049
idges+0.042
ad+0.040
 yogurt+0.040
ement+0.039
Neg logit contributions
gy-0.061
 bank-0.050
lves-0.042
 station-0.041
zag-0.040
Tokeneh
Token ID17231
Feature activation-3.51e+00

Pos logit contributions
 ey+0.068
ad+0.059
idges+0.058
 yogurt+0.058
 honey+0.056
Neg logit contributions
gy-0.080
 bank-0.066
lves-0.056
 drown-0.053
 argue-0.053
Tokenive
Token ID425
Feature activation-4.31e-01

Pos logit contributions
gy+0.296
 bank+0.235
lves+0.198
 station+0.185
 drown+0.183
Neg logit contributions
 ey-0.282
 yogurt-0.239
idges-0.239
ad-0.238
 honey-0.232
Token full
Token ID1336
Feature activation+2.14e+00

Pos logit contributions
gy+0.038
 bank+0.030
lves+0.026
zag+0.024
 station+0.024
Neg logit contributions
 ey-0.033
idges-0.028
 yogurt-0.028
ad-0.027
 honey-0.027
Token of
Token ID286
Feature activation+3.05e+00

Pos logit contributions
 ey+0.157
idges+0.125
ement+0.119
ango+0.116
ad+0.110
Neg logit contributions
gy-0.188
 bank-0.166
 station-0.132
house-0.127
 neither-0.127
Token honey
Token ID12498
Feature activation+1.11e+01

Pos logit contributions
 ey+0.225
ement+0.185
idges+0.182
ango+0.175
mmmm+0.174
Neg logit contributions
gy-0.264
 bank-0.236
lves-0.184
 drown-0.183
 fight-0.180
Token!
Token ID0
Feature activation+2.38e+00

Pos logit contributions
 ey+0.868
idges+0.723
 yogurt+0.702
ad+0.700
ement+0.682
Neg logit contributions
gy-0.993
 bank-0.803
lves-0.661
zag-0.644
 station-0.636
Token He
Token ID679
Feature activation+3.00e+00

Pos logit contributions
 ey+0.167
idges+0.138
 yogurt+0.132
ad+0.131
ement+0.130
Neg logit contributions
gy-0.230
 bank-0.189
lves-0.160
 station-0.153
zag-0.153
Token was
Token ID373
Feature activation+1.24e+00

Pos logit contributions
 ey+0.257
idges+0.221
ement+0.212
 yogurt+0.211
ad+0.209
Neg logit contributions
gy-0.246
 bank-0.199
lves-0.155
zag-0.150
 station-0.146
Token so
Token ID523
Feature activation+6.51e-01

Pos logit contributions
 ey+0.105
idges+0.090
ement+0.085
 yogurt+0.084
ad+0.083
Neg logit contributions
gy-0.104
 bank-0.082
lves-0.066
zag-0.063
 drown-0.063
Token happy
Token ID3772
Feature activation+1.15e+00

Pos logit contributions
 ey+0.060
idges+0.052
ad+0.049
ement+0.049
ango+0.047
Neg logit contributions
gy-0.048
 bank-0.037
 drown-0.030
lves-0.030
 neither-0.028
Token big
Token ID1263
Feature activation+1.72e+00

Pos logit contributions
 ey+0.088
idges+0.079
ad+0.075
ement+0.074
 yogurt+0.070
Neg logit contributions
gy-0.111
 bank-0.096
 station-0.078
lves-0.077
zag-0.075
Token bowl
Token ID9396
Feature activation+4.34e+00

Pos logit contributions
 ey+0.134
idges+0.123
ad+0.112
ango+0.112
ement+0.112
Neg logit contributions
gy-0.144
 bank-0.120
 station-0.096
 fight-0.093
lves-0.090
Token of
Token ID286
Feature activation+3.47e+00

Pos logit contributions
 ey+0.314
idges+0.261
 yogurt+0.244
 honey+0.242
ad+0.241
Neg logit contributions
gy-0.414
 bank-0.340
 station-0.278
zag-0.276
lves-0.275
Token sweet
Token ID6029
Feature activation+9.71e+00

Pos logit contributions
 ey+0.243
ango+0.216
idges+0.212
ement+0.211
lad+0.208
Neg logit contributions
 bank-0.281
gy-0.279
 fight-0.204
 station-0.204
 drown-0.199
Token sticky
Token ID23408
Feature activation+2.74e+00

Pos logit contributions
 ey+0.678
idges+0.582
ango+0.559
ad+0.537
 importantly+0.534
Neg logit contributions
gy-0.886
 bank-0.801
 fight-0.593
house-0.589
 station-0.577
Token honey
Token ID12498
Feature activation+1.11e+01

Pos logit contributions
 ey+0.201
idges+0.173
ango+0.165
 importantly+0.160
ad+0.159
Neg logit contributions
gy-0.250
 bank-0.219
 station-0.161
 fight-0.161
 neither-0.161
Token.
Token ID13
Feature activation+4.13e-01

Pos logit contributions
 ey+0.837
idges+0.702
 yogurt+0.688
ad+0.679
 honey+0.670
Neg logit contributions
gy-1.007
 bank-0.817
lves-0.689
zag-0.655
 station-0.651
Token It
Token ID632
Feature activation+1.40e+00

Pos logit contributions
 ey+0.028
idges+0.024
ad+0.022
ement+0.021
 honey+0.021
Neg logit contributions
gy-0.041
 bank-0.034
lves-0.028
 station-0.027
house-0.027
Token looked
Token ID3114
Feature activation+8.18e-01

Pos logit contributions
 ey+0.120
idges+0.101
ement+0.096
ad+0.095
 yogurt+0.094
Neg logit contributions
gy-0.118
 bank-0.094
lves-0.074
zag-0.072
 sank-0.071
Token so
Token ID523
Feature activation+5.65e-01

Pos logit contributions
 ey+0.066
ad+0.057
idges+0.056
ango+0.055
odic+0.052
Neg logit contributions
gy-0.065
 bank-0.056
lves-0.046
 neither-0.044
 away-0.042
Token tasty
Token ID25103
Feature activation+6.57e+00

Pos logit contributions
 ey+0.043
ad+0.034
ango+0.034
idges+0.033
odic+0.030
Neg logit contributions
gy-0.047
 bank-0.042
 neither-0.037
 sank-0.035
 drown-0.035
Token
Token ID198
Feature activation+2.88e-01

Pos logit contributions
 ey+0.316
 honey+0.267
 yogurt+0.267
ad+0.267
idges+0.262
Neg logit contributions
gy-0.408
 bank-0.345
lves-0.301
 station-0.279
zag-0.276
Token
Token ID198
Feature activation+5.46e-01

Pos logit contributions
 ey+0.019
idges+0.015
 yogurt+0.015
ad+0.015
 honey+0.015
Neg logit contributions
gy-0.029
 bank-0.024
lves-0.021
zag-0.020
 station-0.020
Token"
Token ID1
Feature activation-9.34e-01

Pos logit contributions
 ey+0.034
idges+0.027
 yogurt+0.027
ad+0.027
 honey+0.026
Neg logit contributions
gy-0.057
 bank-0.047
lves-0.041
zag-0.039
 station-0.039
TokenSure
Token ID19457
Feature activation+2.01e+00

Pos logit contributions
gy+0.098
 bank+0.083
lves+0.072
 station+0.069
zag+0.069
Neg logit contributions
 ey-0.057
idges-0.045
 yogurt-0.044
ad-0.043
 honey-0.043
Token,
Token ID11
Feature activation+6.35e-01

Pos logit contributions
 ey+0.160
idges+0.135
 yogurt+0.132
ad+0.130
 honey+0.128
Neg logit contributions
gy-0.175
 bank-0.141
lves-0.117
zag-0.111
 station-0.111
Token honey
Token ID12498
Feature activation+1.11e+01

Pos logit contributions
 ey+0.048
idges+0.039
ement+0.039
ad+0.037
 yogurt+0.037
Neg logit contributions
gy-0.057
 bank-0.047
lves-0.039
 station-0.039
 neither-0.037
Token,
Token ID11
Feature activation+6.10e-01

Pos logit contributions
 ey+0.887
idges+0.749
 yogurt+0.726
ad+0.717
ement+0.705
Neg logit contributions
gy-0.978
 bank-0.778
lves-0.638
zag-0.623
 station-0.617
Token but
Token ID475
Feature activation-1.28e+00

Pos logit contributions
 ey+0.044
ement+0.036
idges+0.034
ad+0.034
odic+0.032
Neg logit contributions
gy-0.056
 bank-0.046
 station-0.040
lves-0.039
 neither-0.039
Token be
Token ID307
Feature activation+4.39e-01

Pos logit contributions
gy+0.112
 bank+0.090
lves+0.074
 station+0.072
 drown+0.071
Neg logit contributions
 ey-0.102
idges-0.086
ad-0.083
ement-0.083
 yogurt-0.082
Token careful
Token ID8161
Feature activation+8.80e-01

Pos logit contributions
 ey+0.035
idges+0.029
ad+0.028
ement+0.028
 yogurt+0.028
Neg logit contributions
gy-0.039
 bank-0.031
lves-0.026
 station-0.024
 drown-0.024
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
 ey+0.071
idges+0.059
 yogurt+0.058
ad+0.057
ement+0.056
Neg logit contributions
gy-0.078
 bank-0.061
lves-0.050
zag-0.050
 station-0.049
Tokening
Token ID278
Feature activation+2.34e+00

Pos logit contributions
gy+0.033
 bank+0.028
lves+0.024
zag+0.023
 station+0.023
Neg logit contributions
 ey-0.022
idges-0.017
 yogurt-0.017
ad-0.016
ement-0.016
Token?
Token ID30
Feature activation+2.93e+00

Pos logit contributions
 ey+0.191
idges+0.163
 yogurt+0.160
ad+0.158
 honey+0.157
Neg logit contributions
gy-0.196
 bank-0.156
lves-0.130
zag-0.122
 station-0.121
Token Are
Token ID4231
Feature activation+4.19e+00

Pos logit contributions
 ey+0.206
idges+0.171
 yogurt+0.166
ad+0.163
 honey+0.163
Neg logit contributions
gy-0.281
 bank-0.231
lves-0.196
 station-0.187
zag-0.187
Token you
Token ID345
Feature activation+3.45e+00

Pos logit contributions
 ey+0.267
idges+0.206
ad+0.197
ement+0.196
 honey+0.195
Neg logit contributions
gy-0.431
 bank-0.356
lves-0.310
 neither-0.306
 drown-0.300
Token tired
Token ID10032
Feature activation-2.85e+00

Pos logit contributions
 ey+0.268
idges+0.227
 yogurt+0.224
ad+0.221
 honey+0.219
Neg logit contributions
gy-0.302
 bank-0.244
lves-0.205
zag-0.194
 station-0.193
Token honey
Token ID12498
Feature activation+1.11e+01

Pos logit contributions
gy+0.283
 bank+0.234
zag+0.195
 station+0.195
 drown+0.194
Neg logit contributions
 ey-0.192
idges-0.157
 yogurt-0.148
ement-0.147
ad-0.146
Token?"
Token ID1701
Feature activation+1.18e+00

Pos logit contributions
 ey+0.734
idges+0.597
 yogurt+0.580
ad+0.573
 honey+0.560
Neg logit contributions
gy-1.112
 bank-0.919
lves-0.788
zag-0.761
 station-0.755
Token she
Token ID673
Feature activation+3.17e-01

Pos logit contributions
 ey+0.088
idges+0.075
ement+0.069
 honey+0.069
 yogurt+0.068
Neg logit contributions
gy-0.107
 bank-0.087
lves-0.071
 neither-0.069
 station-0.069
Token said
Token ID531
Feature activation+1.38e-01

Pos logit contributions
 ey+0.031
idges+0.029
mmmm+0.027
umm+0.027
ummy+0.027
Neg logit contributions
gy-0.020
 bank-0.015
 argue-0.011
 station-0.011
 crashed-0.010
Token,
Token ID11
Feature activation+9.20e-01

Pos logit contributions
 ey+0.013
idges+0.011
 yogurt+0.010
mmmm+0.010
ad+0.010
Neg logit contributions
gy-0.011
 bank-0.008
 neither-0.006
zag-0.006
 station-0.006
Token smiling
Token ID16755
Feature activation+8.00e+00

Pos logit contributions
 ey+0.070
idges+0.059
 yogurt+0.055
ad+0.054
ement+0.054
Neg logit contributions
gy-0.085
 bank-0.067
 station-0.056
 argue-0.055
 neither-0.054
Token
Token ID198
Feature activation+2.88e-01

Pos logit contributions
 ey+0.044
ad+0.038
idges+0.037
ement+0.036
odic+0.036
Neg logit contributions
gy-0.047
 bank-0.039
 neither-0.036
 station-0.035
 drown-0.033
Token
Token ID198
Feature activation+5.46e-01

Pos logit contributions
 ey+0.019
idges+0.015
 yogurt+0.015
ad+0.015
 honey+0.015
Neg logit contributions
gy-0.029
 bank-0.024
lves-0.021
zag-0.020
 station-0.020
Token"
Token ID1
Feature activation-9.34e-01

Pos logit contributions
 ey+0.034
idges+0.027
 yogurt+0.027
ad+0.027
 honey+0.026
Neg logit contributions
gy-0.057
 bank-0.047
lves-0.041
zag-0.039
 station-0.039
TokenSorry
Token ID14385
Feature activation+2.23e+00

Pos logit contributions
gy+0.098
 bank+0.083
lves+0.072
 station+0.069
zag+0.069
Neg logit contributions
 ey-0.057
idges-0.045
 yogurt-0.044
ad-0.043
 honey-0.043
Token,
Token ID11
Feature activation+6.68e-01

Pos logit contributions
 ey+0.212
idges+0.175
ement+0.174
ad+0.168
odic+0.167
Neg logit contributions
gy-0.167
 bank-0.124
 argue-0.097
 station-0.096
 neither-0.095
Token honey
Token ID12498
Feature activation+1.11e+01

Pos logit contributions
 ey+0.045
idges+0.037
ad+0.036
 yogurt+0.036
ement+0.035
Neg logit contributions
gy-0.065
 bank-0.054
lves-0.046
 station-0.045
 drown-0.044
Token,
Token ID11
Feature activation+6.74e-01

Pos logit contributions
 ey+0.796
 honey+0.676
 yogurt+0.676
idges+0.675
ad+0.659
Neg logit contributions
gy-0.999
 bank-0.826
lves-0.725
zag-0.655
 station-0.653
Token we
Token ID356
Feature activation-3.93e+00

Pos logit contributions
 ey+0.035
ement+0.029
idges+0.028
ad+0.028
ango+0.025
Neg logit contributions
gy-0.073
 bank-0.063
 drown-0.055
 station-0.054
 neither-0.054
Token can
Token ID460
Feature activation+3.48e+00

Pos logit contributions
gy+0.361
 bank+0.292
lves+0.254
zag+0.241
 station+0.236
Neg logit contributions
 ey-0.287
 yogurt-0.246
idges-0.246
 honey-0.239
ad-0.238
Token't
Token ID470
Feature activation-4.39e+00

Pos logit contributions
 ey+0.273
idges+0.236
 yogurt+0.235
ad+0.232
 honey+0.229
Neg logit contributions
gy-0.294
 bank-0.235
lves-0.208
 station-0.186
zag-0.185
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
gy+0.403
 bank+0.326
lves+0.286
zag+0.265
 station+0.264
Neg logit contributions
 ey-0.320
idges-0.273
 yogurt-0.271
ad-0.267
 honey-0.266
Token saw
Token ID2497
Feature activation-4.72e-01

Pos logit contributions
 ey+0.118
idges+0.102
 yogurt+0.101
ad+0.100
 honey+0.099
Neg logit contributions
gy-0.112
 bank-0.088
lves-0.074
zag-0.069
 station-0.067
Token a
Token ID257
Feature activation+1.03e+00

Pos logit contributions
gy+0.041
 bank+0.034
lves+0.027
 station+0.026
 neither+0.026
Neg logit contributions
 ey-0.038
idges-0.032
ement-0.030
ummy-0.030
mmmm-0.030
Token big
Token ID1263
Feature activation+1.48e+00

Pos logit contributions
 ey+0.074
idges+0.065
ad+0.062
ement+0.061
 yogurt+0.059
Neg logit contributions
gy-0.094
 bank-0.079
lves-0.066
 station-0.065
zag-0.063
Token cup
Token ID6508
Feature activation-6.03e-01

Pos logit contributions
 ey+0.118
idges+0.104
ad+0.098
 yogurt+0.097
ement+0.097
Neg logit contributions
gy-0.126
 bank-0.102
lves-0.082
 station-0.081
 drown-0.078
Token of
Token ID286
Feature activation+3.22e+00

Pos logit contributions
gy+0.058
 bank+0.049
 station+0.041
zag+0.041
house+0.039
Neg logit contributions
 ey-0.042
idges-0.034
ad-0.031
 honey-0.031
 importantly-0.031
Token yogurt
Token ID32132
Feature activation+1.11e+01

Pos logit contributions
 ey+0.228
ement+0.206
idges+0.204
lad+0.189
ango+0.189
Neg logit contributions
gy-0.275
 bank-0.259
 station-0.205
lves-0.194
 jet-0.188
Token.
Token ID13
Feature activation+4.55e-01

Pos logit contributions
 ey+0.908
idges+0.773
ad+0.742
 honey+0.718
ement+0.718
Neg logit contributions
gy-0.934
 bank-0.768
lves-0.599
zag-0.597
 station-0.592
Token It
Token ID632
Feature activation+1.58e+00

Pos logit contributions
 ey+0.030
idges+0.026
ad+0.024
ement+0.024
 honey+0.023
Neg logit contributions
gy-0.045
 bank-0.038
lves-0.031
 station-0.031
house-0.030
Token was
Token ID373
Feature activation+1.54e+00

Pos logit contributions
 ey+0.142
idges+0.124
ement+0.116
 importantly+0.115
ad+0.115
Neg logit contributions
gy-0.126
 bank-0.100
house-0.073
zag-0.073
lves-0.072
Token his
Token ID465
Feature activation+1.28e+00

Pos logit contributions
 ey+0.125
idges+0.116
ement+0.111
odic+0.104
lad+0.104
Neg logit contributions
gy-0.119
 bank-0.103
 neither-0.078
 station-0.077
 crashed-0.074
Token favorite
Token ID4004
Feature activation-4.72e+00

Pos logit contributions
 ey+0.108
idges+0.100
ad+0.092
odic+0.091
ement+0.091
Neg logit contributions
gy-0.101
 bank-0.083
 station-0.063
 fight-0.061
zag-0.060
Token be
Token ID307
Feature activation+7.56e-01

Pos logit contributions
 ey+0.074
idges+0.063
ad+0.061
ement+0.060
 yogurt+0.059
Neg logit contributions
gy-0.096
 bank-0.080
lves-0.067
 station-0.065
zag-0.065
Tokeneh
Token ID17231
Feature activation-3.72e+00

Pos logit contributions
 ey+0.062
idges+0.053
 yogurt+0.052
ad+0.051
 honey+0.050
Neg logit contributions
gy-0.064
 bank-0.051
lves-0.043
zag-0.040
 station-0.040
Tokenive
Token ID425
Feature activation-5.50e-01

Pos logit contributions
gy+0.311
 bank+0.247
lves+0.206
 station+0.193
zag+0.192
Neg logit contributions
 ey-0.304
idges-0.259
 yogurt-0.258
ad-0.254
 honey-0.251
Token full
Token ID1336
Feature activation+1.96e+00

Pos logit contributions
gy+0.050
 bank+0.040
lves+0.035
zag+0.032
 drown+0.032
Neg logit contributions
 ey-0.041
idges-0.034
 yogurt-0.034
ad-0.033
 honey-0.033
Token of
Token ID286
Feature activation+2.91e+00

Pos logit contributions
 ey+0.147
idges+0.121
ement+0.115
ango+0.114
Jamie+0.111
Neg logit contributions
gy-0.162
 bank-0.145
 station-0.113
house-0.111
 neither-0.106
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.203
ement+0.174
idges+0.166
mmmm+0.163
ango+0.161
Neg logit contributions
gy-0.252
 bank-0.233
 drown-0.185
lves-0.181
 fight-0.179
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
 ey+0.832
idges+0.694
 yogurt+0.676
ad+0.671
ement+0.654
Neg logit contributions
gy-1.004
 bank-0.816
lves-0.683
zag-0.656
 station-0.650
Token He
Token ID679
Feature activation+2.90e+00

Pos logit contributions
 ey+0.009
idges+0.007
 yogurt+0.007
ad+0.007
ement+0.007
Neg logit contributions
gy-0.012
 bank-0.010
lves-0.009
 station-0.008
zag-0.008
Token was
Token ID373
Feature activation+1.16e+00

Pos logit contributions
 ey+0.249
idges+0.214
ement+0.206
 yogurt+0.205
ad+0.204
Neg logit contributions
gy-0.237
 bank-0.190
lves-0.150
zag-0.143
 station-0.141
Token so
Token ID523
Feature activation+5.07e-01

Pos logit contributions
 ey+0.100
idges+0.086
ement+0.081
 yogurt+0.080
ad+0.080
Neg logit contributions
gy-0.097
 bank-0.076
lves-0.061
 drown-0.058
zag-0.058
Token happy
Token ID3772
Feature activation+1.02e+00

Pos logit contributions
 ey+0.047
idges+0.041
ad+0.039
ement+0.039
ango+0.037
Neg logit contributions
gy-0.037
 bank-0.029
lves-0.023
 drown-0.023
 neither-0.022
Token's
Token ID338
Feature activation-6.08e+00

Pos logit contributions
 ey+0.078
idges+0.067
 yogurt+0.065
ad+0.065
 honey+0.064
Neg logit contributions
gy-0.072
 bank-0.057
lves-0.046
zag-0.044
 station-0.043
Token go
Token ID467
Feature activation+2.41e-01

Pos logit contributions
gy+0.494
 bank+0.390
lves+0.325
zag+0.303
 station+0.299
Neg logit contributions
 ey-0.511
idges-0.438
 yogurt-0.433
ad-0.427
 honey-0.423
Token have
Token ID423
Feature activation-3.35e+00

Pos logit contributions
 ey+0.018
 yogurt+0.016
ad+0.015
idges+0.015
 honey+0.015
Neg logit contributions
gy-0.021
 bank-0.017
lves-0.015
 drown-0.013
 neither-0.013
Token some
Token ID617
Feature activation-3.11e+00

Pos logit contributions
gy+0.284
 bank+0.239
 station+0.186
 drowned+0.186
lves+0.185
Neg logit contributions
 ey-0.277
idges-0.224
ement-0.217
ad-0.212
ango-0.210
Token more
Token ID517
Feature activation+1.92e+00

Pos logit contributions
gy+0.267
 bank+0.248
 station+0.200
 fight+0.196
 drown+0.187
Neg logit contributions
 ey-0.228
idges-0.181
ad-0.178
ango-0.178
ement-0.174
Token yogurt
Token ID32132
Feature activation+1.10e+01

Pos logit contributions
 ey+0.131
idges+0.109
ad+0.105
ement+0.102
ango+0.100
Neg logit contributions
gy-0.183
 bank-0.158
 station-0.127
lves-0.126
 argue-0.125
Token and
Token ID290
Feature activation-2.20e-01

Pos logit contributions
 ey+0.791
 yogurt+0.667
idges+0.663
 honey+0.645
ad+0.641
Neg logit contributions
gy-1.020
 bank-0.827
lves-0.715
zag-0.669
 drown-0.667
Token play
Token ID711
Feature activation+1.26e+00

Pos logit contributions
gy+0.019
 bank+0.016
 station+0.012
 neither+0.012
 argue+0.012
Neg logit contributions
 ey-0.018
idges-0.015
ement-0.015
ad-0.014
ango-0.014
Token together
Token ID1978
Feature activation-3.46e+00

Pos logit contributions
 ey+0.113
idges+0.093
ad+0.090
ement+0.087
 importantly+0.087
Neg logit contributions
gy-0.097
 bank-0.081
lves-0.061
 station-0.061
house-0.060
Token!"
Token ID2474
Feature activation+2.96e-01

Pos logit contributions
gy+0.304
 bank+0.246
lves+0.204
zag+0.196
 station+0.194
Neg logit contributions
 ey-0.273
idges-0.228
 yogurt-0.223
ad-0.221
 honey-0.217
Token Lily
Token ID20037
Feature activation-1.87e+00

Pos logit contributions
 ey+0.020
idges+0.016
 yogurt+0.016
ad+0.016
 honey+0.016
Neg logit contributions
gy-0.029
 bank-0.024
lves-0.021
zag-0.020
 station-0.020
Token liked
Token ID8288
Feature activation+2.11e+00

Pos logit contributions
gy+0.101
 bank+0.081
lves+0.067
zag+0.063
 station+0.063
Neg logit contributions
 ey-0.099
idges-0.084
 yogurt-0.083
ad-0.082
 honey-0.081
Token to
Token ID284
Feature activation+1.23e+00

Pos logit contributions
 ey+0.200
ement+0.172
idges+0.169
mmmm+0.164
ad+0.163
Neg logit contributions
gy-0.156
 bank-0.124
lves-0.090
 station-0.090
 fight-0.089
Token eat
Token ID4483
Feature activation+2.17e+00

Pos logit contributions
 ey+0.111
idges+0.096
 yogurt+0.093
ement+0.093
ad+0.091
Neg logit contributions
gy-0.095
 bank-0.075
lves-0.058
zag-0.056
 station-0.056
Token y
Token ID331
Feature activation+4.71e+00

Pos logit contributions
 ey+0.169
idges+0.139
ement+0.134
ad+0.132
 importantly+0.130
Neg logit contributions
gy-0.184
 bank-0.173
 banks-0.124
lves-0.122
 station-0.121
Tokenummy
Token ID13513
Feature activation+9.03e+00

Pos logit contributions
 ey+0.191
Jamie+0.126
idges+0.120
lad+0.115
Adam+0.113
Neg logit contributions
gy-0.569
 bank-0.497
 drown-0.412
 banks-0.410
 neither-0.408
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.641
idges+0.508
ad+0.497
ement+0.495
 importantly+0.483
Neg logit contributions
gy-0.853
 bank-0.755
 fight-0.571
house-0.570
 station-0.566
Token.
Token ID13
Feature activation+5.78e-01

Pos logit contributions
 ey+0.765
 yogurt+0.658
idges+0.651
 honey+0.648
ad+0.629
Neg logit contributions
gy-1.019
 bank-0.828
lves-0.732
 drown-0.680
 station-0.674
Token One
Token ID1881
Feature activation-5.24e+00

Pos logit contributions
 ey+0.044
idges+0.037
ad+0.035
 yogurt+0.035
ement+0.035
Neg logit contributions
gy-0.053
 bank-0.043
lves-0.036
 station-0.034
zag-0.033
Token day
Token ID1110
Feature activation-2.21e+00

Pos logit contributions
gy+0.379
 bank+0.288
lves+0.227
zag+0.212
 station+0.210
Neg logit contributions
 ey-0.496
idges-0.433
 yogurt-0.423
ad-0.420
 honey-0.414
Token,
Token ID11
Feature activation+5.17e-01

Pos logit contributions
gy+0.192
 bank+0.154
lves+0.129
zag+0.122
 station+0.121
Neg logit contributions
 ey-0.176
idges-0.149
 yogurt-0.146
ad-0.144
 honey-0.142
Token he
Token ID339
Feature activation+1.20e+00

Pos logit contributions
 ey+0.030
 yogurt+0.026
 honey+0.025
idges+0.025
ad+0.024
Neg logit contributions
gy-0.053
 bank-0.045
lves-0.039
zag-0.038
 drown-0.037
Token
Token ID241
Feature activation-5.47e-01

Pos logit contributions
gy+0.189
 bank+0.155
lves+0.132
 drown+0.126
zag+0.126
Neg logit contributions
 ey-0.138
idges-0.115
ad-0.113
 yogurt-0.112
ement-0.109
TokenI
Token ID40
Feature activation+3.86e+00

Pos logit contributions
gy+0.052
 bank+0.043
lves+0.037
zag+0.036
 station+0.035
Neg logit contributions
 ey-0.038
idges-0.032
 honey-0.030
 yogurt-0.030
ement-0.029
Token'm
Token ID1101
Feature activation-2.89e+00

Pos logit contributions
 ey+0.313
ad+0.269
idges+0.267
 yogurt+0.267
 honey+0.259
Neg logit contributions
gy-0.320
 bank-0.256
lves-0.216
 station-0.196
zag-0.195
Token scattering
Token ID45765
Feature activation-1.07e+00

Pos logit contributions
gy+0.276
 bank+0.226
lves+0.193
zag+0.185
 station+0.184
Neg logit contributions
 ey-0.206
idges-0.169
 yogurt-0.165
ad-0.162
 honey-0.160
Token the
Token ID262
Feature activation+1.17e-01

Pos logit contributions
gy+0.090
 bank+0.078
lves+0.064
 station+0.060
 neither+0.060
Neg logit contributions
 ey-0.080
idges-0.067
ango-0.065
ement-0.064
 importantly-0.063
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.008
idges+0.007
ad+0.007
ement+0.007
mmmm+0.007
Neg logit contributions
gy-0.011
 bank-0.009
 station-0.007
lves-0.007
zag-0.007
Token so
Token ID523
Feature activation+6.40e-01

Pos logit contributions
 ey+0.790
idges+0.658
 yogurt+0.646
ad+0.636
 honey+0.628
Neg logit contributions
gy-1.023
 bank-0.836
lves-0.712
zag-0.677
 station-0.673
Token I
Token ID314
Feature activation+3.65e+00

Pos logit contributions
 ey+0.049
idges+0.037
ad+0.037
ement+0.036
ango+0.035
Neg logit contributions
gy-0.057
 bank-0.047
lves-0.041
 neither-0.040
zag-0.039
Token can
Token ID460
Feature activation+3.25e+00

Pos logit contributions
 ey+0.296
idges+0.252
 yogurt+0.251
ad+0.250
 honey+0.243
Neg logit contributions
gy-0.305
 bank-0.242
lves-0.204
zag-0.190
 station-0.189
Token feed
Token ID3745
Feature activation-2.56e+00

Pos logit contributions
 ey+0.280
idges+0.238
 yogurt+0.233
ement+0.229
 honey+0.229
Neg logit contributions
gy-0.263
 bank-0.209
lves-0.165
zag-0.162
 drown-0.158
Token the
Token ID262
Feature activation+1.95e-02

Pos logit contributions
gy+0.211
 bank+0.185
lves+0.147
 neither+0.143
 station+0.141
Neg logit contributions
 ey-0.201
 importantly-0.164
idges-0.157
ement-0.157
ad-0.148
Token "
Token ID366
Feature activation+2.40e+00

Pos logit contributions
gy+0.122
 bank+0.100
lves+0.086
zag+0.081
 station+0.081
Neg logit contributions
 ey-0.090
idges-0.074
 yogurt-0.072
ad-0.071
ement-0.070
TokenDon
Token ID3987
Feature activation+8.93e-01

Pos logit contributions
 ey+0.147
idges+0.118
 honey+0.113
 yogurt+0.112
ement+0.109
Neg logit contributions
gy-0.252
 bank-0.212
lves-0.184
 station-0.176
zag-0.176
Token't
Token ID470
Feature activation-4.27e+00

Pos logit contributions
 ey+0.081
idges+0.070
 yogurt+0.069
 honey+0.068
ad+0.067
Neg logit contributions
gy-0.068
 bank-0.052
lves-0.042
zag-0.040
 station-0.039
Token worry
Token ID5490
Feature activation-6.82e-01

Pos logit contributions
gy+0.387
 bank+0.317
lves+0.273
zag+0.259
 station+0.256
Neg logit contributions
 ey-0.318
ad-0.270
idges-0.266
 yogurt-0.265
 honey-0.262
Token,
Token ID11
Feature activation+6.22e-01

Pos logit contributions
gy+0.055
 bank+0.041
 neither+0.032
 station+0.032
lves+0.032
Neg logit contributions
 ey-0.062
idges-0.051
ad-0.050
ement-0.049
 yogurt-0.049
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.049
ement+0.040
idges+0.040
ad+0.039
 yogurt+0.037
Neg logit contributions
gy-0.055
 bank-0.044
 station-0.037
lves-0.036
 neither-0.036
Token!
Token ID0
Feature activation+2.37e+00

Pos logit contributions
 ey+0.845
idges+0.711
 yogurt+0.695
ad+0.687
 honey+0.674
Neg logit contributions
gy-0.975
 bank-0.784
lves-0.655
zag-0.627
 station-0.623
Token I
Token ID314
Feature activation+3.80e+00

Pos logit contributions
 ey+0.148
idges+0.118
 yogurt+0.114
ad+0.113
ement+0.111
Neg logit contributions
gy-0.249
 bank-0.205
lves-0.178
 station-0.171
 drown-0.171
Token'm
Token ID1101
Feature activation-3.09e+00

Pos logit contributions
 ey+0.276
ad+0.244
 honey+0.239
 yogurt+0.237
idges+0.237
Neg logit contributions
gy-0.319
 bank-0.260
lves-0.233
zag-0.209
 station-0.207
Token going
Token ID1016
Feature activation+3.16e+00

Pos logit contributions
gy+0.269
 bank+0.215
lves+0.182
 drown+0.176
 station+0.169
Neg logit contributions
 ey-0.247
idges-0.206
ad-0.199
 yogurt-0.198
ement-0.196
Token to
Token ID284
Feature activation+8.00e-01

Pos logit contributions
 ey+0.214
 yogurt+0.188
idges+0.185
 honey+0.184
ad+0.181
Neg logit contributions
gy-0.288
 bank-0.235
lves-0.211
 drown-0.192
zag-0.191
Token and
Token ID290
Feature activation-7.64e-02

Pos logit contributions
gy+0.075
 bank+0.060
lves+0.054
 drown+0.052
 station+0.050
Neg logit contributions
 ey-0.055
 yogurt-0.050
ad-0.048
idges-0.047
 honey-0.046
Token said
Token ID531
Feature activation+1.85e-01

Pos logit contributions
gy+0.007
 bank+0.005
lves+0.005
 station+0.004
zag+0.004
Neg logit contributions
 ey-0.006
idges-0.005
ad-0.005
 yogurt-0.005
ement-0.005
Token,
Token ID11
Feature activation+9.71e-01

Pos logit contributions
 ey+0.016
idges+0.013
 yogurt+0.012
ad+0.012
ement+0.012
Neg logit contributions
gy-0.015
 bank-0.012
lves-0.010
 neither-0.010
zag-0.009
Token "
Token ID366
Feature activation+2.63e+00

Pos logit contributions
 ey+0.065
idges+0.053
ad+0.050
 yogurt+0.050
ement+0.049
Neg logit contributions
gy-0.098
 bank-0.081
 station-0.068
lves-0.068
zag-0.067
TokenNo
Token ID2949
Feature activation-7.05e-02

Pos logit contributions
 ey+0.172
idges+0.137
 honey+0.134
 yogurt+0.132
ement+0.130
Neg logit contributions
gy-0.266
 bank-0.221
lves-0.196
zag-0.185
 station-0.184
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
zag+0.004
 station+0.004
Neg logit contributions
 ey-0.006
idges-0.005
 yogurt-0.005
ad-0.005
ement-0.005
Token,
Token ID11
Feature activation+6.50e-01

Pos logit contributions
 ey+0.784
idges+0.671
 yogurt+0.667
 honey+0.661
ad+0.652
Neg logit contributions
gy-0.981
 bank-0.815
lves-0.705
 station-0.645
 drown-0.641
Token you
Token ID345
Feature activation+2.94e+00

Pos logit contributions
 ey+0.046
idges+0.037
ement+0.037
ad+0.036
 yogurt+0.034
Neg logit contributions
gy-0.061
 bank-0.050
lves-0.043
 drown-0.042
 neither-0.042
Token can
Token ID460
Feature activation+3.44e+00

Pos logit contributions
 ey+0.172
 honey+0.164
 yogurt+0.158
idges+0.158
 sweet+0.157
Neg logit contributions
gy-0.290
 bank-0.237
lves-0.213
 station-0.195
zag-0.193
Token't
Token ID470
Feature activation-4.40e+00

Pos logit contributions
 ey+0.270
ad+0.238
 yogurt+0.237
idges+0.237
 honey+0.229
Neg logit contributions
gy-0.286
 bank-0.228
lves-0.203
 station-0.181
zag-0.175
Token catch
Token ID4929
Feature activation-3.25e+00

Pos logit contributions
gy+0.402
 bank+0.326
lves+0.304
 station+0.276
 sank+0.269
Neg logit contributions
 ey-0.285
ad-0.267
 yogurt-0.263
idges-0.257
 honey-0.255
Token said
Token ID531
Feature activation-7.12e-02

Pos logit contributions
 ey+0.341
umm+0.301
mmmm+0.295
idges+0.294
 goodness+0.286
Neg logit contributions
gy-0.239
 bank-0.182
 argue-0.144
 station-0.143
zag-0.133
Token,
Token ID11
Feature activation+6.96e-01

Pos logit contributions
gy+0.005
 bank+0.004
 neither+0.003
zag+0.003
 argue+0.003
Neg logit contributions
 ey-0.007
idges-0.006
ango-0.006
ad-0.006
mmmm-0.006
Token "
Token ID366
Feature activation+2.42e+00

Pos logit contributions
 ey+0.058
idges+0.049
ad+0.046
ement+0.045
ango+0.044
Neg logit contributions
gy-0.058
 bank-0.046
 station-0.038
 neither-0.037
 argue-0.037
TokenYes
Token ID5297
Feature activation+3.82e+00

Pos logit contributions
 ey+0.195
idges+0.159
ement+0.155
 honey+0.153
ocol+0.147
Neg logit contributions
gy-0.190
 bank-0.161
lves-0.139
 neither-0.136
 argue-0.133
Token,
Token ID11
Feature activation+5.93e-01

Pos logit contributions
 ey+0.368
idges+0.297
ad+0.290
 yogurt+0.285
ango+0.284
Neg logit contributions
gy-0.275
 bank-0.208
 neither-0.173
 station-0.162
lves-0.160
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.052
ement+0.042
ad+0.041
odic+0.040
idges+0.039
Neg logit contributions
gy-0.040
 neither-0.032
 bank-0.031
 they-0.030
 station-0.029
Token,
Token ID11
Feature activation+5.54e-01

Pos logit contributions
 ey+0.939
idges+0.778
ement+0.738
ad+0.738
 importantly+0.733
Neg logit contributions
gy-0.950
 bank-0.714
zag-0.596
 station-0.586
lves-0.550
Token you
Token ID345
Feature activation+2.95e+00

Pos logit contributions
 ey+0.048
ement+0.040
ad+0.038
odic+0.038
ango+0.036
Neg logit contributions
gy-0.040
 bank-0.031
 neither-0.030
 they-0.028
 station-0.028
Token look
Token ID804
Feature activation-1.86e-01

Pos logit contributions
 ey+0.226
idges+0.190
 yogurt+0.185
ad+0.183
 honey+0.180
Neg logit contributions
gy-0.266
 bank-0.216
lves-0.182
zag-0.172
 station-0.172
Token very
Token ID845
Feature activation-6.18e-01

Pos logit contributions
gy+0.015
 bank+0.012
lves+0.010
 station+0.009
 away+0.009
Neg logit contributions
 ey-0.015
ad-0.013
idges-0.013
 subtract-0.012
mmmm-0.012
Token nice
Token ID3621
Feature activation+4.83e+00

Pos logit contributions
gy+0.050
 bank+0.044
lves+0.038
 drown+0.035
 neither+0.035
Neg logit contributions
 ey-0.046
ad-0.039
idges-0.037
mmmm-0.036
ango-0.036
Token he
Token ID339
Feature activation+1.21e+00

Pos logit contributions
gy+0.148
 bank+0.122
lves+0.097
 station+0.094
zag+0.092
Neg logit contributions
 ey-0.142
idges-0.120
ad-0.114
ement-0.114
 yogurt-0.113
Token would
Token ID561
Feature activation+1.63e+00

Pos logit contributions
 ey+0.109
idges+0.093
 yogurt+0.089
ement+0.089
ad+0.088
Neg logit contributions
gy-0.094
 bank-0.074
lves-0.059
zag-0.055
 station-0.055
Token turn
Token ID1210
Feature activation-3.84e-01

Pos logit contributions
 ey+0.141
idges+0.121
 yogurt+0.118
ement+0.117
ad+0.115
Neg logit contributions
gy-0.130
 bank-0.103
lves-0.082
zag-0.078
 drown-0.078
Token into
Token ID656
Feature activation-1.00e+00

Pos logit contributions
gy+0.030
 bank+0.024
lves+0.018
 station+0.017
zag+0.017
Neg logit contributions
 ey-0.034
idges-0.029
ad-0.028
ement-0.027
mmmm-0.027
Token delicious
Token ID12625
Feature activation+8.75e+00

Pos logit contributions
gy+0.086
 bank+0.073
 station+0.055
lves+0.054
 drown+0.053
Neg logit contributions
 ey-0.079
idges-0.068
ement-0.063
ango-0.062
ad-0.062
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.604
idges+0.517
ango+0.491
ad+0.480
 importantly+0.463
Neg logit contributions
gy-0.794
 bank-0.731
 station-0.545
 fight-0.538
 banks-0.531
Token.
Token ID13
Feature activation+2.29e-01

Pos logit contributions
 ey+0.811
idges+0.682
 yogurt+0.672
ad+0.660
 honey+0.657
Neg logit contributions
gy-0.986
 bank-0.799
lves-0.681
zag-0.642
 station-0.637
Token
Token ID198
Feature activation+2.40e-01

Pos logit contributions
 ey+0.017
idges+0.014
 yogurt+0.013
ad+0.013
 honey+0.013
Neg logit contributions
gy-0.022
 bank-0.018
lves-0.015
 station-0.014
zag-0.014
Token
Token ID198
Feature activation+2.64e-01

Pos logit contributions
 ey+0.021
idges+0.017
 honey+0.017
 yogurt+0.017
ement+0.017
Neg logit contributions
gy-0.018
 bank-0.015
zag-0.012
lves-0.012
 station-0.011
TokenOne
Token ID3198
Feature activation-3.22e+00

Pos logit contributions
 ey+0.021
ement+0.016
 honey+0.016
idges+0.016
 yogurt+0.016
Neg logit contributions
gy-0.023
 bank-0.019
lves-0.016
zag-0.016
 station-0.016
Token day
Token ID1110
Feature activation-2.26e+00

Pos logit contributions
gy+0.209
 bank+0.152
lves+0.113
zag+0.111
 station+0.108
Neg logit contributions
 ey-0.328
idges-0.289
ement-0.276
ad-0.275
 yogurt-0.272
Token replied
Token ID8712
Feature activation+1.47e+00

Pos logit contributions
 ey+0.260
idges+0.206
 importantly+0.201
mmmm+0.199
 yogurt+0.194
Neg logit contributions
gy-0.306
 bank-0.245
 station-0.207
 argue-0.197
zag-0.193
Token,
Token ID11
Feature activation+4.14e-01

Pos logit contributions
 ey+0.146
idges+0.122
ango+0.116
ad+0.116
 yogurt+0.114
Neg logit contributions
gy-0.106
 bank-0.079
 neither-0.061
zag-0.056
 station-0.056
Token "
Token ID366
Feature activation+2.16e+00

Pos logit contributions
 ey+0.033
idges+0.027
ad+0.026
 yogurt+0.025
ement+0.025
Neg logit contributions
gy-0.038
 bank-0.030
 station-0.025
 neither-0.024
zag-0.024
TokenNo
Token ID2949
Feature activation-2.82e-01

Pos logit contributions
 ey+0.159
idges+0.127
ement+0.124
 honey+0.122
 yogurt+0.121
Neg logit contributions
gy-0.192
 bank-0.162
lves-0.146
 neither-0.134
 station-0.132
Token,
Token ID11
Feature activation+4.08e-01

Pos logit contributions
gy+0.024
 bank+0.019
lves+0.015
 station+0.015
zag+0.015
Neg logit contributions
 ey-0.024
idges-0.020
 yogurt-0.019
ad-0.019
ement-0.019
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.031
ad+0.025
ement+0.024
idges+0.024
ango+0.023
Neg logit contributions
gy-0.036
 bank-0.030
lves-0.025
 neither-0.025
 station-0.025
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
 ey+0.820
idges+0.701
 yogurt+0.694
 honey+0.688
ad+0.678
Neg logit contributions
gy-0.953
 bank-0.781
lves-0.667
zag-0.614
 station-0.613
Token Let
Token ID3914
Feature activation+1.79e+00

Pos logit contributions
 ey+0.011
idges+0.009
 yogurt+0.008
ad+0.008
 honey+0.008
Neg logit contributions
gy-0.020
 bank-0.017
lves-0.014
zag-0.014
 station-0.014
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
 ey+0.123
 honey+0.119
idges+0.115
 yogurt+0.115
 sweet+0.115
Neg logit contributions
gy-0.160
 bank-0.125
zag-0.112
lves-0.108
 drown-0.104
Token flower
Token ID15061
Feature activation+1.92e+00

Pos logit contributions
 ey+0.010
idges+0.009
ad+0.008
ement+0.008
 yogurt+0.008
Neg logit contributions
gy-0.013
 bank-0.011
lves-0.009
 station-0.009
zag-0.008
Token bloom
Token ID29955
Feature activation+2.09e+00

Pos logit contributions
 ey+0.125
 honey+0.119
 yogurt+0.110
idges+0.108
 sweet+0.106
Neg logit contributions
gy-0.171
 bank-0.139
lves-0.130
 drown-0.118
 drowned-0.118
Token sad
Token ID6507
Feature activation-5.56e+00

Pos logit contributions
 ey+0.124
idges+0.105
 yogurt+0.103
ad+0.102
 honey+0.101
Neg logit contributions
gy-0.134
 bank-0.107
lves-0.090
zag-0.085
 station-0.084
Token because
Token ID780
Feature activation-6.15e+00

Pos logit contributions
gy+0.441
 bank+0.345
lves+0.264
 neither+0.263
zag+0.261
Neg logit contributions
 ey-0.492
idges-0.423
ad-0.408
 yogurt-0.401
ement-0.392
Token he
Token ID339
Feature activation+1.11e+00

Pos logit contributions
gy+0.589
 bank+0.484
lves+0.407
 station+0.398
 neither+0.395
Neg logit contributions
 ey-0.429
idges-0.348
ement-0.330
ad-0.327
 yogurt-0.324
Token wanted
Token ID2227
Feature activation-1.07e+00

Pos logit contributions
 ey+0.101
idges+0.087
 yogurt+0.085
ad+0.084
ement+0.083
Neg logit contributions
gy-0.086
 bank-0.067
lves-0.054
zag-0.050
 station-0.049
Token the
Token ID262
Feature activation-1.11e-01

Pos logit contributions
gy+0.082
 bank+0.066
 station+0.049
 fight+0.048
 drown+0.048
Neg logit contributions
 ey-0.098
idges-0.083
ement-0.083
mmmm-0.078
ad-0.077
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
gy+0.010
 bank+0.008
 station+0.007
lves+0.007
 drown+0.007
Neg logit contributions
 ey-0.008
idges-0.007
ad-0.007
ement-0.007
mmmm-0.007
Token so
Token ID523
Feature activation+6.18e-01

Pos logit contributions
 ey+0.835
 yogurt+0.718
idges+0.710
 honey+0.705
ad+0.694
Neg logit contributions
gy-0.939
 bank-0.756
lves-0.655
zag-0.600
 station-0.599
Token much
Token ID881
Feature activation-1.89e+00

Pos logit contributions
 ey+0.059
idges+0.051
 yogurt+0.051
ad+0.050
 honey+0.050
Neg logit contributions
gy-0.044
 bank-0.034
lves-0.027
zag-0.025
 station-0.024
Token,
Token ID11
Feature activation+4.64e-01

Pos logit contributions
gy+0.115
 bank+0.100
 neither+0.073
 fight+0.069
 they+0.066
Neg logit contributions
 ey-0.188
idges-0.161
ango-0.153
Jamie-0.152
ad-0.148
Token but
Token ID475
Feature activation-1.38e+00

Pos logit contributions
 ey+0.035
idges+0.029
 yogurt+0.028
ad+0.028
ement+0.028
Neg logit contributions
gy-0.042
 bank-0.034
lves-0.029
 station-0.027
 drown-0.027
Token he
Token ID339
Feature activation+9.25e-01

Pos logit contributions
gy+0.148
 bank+0.124
lves+0.109
zag+0.105
 drown+0.103
Neg logit contributions
 ey-0.081
 yogurt-0.066
idges-0.064
 honey-0.064
ad-0.063
Token the
Token ID262
Feature activation-6.09e-02

Pos logit contributions
 ey+0.040
idges+0.038
ad+0.034
ement+0.034
heart+0.033
Neg logit contributions
gy-0.044
 bank-0.035
 drown-0.030
 neither-0.028
lves-0.028
Token jar
Token ID17379
Feature activation+6.72e-01

Pos logit contributions
gy+0.005
 bank+0.004
lves+0.004
 station+0.003
zag+0.003
Neg logit contributions
 ey-0.005
idges-0.004
ad-0.004
 yogurt-0.004
ement-0.004
Token and
Token ID290
Feature activation+1.78e-01

Pos logit contributions
 ey+0.049
idges+0.041
 yogurt+0.040
ad+0.040
 honey+0.039
Neg logit contributions
gy-0.062
 bank-0.050
lves-0.043
zag-0.041
 station-0.040
Token have
Token ID423
Feature activation-3.04e+00

Pos logit contributions
 ey+0.015
idges+0.013
ement+0.013
ad+0.013
 yogurt+0.012
Neg logit contributions
gy-0.014
 bank-0.012
lves-0.009
 station-0.009
 drown-0.009
Token some
Token ID617
Feature activation-3.06e+00

Pos logit contributions
gy+0.248
 bank+0.214
 drowned+0.164
 station+0.160
lves+0.157
Neg logit contributions
 ey-0.260
idges-0.213
ement-0.208
ango-0.200
ad-0.200
Token honey
Token ID12498
Feature activation+1.08e+01

Pos logit contributions
gy+0.245
 bank+0.236
 fight+0.177
 station+0.177
house+0.170
Neg logit contributions
 ey-0.228
ango-0.193
idges-0.188
ad-0.181
ement-0.179
Token,"
Token ID553
Feature activation-4.28e-01

Pos logit contributions
 ey+0.730
 yogurt+0.654
 honey+0.647
idges+0.627
ad+0.609
Neg logit contributions
gy-0.994
 bank-0.818
lves-0.737
 drown-0.677
 argue-0.662
Token he
Token ID339
Feature activation+1.22e+00

Pos logit contributions
gy+0.041
 bank+0.034
lves+0.028
 station+0.027
 argue+0.027
Neg logit contributions
 ey-0.031
idges-0.025
 yogurt-0.024
ement-0.024
ad-0.024
Token said
Token ID531
Feature activation-1.35e-01

Pos logit contributions
 ey+0.097
idges+0.082
 yogurt+0.078
ement+0.078
ad+0.077
Neg logit contributions
gy-0.105
 bank-0.086
lves-0.069
 station-0.067
 argue-0.067
Token to
Token ID284
Feature activation+7.66e-01

Pos logit contributions
gy+0.012
 bank+0.010
lves+0.008
zag+0.008
 station+0.008
Neg logit contributions
 ey-0.010
idges-0.009
 yogurt-0.009
ad-0.008
 honey-0.008
Token Lily
Token ID20037
Feature activation-1.78e+00

Pos logit contributions
 ey+0.052
idges+0.042
ement+0.040
 yogurt+0.039
 importantly+0.038
Neg logit contributions
gy-0.078
 bank-0.063
lves-0.052
 drown-0.052
 station-0.052
Token the
Token ID262
Feature activation+3.99e-01

Pos logit contributions
gy+0.320
 bank+0.265
lves+0.227
 station+0.217
zag+0.217
Neg logit contributions
 ey-0.217
idges-0.177
 yogurt-0.173
ad-0.170
 honey-0.166
Token bees
Token ID17002
Feature activation+3.98e+00

Pos logit contributions
 ey+0.029
idges+0.024
ad+0.024
ement+0.023
 yogurt+0.023
Neg logit contributions
gy-0.036
 bank-0.031
lves-0.025
 station-0.025
 argue-0.024
Token started
Token ID2067
Feature activation+2.21e-01

Pos logit contributions
 ey+0.302
idges+0.260
 honey+0.252
ad+0.251
 yogurt+0.251
Neg logit contributions
gy-0.351
 bank-0.279
lves-0.238
zag-0.224
 station-0.220
Token eating
Token ID6600
Feature activation+5.02e+00

Pos logit contributions
 ey+0.017
idges+0.015
 yogurt+0.014
ad+0.014
 honey+0.014
Neg logit contributions
gy-0.019
 bank-0.016
lves-0.013
zag-0.012
 station-0.012
Token more
Token ID517
Feature activation+1.88e+00

Pos logit contributions
 ey+0.425
idges+0.362
ad+0.351
 importantly+0.345
ango+0.344
Neg logit contributions
gy-0.393
 bank-0.346
 argue-0.247
 fight-0.246
lves-0.243
Token honey
Token ID12498
Feature activation+1.08e+01

Pos logit contributions
 ey+0.132
idges+0.109
ad+0.108
ango+0.107
ement+0.104
Neg logit contributions
gy-0.168
 bank-0.151
 drown-0.113
lves-0.113
house-0.112
Token too
Token ID1165
Feature activation-9.55e-01

Pos logit contributions
 ey+0.785
idges+0.663
 yogurt+0.663
 honey+0.655
ad+0.643
Neg logit contributions
gy-0.989
 bank-0.801
lves-0.700
 station-0.649
 drown-0.647
Token.
Token ID13
Feature activation+5.87e-02

Pos logit contributions
gy+0.083
 bank+0.068
lves+0.055
zag+0.053
 drown+0.053
Neg logit contributions
 ey-0.077
idges-0.064
ad-0.062
 yogurt-0.061
ement-0.060
Token They
Token ID1119
Feature activation-3.86e+00

Pos logit contributions
 ey+0.004
idges+0.004
 yogurt+0.004
ad+0.004
 honey+0.003
Neg logit contributions
gy-0.005
 bank-0.004
lves-0.004
zag-0.003
 station-0.003
Token all
Token ID477
Feature activation-3.82e+00

Pos logit contributions
gy+0.333
 bank+0.261
lves+0.225
zag+0.216
 station+0.210
Neg logit contributions
 ey-0.299
 yogurt-0.260
idges-0.257
 honey-0.256
ad-0.256
Token became
Token ID2627
Feature activation-2.54e+00

Pos logit contributions
gy+0.320
 bank+0.254
lves+0.212
zag+0.200
 station+0.198
Neg logit contributions
 ey-0.312
idges-0.267
 yogurt-0.264
ad-0.261
 honey-0.258
Token that
Token ID326
Feature activation-1.08e+00

Pos logit contributions
 ey+0.073
idges+0.060
 yogurt+0.060
 honey+0.057
 layers+0.056
Neg logit contributions
gy-0.074
 bank-0.058
lves-0.049
 station-0.046
zag-0.044
Token day
Token ID1110
Feature activation-2.71e+00

Pos logit contributions
gy+0.089
 bank+0.072
lves+0.061
 drown+0.056
 argue+0.054
Neg logit contributions
 ey-0.089
ad-0.076
 yogurt-0.076
 honey-0.076
idges-0.075
Token on
Token ID319
Feature activation-1.35e+00

Pos logit contributions
gy+0.252
 bank+0.222
lves+0.182
 drown+0.175
 argue+0.175
Neg logit contributions
 ey-0.178
ad-0.162
idges-0.161
 importantly-0.160
ement-0.153
Token,
Token ID11
Feature activation+1.26e-01

Pos logit contributions
gy+0.121
 bank+0.099
lves+0.085
 drown+0.079
zag+0.079
Neg logit contributions
 ey-0.102
idges-0.086
 yogurt-0.084
ad-0.084
 honey-0.083
Token Mag
Token ID2944
Feature activation-5.54e+00

Pos logit contributions
 ey+0.008
 importantly+0.007
ad+0.007
idges+0.007
 sweet+0.007
Neg logit contributions
gy-0.011
 bank-0.010
 argue-0.009
 drown-0.008
 fight-0.008
Tokengy
Token ID1360
Feature activation-1.63e+01

Pos logit contributions
gy+0.039
 bank+0.028
 argue-0.047
 drown-0.052
 fight-0.062
Neg logit contributions
 ey-0.803
ad-0.744
idges-0.738
ement-0.721
ummy-0.721
Token was
Token ID373
Feature activation+9.19e-01

Pos logit contributions
gy+1.505
 bank+1.238
lves+1.131
 drown+1.074
 argue+1.048
Neg logit contributions
 ey-1.031
ad-0.934
idges-0.892
 yogurt-0.880
 honey-0.865
Token never
Token ID1239
Feature activation-5.07e+00

Pos logit contributions
 ey+0.074
idges+0.065
ad+0.064
 yogurt+0.064
 honey+0.064
Neg logit contributions
gy-0.075
 bank-0.061
lves-0.050
zag-0.047
 station-0.047
Token fearful
Token ID26844
Feature activation-4.78e+00

Pos logit contributions
gy+0.429
 bank+0.352
lves+0.289
zag+0.285
 station+0.276
Neg logit contributions
 ey-0.396
 yogurt-0.341
 honey-0.338
ad-0.334
idges-0.334
Token of
Token ID286
Feature activation+2.57e+00

Pos logit contributions
gy+0.429
 bank+0.345
lves+0.294
 drown+0.279
 neither+0.278
Neg logit contributions
 ey-0.364
idges-0.302
 yogurt-0.292
ad-0.288
 honey-0.280
Token boards
Token ID11490
Feature activation-5.93e-02

Pos logit contributions
 ey+0.188
idges+0.157
mmmm+0.151
ement+0.150
 yogurt+0.150
Neg logit contributions
gy-0.235
 bank-0.193
lves-0.162
 station-0.156
 drown-0.155
Token board
Token ID3096
Feature activation-1.11e+00

Pos logit contributions
 ey+0.001
idges+0.001
ad+0.001
 honey+0.001
ement+0.001
Neg logit contributions
gy-0.001
 bank-0.001
 station-0.000
lves-0.000
zag-0.000
Token far
Token ID1290
Feature activation-3.05e+00

Pos logit contributions
gy+0.092
 bank+0.072
lves+0.069
 drown+0.064
 argue+0.061
Neg logit contributions
 ey-0.080
 yogurt-0.074
ad-0.074
idges-0.070
 honey-0.070
Token away
Token ID1497
Feature activation-7.01e+00

Pos logit contributions
gy+0.202
 bank+0.149
lves+0.130
 drown+0.129
zag+0.121
Neg logit contributions
 ey-0.269
ad-0.248
ement-0.246
 honey-0.240
ummy-0.237
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
gy+0.664
 bank+0.547
lves+0.488
 drown+0.451
zag+0.450
Neg logit contributions
 ey-0.474
idges-0.393
ad-0.391
 yogurt-0.390
 honey-0.386
Token Mag
Token ID2944
Feature activation-5.51e+00

Pos logit contributions
 ey+0.008
ad+0.007
idges+0.007
 importantly+0.007
ement+0.007
Neg logit contributions
gy-0.012
 bank-0.011
lves-0.009
 drown-0.009
 argue-0.009
Tokengy
Token ID1360
Feature activation-1.62e+01

Pos logit contributions
gy+0.055
 bank+0.038
 argue-0.035
 drown-0.036
 fight-0.043
Neg logit contributions
 ey-0.780
ad-0.722
idges-0.712
ement-0.702
ummy-0.694
Token was
Token ID373
Feature activation+9.44e-01

Pos logit contributions
gy+1.522
 bank+1.221
lves+1.111
 drown+1.068
zag+1.046
Neg logit contributions
 ey-1.037
ad-0.922
idges-0.886
 yogurt-0.886
 honey-0.857
Token so
Token ID523
Feature activation+3.81e-01

Pos logit contributions
 ey+0.062
ad+0.052
idges+0.051
 yogurt+0.051
 honey+0.050
Neg logit contributions
gy-0.091
 bank-0.076
lves-0.066
zag-0.062
 argue-0.062
Token relieved
Token ID22598
Feature activation+8.50e-01

Pos logit contributions
 ey+0.027
idges+0.023
 yogurt+0.022
ad+0.022
 honey+0.022
Neg logit contributions
gy-0.036
 bank-0.030
lves-0.025
zag-0.024
 station-0.024
Token,
Token ID11
Feature activation+1.92e-01

Pos logit contributions
 ey+0.072
idges+0.060
 yogurt+0.058
ement+0.056
ad+0.056
Neg logit contributions
gy-0.072
 bank-0.056
lves-0.045
 station-0.044
zag-0.044
Token she
Token ID673
Feature activation-5.26e-01

Pos logit contributions
 ey+0.012
idges+0.010
ad+0.010
 yogurt+0.010
 honey+0.010
Neg logit contributions
gy-0.020
 bank-0.016
lves-0.014
zag-0.014
 drown-0.013
TokenAfter
Token ID3260
Feature activation+1.57e+00

Pos logit contributions
 ey+0.006
idges+0.005
 yogurt+0.005
 honey+0.005
ement+0.005
Neg logit contributions
gy-0.010
 bank-0.008
lves-0.007
zag-0.007
 station-0.007
Token a
Token ID257
Feature activation+2.61e-01

Pos logit contributions
 ey+0.119
idges+0.098
 yogurt+0.093
ement+0.093
ad+0.092
Neg logit contributions
gy-0.144
 bank-0.118
lves-0.097
 station-0.094
zag-0.093
Token while
Token ID981
Feature activation-2.04e+00

Pos logit contributions
 ey+0.020
 honey+0.018
 yogurt+0.018
 sweet+0.017
idges+0.017
Neg logit contributions
gy-0.023
 bank-0.018
lves-0.015
 drown-0.014
zag-0.014
Token,
Token ID11
Feature activation+2.41e-01

Pos logit contributions
gy+0.190
 bank+0.156
lves+0.137
zag+0.126
 station+0.125
Neg logit contributions
 ey-0.145
ad-0.123
idges-0.123
 yogurt-0.123
 honey-0.122
Token Mag
Token ID2944
Feature activation-5.51e+00

Pos logit contributions
 ey+0.013
 yogurt+0.012
 honey+0.012
ad+0.011
idges+0.011
Neg logit contributions
gy-0.024
 bank-0.020
lves-0.018
zag-0.018
 argue-0.018
Tokengy
Token ID1360
Feature activation-1.62e+01

Pos logit contributions
gy+0.349
 bank+0.306
 argue+0.232
lves+0.230
 drown+0.228
Neg logit contributions
 ey-0.503
ad-0.450
ement-0.434
idges-0.433
 goodness-0.425
Token and
Token ID290
Feature activation-3.44e-01

Pos logit contributions
gy+1.439
 bank+1.138
lves+1.071
 drown+1.006
zag+0.985
Neg logit contributions
 ey-1.066
ad-0.981
 yogurt-0.937
 honey-0.907
idges-0.906
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
gy+0.032
 bank+0.028
 drown+0.025
lves+0.024
 argue+0.024
Neg logit contributions
 ey-0.021
ad-0.019
 honey-0.018
 sweet-0.017
 importantly-0.017
Token friend
Token ID1545
Feature activation-3.33e+00

Pos logit contributions
 ey+0.083
idges+0.072
ad+0.067
 yogurt+0.067
mmmm+0.067
Neg logit contributions
gy-0.087
 bank-0.070
 station-0.056
lves-0.055
zag-0.055
Token had
Token ID550
Feature activation-1.20e+00

Pos logit contributions
gy+0.296
 bank+0.240
lves+0.206
zag+0.194
 drown+0.193
Neg logit contributions
 ey-0.247
idges-0.211
ad-0.209
 yogurt-0.209
 honey-0.205
Token carried
Token ID5281
Feature activation-6.75e-01

Pos logit contributions
gy+0.104
 bank+0.086
 station+0.068
lves+0.068
 drowned+0.066
Neg logit contributions
 ey-0.098
idges-0.081
ement-0.078
ad-0.074
 yogurt-0.074
Token was
Token ID373
Feature activation+9.19e-01

Pos logit contributions
gy+0.129
 bank+0.097
zag+0.076
 station+0.076
lves+0.076
Neg logit contributions
 ey-0.137
idges-0.120
 honey-0.112
 yogurt-0.110
ad-0.109
Token a
Token ID257
Feature activation+1.87e-01

Pos logit contributions
 ey+0.069
idges+0.058
ement+0.055
ad+0.054
 yogurt+0.053
Neg logit contributions
gy-0.085
 bank-0.068
lves-0.058
 station-0.055
zag-0.054
Token bug
Token ID5434
Feature activation-3.43e-02

Pos logit contributions
 ey+0.012
 yogurt+0.009
idges+0.009
 honey+0.009
ad+0.009
Neg logit contributions
gy-0.019
 bank-0.016
lves-0.014
zag-0.013
 drown-0.013
Token named
Token ID3706
Feature activation-6.65e+00

Pos logit contributions
gy+0.002
 bank+0.002
lves+0.002
 argue+0.002
 drown+0.002
Neg logit contributions
 ey-0.003
 yogurt-0.003
ad-0.003
 honey-0.003
idges-0.003
Token Bug
Token ID15217
Feature activation-3.27e+00

Pos logit contributions
gy+0.617
 bank+0.486
lves+0.419
zag+0.393
 station+0.384
Neg logit contributions
 ey-0.504
idges-0.421
ement-0.412
ad-0.404
 yogurt-0.394
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.160
 bank+0.151
 drown+0.121
 argue+0.118
lves+0.118
Neg logit contributions
 ey-0.281
ad-0.276
 sweet-0.272
 honey-0.271
ango-0.261
Token.
Token ID13
Feature activation-2.98e-02

Pos logit contributions
gy+1.510
 bank+1.241
lves+1.198
 drown+1.148
 argue+1.103
Neg logit contributions
 ey-0.951
ad-0.850
 yogurt-0.828
 honey-0.810
idges-0.761
Token Bug
Token ID15217
Feature activation-3.26e+00

Pos logit contributions
gy+0.002
 bank+0.001
lves+0.001
 drown+0.001
house+0.001
Neg logit contributions
 ey-0.003
idges-0.003
 yogurt-0.003
ement-0.003
ad-0.003
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.029
 bank+0.005
lves-0.033
 drown-0.034
 station-0.036
Neg logit contributions
 ey-0.461
ad-0.431
 honey-0.424
idges-0.422
 yogurt-0.419
Token had
Token ID550
Feature activation-1.18e+00

Pos logit contributions
gy+1.532
 bank+1.268
lves+1.149
 drown+1.109
zag+1.068
Neg logit contributions
 ey-1.032
ad-0.883
 yogurt-0.868
idges-0.847
 honey-0.842
Token a
Token ID257
Feature activation+2.00e-01

Pos logit contributions
gy+0.111
 bank+0.089
lves+0.075
zag+0.072
 drown+0.071
Neg logit contributions
 ey-0.088
idges-0.076
ement-0.073
 yogurt-0.071
ad-0.070
Token wanted
Token ID2227
Feature activation-1.31e+00

Pos logit contributions
 ey+0.067
idges+0.057
 yogurt+0.057
ad+0.057
 honey+0.056
Neg logit contributions
gy-0.070
 bank-0.055
lves-0.046
zag-0.043
 station-0.043
Token to
Token ID284
Feature activation+4.60e-01

Pos logit contributions
gy+0.076
 bank+0.063
 drowned+0.041
 neither+0.041
 fight+0.040
Neg logit contributions
 ey-0.145
ement-0.121
idges-0.120
mmmm-0.115
 importantly-0.114
Token give
Token ID1577
Feature activation-1.50e+00

Pos logit contributions
 ey+0.040
idges+0.034
 yogurt+0.033
ement+0.033
 honey+0.032
Neg logit contributions
gy-0.037
 bank-0.030
lves-0.023
 drown-0.023
zag-0.023
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
gy+0.153
 bank+0.127
lves+0.110
zag+0.106
 station+0.105
Neg logit contributions
 ey-0.097
idges-0.079
 yogurt-0.077
ad-0.076
 honey-0.075
Token pig
Token ID12967
Feature activation-5.52e+00

Pos logit contributions
 ey+0.015
idges+0.013
 yogurt+0.013
ad+0.012
 honey+0.012
Neg logit contributions
gy-0.011
 bank-0.008
lves-0.007
zag-0.006
 station-0.006
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.527
 bank+0.445
lves+0.397
 drown+0.372
zag+0.370
Neg logit contributions
 ey-0.353
 yogurt-0.304
 honey-0.297
ad-0.297
idges-0.290
Token a
Token ID257
Feature activation+2.62e-01

Pos logit contributions
gy+1.470
 bank+1.152
lves+1.066
zag+1.009
 drown+0.988
Neg logit contributions
 ey-1.125
 yogurt-0.998
 honey-0.962
ad-0.940
idges-0.910
Token gift
Token ID6979
Feature activation+2.44e+00

Pos logit contributions
 ey+0.019
idges+0.016
ad+0.015
ement+0.015
 yogurt+0.015
Neg logit contributions
gy-0.025
 bank-0.020
lves-0.017
zag-0.017
 station-0.016
Token too
Token ID1165
Feature activation-1.01e+00

Pos logit contributions
 ey+0.188
idges+0.158
 yogurt+0.154
ad+0.152
 honey+0.150
Neg logit contributions
gy-0.219
 bank-0.177
lves-0.148
zag-0.141
 station-0.141
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
gy+0.087
 bank+0.070
lves+0.056
zag+0.055
 station+0.055
Neg logit contributions
 ey-0.085
idges-0.069
ad-0.066
 yogurt-0.065
 honey-0.064
Token But
Token ID887
Feature activation-3.28e+00

Pos logit contributions
 ey+0.010
idges+0.008
 yogurt+0.008
ad+0.008
 honey+0.007
Neg logit contributions
gy-0.014
 bank-0.012
lves-0.010
zag-0.010
 station-0.010
Token money
Token ID1637
Feature activation-3.11e+00

Pos logit contributions
gy+0.193
 bank+0.153
lves+0.131
 drown+0.122
zag+0.121
Neg logit contributions
 ey-0.186
 yogurt-0.160
idges-0.158
 honey-0.156
ad-0.154
Token away
Token ID1497
Feature activation-7.04e+00

Pos logit contributions
gy+0.275
 bank+0.221
lves+0.189
zag+0.177
 drown+0.177
Neg logit contributions
 ey-0.235
 yogurt-0.200
idges-0.200
ad-0.195
 honey-0.194
Token in
Token ID287
Feature activation+1.22e+00

Pos logit contributions
gy+0.627
 bank+0.506
lves+0.419
zag+0.402
 station+0.400
Neg logit contributions
 ey-0.545
idges-0.459
 yogurt-0.446
ad-0.442
 honey-0.434
Token her
Token ID607
Feature activation+9.58e-01

Pos logit contributions
 ey+0.078
idges+0.063
 yogurt+0.062
ad+0.061
 honey+0.060
Neg logit contributions
gy-0.125
 bank-0.104
lves-0.090
zag-0.086
 station-0.085
Token pig
Token ID12967
Feature activation-5.38e+00

Pos logit contributions
 ey+0.077
 yogurt+0.064
idges+0.064
ad+0.063
 honey+0.062
Neg logit contributions
gy-0.083
 bank-0.066
lves-0.056
zag-0.052
 station-0.052
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.317
lves+0.262
 bank+0.246
 drown+0.244
 argue+0.221
Neg logit contributions
 ey-0.438
 honey-0.410
 yogurt-0.409
ad-0.406
 sweet-0.383
Tokenbank
Token ID17796
Feature activation-9.31e+00

Pos logit contributions
gy+0.974
lves+0.659
 bank+0.618
 drown+0.580
 neither+0.545
Neg logit contributions
 ey-1.556
 yogurt-1.442
 honey-1.388
ad-1.358
 pasta-1.323
Token every
Token ID790
Feature activation-2.82e+00

Pos logit contributions
gy+0.834
 bank+0.675
lves+0.564
zag+0.539
 station+0.535
Neg logit contributions
 ey-0.711
idges-0.597
 yogurt-0.584
ad-0.576
 honey-0.569
Token week
Token ID1285
Feature activation-2.60e+00

Pos logit contributions
gy+0.233
 bank+0.179
lves+0.158
zag+0.140
 drown+0.137
Neg logit contributions
 ey-0.235
 yogurt-0.207
ad-0.202
 honey-0.200
idges-0.199
Token.
Token ID13
Feature activation+4.70e-02

Pos logit contributions
gy+0.235
 bank+0.191
lves+0.160
zag+0.153
 station+0.152
Neg logit contributions
 ey-0.196
idges-0.165
 yogurt-0.161
ad-0.159
 honey-0.157
Token This
Token ID770
Feature activation-3.98e+00

Pos logit contributions
 ey+0.004
idges+0.003
ad+0.003
 yogurt+0.003
ement+0.003
Neg logit contributions
gy-0.004
 bank-0.003
lves-0.003
 station-0.003
zag-0.003
Token them
Token ID606
Feature activation-8.79e-01

Pos logit contributions
 ey+0.098
idges+0.081
 yogurt+0.079
ad+0.078
 honey+0.077
Neg logit contributions
gy-0.133
 bank-0.110
lves-0.094
 station-0.088
zag-0.088
Token safe
Token ID3338
Feature activation-1.21e+00

Pos logit contributions
gy+0.084
 bank+0.068
lves+0.060
 drown+0.059
zag+0.058
Neg logit contributions
 ey-0.059
 yogurt-0.051
 honey-0.050
idges-0.049
 sweet-0.048
Token in
Token ID287
Feature activation+1.33e+00

Pos logit contributions
gy+0.113
 bank+0.092
lves+0.081
zag+0.077
 drown+0.076
Neg logit contributions
 ey-0.085
 yogurt-0.071
idges-0.070
 honey-0.070
ad-0.069
Token her
Token ID607
Feature activation+1.01e+00

Pos logit contributions
 ey+0.082
idges+0.067
 yogurt+0.063
ement+0.062
ad+0.062
Neg logit contributions
gy-0.139
 bank-0.117
lves-0.100
 station-0.097
 drown-0.096
Token pig
Token ID12967
Feature activation-5.38e+00

Pos logit contributions
 ey+0.073
 yogurt+0.060
 honey+0.058
idges+0.057
ad+0.056
Neg logit contributions
gy-0.095
 bank-0.078
lves-0.067
zag-0.065
 drown-0.064
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.219
 drown+0.208
lves+0.192
 crashed+0.171
 neither+0.169
Neg logit contributions
 ey-0.495
ad-0.471
 yogurt-0.461
 honey-0.459
 sweet-0.455
Token bank
Token ID3331
Feature activation-1.26e+01

Pos logit contributions
gy+0.580
lves+0.365
 drown+0.331
 neither+0.289
zag+0.246
Neg logit contributions
 ey-1.793
 yogurt-1.739
 honey-1.697
 cereal-1.664
 pasta-1.647
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
gy+1.131
 bank+0.921
lves+0.767
zag+0.731
 station+0.728
Neg logit contributions
 ey-0.967
idges-0.813
 yogurt-0.794
ad-0.784
 honey-0.775
Token One
Token ID1881
Feature activation-5.47e+00

Pos logit contributions
 ey+0.010
idges+0.009
ad+0.008
 yogurt+0.008
ement+0.008
Neg logit contributions
gy-0.008
 bank-0.006
lves-0.005
 station-0.005
zag-0.005
Token day
Token ID1110
Feature activation-2.54e+00

Pos logit contributions
gy+0.448
 bank+0.368
lves+0.309
 drown+0.293
 argue+0.286
Neg logit contributions
 ey-0.445
 yogurt-0.399
 honey-0.383
ad-0.378
ummy-0.371
Token,
Token ID11
Feature activation+3.02e-01

Pos logit contributions
gy+0.235
 bank+0.194
lves+0.166
 station+0.157
zag+0.155
Neg logit contributions
 ey-0.185
 yogurt-0.158
idges-0.155
 honey-0.152
ad-0.149
Token named
Token ID3706
Feature activation-6.65e+00

Pos logit contributions
gy+0.002
 bank+0.002
lves+0.002
 argue+0.002
 drown+0.002
Neg logit contributions
 ey-0.003
 yogurt-0.003
ad-0.003
 honey-0.003
idges-0.003
Token Bug
Token ID15217
Feature activation-3.27e+00

Pos logit contributions
gy+0.617
 bank+0.486
lves+0.419
zag+0.393
 station+0.384
Neg logit contributions
 ey-0.504
idges-0.421
ement-0.412
ad-0.404
 yogurt-0.394
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.160
 bank+0.151
 drown+0.121
 argue+0.118
lves+0.118
Neg logit contributions
 ey-0.281
ad-0.276
 sweet-0.272
 honey-0.271
ango-0.261
Token.
Token ID13
Feature activation-2.98e-02

Pos logit contributions
gy+1.510
 bank+1.241
lves+1.198
 drown+1.148
 argue+1.103
Neg logit contributions
 ey-0.951
ad-0.850
 yogurt-0.828
 honey-0.810
idges-0.761
Token Bug
Token ID15217
Feature activation-3.26e+00

Pos logit contributions
gy+0.002
 bank+0.001
lves+0.001
 drown+0.001
house+0.001
Neg logit contributions
 ey-0.003
idges-0.003
 yogurt-0.003
ement-0.003
ad-0.003
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.029
 bank+0.005
lves-0.033
 drown-0.034
 station-0.036
Neg logit contributions
 ey-0.461
ad-0.431
 honey-0.424
idges-0.422
 yogurt-0.419
Token had
Token ID550
Feature activation-1.18e+00

Pos logit contributions
gy+1.532
 bank+1.268
lves+1.149
 drown+1.109
zag+1.068
Neg logit contributions
 ey-1.032
ad-0.883
 yogurt-0.868
idges-0.847
 honey-0.842
Token a
Token ID257
Feature activation+2.00e-01

Pos logit contributions
gy+0.111
 bank+0.089
lves+0.075
zag+0.072
 drown+0.071
Neg logit contributions
 ey-0.088
idges-0.076
ement-0.073
 yogurt-0.071
ad-0.070
Token lot
Token ID1256
Feature activation-4.96e+00

Pos logit contributions
 ey+0.013
 yogurt+0.010
 honey+0.010
idges+0.010
 sweet+0.010
Neg logit contributions
gy-0.020
 bank-0.017
lves-0.015
 station-0.014
zag-0.014
Token of
Token ID286
Feature activation+2.71e+00

Pos logit contributions
gy+0.401
 bank+0.333
zag+0.279
house+0.273
lves+0.259
Neg logit contributions
 ey-0.362
ement-0.321
ango-0.315
Jamie-0.307
idges-0.307
Token friends
Token ID2460
Feature activation+2.59e-01

Pos logit contributions
 ey+0.206
ement+0.203
idges+0.194
Jamie+0.186
mmmm+0.184
Neg logit contributions
gy-0.209
 bank-0.184
 fight-0.142
 argue-0.135
 drown-0.135
Token body
Token ID1767
Feature activation-9.39e-01

Pos logit contributions
gy+0.044
 bank+0.035
lves+0.034
 drown+0.030
 sank+0.029
Neg logit contributions
 ey-0.041
 honey-0.035
 yogurt-0.034
 sweet-0.034
ad-0.033
Token and
Token ID290
Feature activation-4.17e-01

Pos logit contributions
gy+0.094
 bank+0.078
lves+0.074
 drown+0.070
 argue+0.069
Neg logit contributions
 ey-0.055
 yogurt-0.046
ad-0.045
idges-0.042
 honey-0.042
Token a
Token ID257
Feature activation+2.27e-01

Pos logit contributions
gy+0.036
 bank+0.028
zag+0.022
lves+0.021
 neither+0.021
Neg logit contributions
 ey-0.035
idges-0.031
ement-0.031
ummy-0.029
ad-0.029
Token w
Token ID266
Feature activation+1.52e+00

Pos logit contributions
 ey+0.015
 honey+0.013
 yogurt+0.013
 sweet+0.012
idges+0.012
Neg logit contributions
gy-0.022
 bank-0.018
lves-0.016
zag-0.015
 drown-0.014
Tokenag
Token ID363
Feature activation-1.11e+00

Pos logit contributions
 ey+0.095
 yogurt+0.076
idges+0.076
 honey+0.074
ad+0.071
Neg logit contributions
gy-0.155
 bank-0.129
lves-0.113
zag-0.112
 drown-0.108
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.079
 bank+0.073
lves+0.060
 drown+0.056
 station+0.056
Neg logit contributions
 ey-0.090
ad-0.083
idges-0.076
ement-0.075
 yogurt-0.074
Token tail
Token ID7894
Feature activation-2.59e+00

Pos logit contributions
gy+1.249
lves+0.965
 drown+0.914
 bank+0.893
 neither+0.869
Neg logit contributions
 ey-1.218
 yogurt-1.092
 honey-1.081
 sweet-1.030
 goodness-1.027
Token.
Token ID13
Feature activation+1.39e-03

Pos logit contributions
gy+0.250
 bank+0.203
lves+0.183
 drown+0.170
 argue+0.168
Neg logit contributions
 ey-0.171
 yogurt-0.143
ad-0.143
idges-0.140
 honey-0.138
Token One
Token ID1881
Feature activation-5.50e+00

Pos logit contributions
 ey+0.000
idges+0.000
ement+0.000
illy+0.000
odic+0.000
Neg logit contributions
gy-0.000
 bank-0.000
 station-0.000
house-0.000
zag-0.000
Token day
Token ID1110
Feature activation-2.60e+00

Pos logit contributions
gy+0.438
 bank+0.356
lves+0.295
 drown+0.269
 argue+0.269
Neg logit contributions
 ey-0.468
 yogurt-0.408
 honey-0.398
ad-0.398
idges-0.394
Token,
Token ID11
Feature activation+2.66e-01

Pos logit contributions
gy+0.207
 bank+0.158
lves+0.125
zag+0.123
 neither+0.120
Neg logit contributions
 ey-0.231
idges-0.198
ad-0.191
ement-0.189
 yogurt-0.187
Token and
Token ID290
Feature activation-3.51e-01

Pos logit contributions
 ey+0.021
idges+0.018
 yogurt+0.017
ad+0.017
ement+0.016
Neg logit contributions
gy-0.017
 bank-0.013
lves-0.010
 neither-0.010
 argue-0.009
Token said
Token ID531
Feature activation-2.78e-01

Pos logit contributions
gy+0.033
 bank+0.027
lves+0.023
zag+0.022
 station+0.022
Neg logit contributions
 ey-0.025
idges-0.021
 yogurt-0.021
ad-0.021
 honey-0.020
Token,
Token ID11
Feature activation+2.03e-01

Pos logit contributions
gy+0.019
 bank+0.014
 neither+0.011
zag+0.011
 argue+0.010
Neg logit contributions
 ey-0.028
idges-0.023
ad-0.022
ement-0.022
ango-0.022
Token "
Token ID366
Feature activation+2.04e+00

Pos logit contributions
 ey+0.016
idges+0.013
ad+0.013
ement+0.012
 yogurt+0.012
Neg logit contributions
gy-0.019
 bank-0.015
 station-0.012
zag-0.012
lves-0.012
TokenDog
Token ID32942
Feature activation-8.41e+00

Pos logit contributions
 ey+0.142
idges+0.115
 honey+0.112
 yogurt+0.110
ement+0.109
Neg logit contributions
gy-0.201
 bank-0.162
lves-0.146
zag-0.135
 neither-0.133
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.387
 bank+0.251
lves+0.157
zag+0.125
 station+0.123
Neg logit contributions
 ey-0.998
idges-0.898
 yogurt-0.888
ad-0.887
 honey-0.877
Token,
Token ID11
Feature activation+2.19e-01

Pos logit contributions
gy+1.508
 bank+1.234
lves+1.052
zag+1.001
 station+0.994
Neg logit contributions
 ey-1.156
idges-0.963
 yogurt-0.944
ad-0.930
 honey-0.919
Token stop
Token ID2245
Feature activation-2.03e-01

Pos logit contributions
 ey+0.016
ement+0.013
idges+0.013
ad+0.012
 importantly+0.012
Neg logit contributions
gy-0.020
 bank-0.017
 station-0.014
lves-0.014
 drown-0.014
Token!
Token ID0
Feature activation+2.08e+00

Pos logit contributions
gy+0.020
 bank+0.016
lves+0.014
 drown+0.013
 station+0.013
Neg logit contributions
 ey-0.014
idges-0.012
ement-0.011
 yogurt-0.011
ad-0.011
Token You
Token ID921
Feature activation+7.36e-01

Pos logit contributions
 ey+0.135
idges+0.110
 yogurt+0.106
ement+0.104
 honey+0.103
Neg logit contributions
gy-0.214
 bank-0.173
lves-0.149
 drown-0.147
zag-0.145
Token're
Token ID821
Feature activation-2.64e+00

Pos logit contributions
 ey+0.048
idges+0.042
 honey+0.042
 yogurt+0.041
ad+0.041
Neg logit contributions
gy-0.071
 bank-0.058
lves-0.050
zag-0.048
 station-0.047
Tokenly
Token ID306
Feature activation+3.93e+00

Pos logit contributions
gy+0.048
 bank+0.041
lves+0.036
 drown+0.036
 argue+0.036
Neg logit contributions
 ey-0.022
idges-0.018
ad-0.018
 honey-0.018
 yogurt-0.017
Token said
Token ID531
Feature activation-4.08e-01

Pos logit contributions
 ey+0.344
idges+0.297
 yogurt+0.292
ad+0.289
 honey+0.286
Neg logit contributions
gy-0.306
 bank-0.239
lves-0.194
zag-0.182
 station-0.181
Token,
Token ID11
Feature activation+3.23e-01

Pos logit contributions
gy+0.031
 bank+0.024
zag+0.019
 neither+0.019
 drown+0.018
Neg logit contributions
 ey-0.038
idges-0.032
ement-0.030
ad-0.030
ango-0.029
Token "
Token ID366
Feature activation+2.07e+00

Pos logit contributions
 ey+0.021
idges+0.017
 yogurt+0.016
ad+0.016
ement+0.016
Neg logit contributions
gy-0.033
 bank-0.027
lves-0.023
 station-0.023
zag-0.023
TokenBug
Token ID25624
Feature activation-2.44e+00

Pos logit contributions
 ey+0.150
idges+0.122
 yogurt+0.119
 honey+0.118
ement+0.117
Neg logit contributions
gy-0.198
 bank-0.161
lves-0.142
zag-0.132
 station-0.131
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.208
 bank+0.168
lves+0.140
zag+0.132
 station+0.131
Neg logit contributions
 ey-0.195
idges-0.166
 yogurt-0.163
ad-0.162
 honey-0.160
Token,
Token ID11
Feature activation+3.11e-01

Pos logit contributions
gy+1.440
 bank+1.159
lves+0.945
zag+0.914
 station+0.913
Neg logit contributions
 ey-1.267
idges-1.063
 yogurt-1.024
ad-1.005
ement-1.003
Token today
Token ID1909
Feature activation-4.17e+00

Pos logit contributions
 ey+0.024
ement+0.020
idges+0.020
ad+0.019
 yogurt+0.019
Neg logit contributions
gy-0.028
 bank-0.023
lves-0.019
 station-0.019
 drown-0.019
Token was
Token ID373
Feature activation+1.15e+00

Pos logit contributions
gy+0.370
 bank+0.303
lves+0.246
 station+0.244
 drown+0.241
Neg logit contributions
 ey-0.324
idges-0.268
ad-0.260
 yogurt-0.257
ement-0.253
Token so
Token ID523
Feature activation+3.98e-01

Pos logit contributions
 ey+0.089
idges+0.074
ement+0.072
ad+0.071
 yogurt+0.069
Neg logit contributions
gy-0.105
 bank-0.085
lves-0.071
 drown-0.069
 station-0.068
Token much
Token ID881
Feature activation-1.96e+00

Pos logit contributions
 ey+0.036
idges+0.032
ement+0.031
ad+0.030
ango+0.030
Neg logit contributions
gy-0.028
 bank-0.022
 drown-0.019
 drowned-0.017
lves-0.017
Token Tim
Token ID5045
Feature activation-5.14e-01

Pos logit contributions
gy+0.001
 bank+0.001
house+0.001
 station+0.001
zag+0.001
Neg logit contributions
 ey-0.001
idges-0.001
ement-0.001
 honey-0.001
ad-0.001
Tokenmy
Token ID1820
Feature activation+2.54e+00

Pos logit contributions
gy+0.050
 bank+0.039
lves+0.033
 station+0.032
zag+0.032
Neg logit contributions
 ey-0.037
idges-0.032
ement-0.030
 honey-0.030
 yogurt-0.030
Token had
Token ID550
Feature activation-1.11e+00

Pos logit contributions
 ey+0.152
 yogurt+0.126
ad+0.124
idges+0.115
 sweet+0.114
Neg logit contributions
gy-0.249
 bank-0.217
lves-0.194
 drown-0.186
 argue-0.182
Token a
Token ID257
Feature activation+3.24e-01

Pos logit contributions
gy+0.107
 bank+0.088
lves+0.075
zag+0.071
 station+0.071
Neg logit contributions
 ey-0.079
idges-0.066
ement-0.062
 yogurt-0.062
ad-0.062
Token pig
Token ID12967
Feature activation-5.30e+00

Pos logit contributions
 ey+0.022
 yogurt+0.019
 honey+0.018
 sweet+0.018
 pasta+0.017
Neg logit contributions
gy-0.031
 bank-0.025
lves-0.022
 drown-0.021
zag-0.021
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.273
 drown+0.255
 bank+0.254
lves+0.235
 argue+0.231
Neg logit contributions
ad-0.431
 ey-0.428
 yogurt-0.410
 sweet-0.408
ummy-0.390
Token bank
Token ID3331
Feature activation-1.26e+01

Pos logit contributions
gy+1.030
lves+0.788
 drown+0.718
 bank+0.713
 neither+0.651
Neg logit contributions
 ey-1.386
 yogurt-1.318
 honey-1.291
ad-1.234
 sweet-1.232
Token that
Token ID326
Feature activation-8.68e-01

Pos logit contributions
gy+1.188
 bank+0.982
lves+0.819
zag+0.788
 station+0.787
Neg logit contributions
 ey-0.916
idges-0.758
 yogurt-0.727
ad-0.719
 honey-0.718
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
gy+0.090
 bank+0.076
lves+0.067
zag+0.064
 drown+0.064
Neg logit contributions
 ey-0.052
 yogurt-0.042
idges-0.041
 honey-0.041
ad-0.040
Token full
Token ID1336
Feature activation+1.74e+00

Pos logit contributions
 ey+0.080
 yogurt+0.069
 honey+0.068
idges+0.067
ad+0.067
Neg logit contributions
gy-0.096
 bank-0.077
lves-0.067
zag-0.064
 drown-0.063
Token of
Token ID286
Feature activation+2.75e+00

Pos logit contributions
 ey+0.127
idges+0.101
ement+0.094
Jamie+0.092
ad+0.092
Neg logit contributions
gy-0.162
 bank-0.142
 station-0.119
house-0.109
lves-0.107
Token day
Token ID1110
Feature activation-2.64e+00

Pos logit contributions
gy+0.482
 bank+0.425
lves+0.368
 argue+0.354
 drown+0.348
Neg logit contributions
 ey-0.375
 sweet-0.350
 honey-0.349
 yogurt-0.344
ummy-0.335
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
gy+0.212
 bank+0.163
lves+0.130
zag+0.128
 station+0.124
Neg logit contributions
 ey-0.231
idges-0.197
ad-0.191
ement-0.188
 yogurt-0.187
Token a
Token ID257
Feature activation+2.52e-01

Pos logit contributions
 ey+0.016
idges+0.014
ad+0.013
ement+0.013
 yogurt+0.013
Neg logit contributions
gy-0.021
 bank-0.017
lves-0.014
 station-0.014
zag-0.014
Token little
Token ID1310
Feature activation+1.03e+00

Pos logit contributions
 ey+0.014
 honey+0.012
 yogurt+0.012
idges+0.011
 sweet+0.011
Neg logit contributions
gy-0.027
 bank-0.023
lves-0.020
 argue-0.019
zag-0.019
Token pig
Token ID12967
Feature activation-5.36e+00

Pos logit contributions
 ey+0.057
 honey+0.056
 sweet+0.054
 yogurt+0.050
ummy+0.049
Neg logit contributions
gy-0.102
 bank-0.087
 argue-0.078
zag-0.077
 drowned-0.077
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.406
 bank+0.400
lves+0.374
 drown+0.373
 argue+0.363
Neg logit contributions
ad-0.307
 ey-0.303
 yogurt-0.253
illy-0.244
idges-0.242
Token named
Token ID3706
Feature activation-6.64e+00

Pos logit contributions
gy+1.430
 drown+1.201
lves+1.186
 argue+1.179
zag+1.144
Neg logit contributions
ad-0.774
 ey-0.704
 honey-0.689
 sweet-0.677
 yogurt-0.676
Token Pe
Token ID2631
Feature activation-2.89e+00

Pos logit contributions
gy+0.627
 bank+0.518
lves+0.441
zag+0.424
 station+0.416
Neg logit contributions
 ey-0.471
idges-0.394
 yogurt-0.391
 honey-0.383
ad-0.383
Tokenppa
Token ID44989
Feature activation-3.86e+00

Pos logit contributions
gy+0.251
 bank+0.209
 drown+0.174
lves+0.170
 argue+0.168
Neg logit contributions
 ey-0.205
idges-0.186
ad-0.177
 honey-0.176
 yogurt-0.172
Token went
Token ID1816
Feature activation-1.18e+00

Pos logit contributions
gy+0.333
 bank+0.295
lves+0.267
 drown+0.260
 argue+0.254
Neg logit contributions
 ey-0.237
ad-0.217
 yogurt-0.208
 honey-0.200
idges-0.199
Token for
Token ID329
Feature activation-1.75e+00

Pos logit contributions
gy+0.117
 bank+0.097
lves+0.094
 drowned+0.087
 neither+0.086
Neg logit contributions
 ey-0.066
 honey-0.060
 yogurt-0.059
idges-0.054
ad-0.053
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
gy+0.087
 bank+0.070
lves+0.056
zag+0.055
 station+0.055
Neg logit contributions
 ey-0.085
idges-0.069
ad-0.066
 yogurt-0.065
 honey-0.064
Token But
Token ID887
Feature activation-3.28e+00

Pos logit contributions
 ey+0.010
idges+0.008
 yogurt+0.008
ad+0.008
 honey+0.007
Neg logit contributions
gy-0.014
 bank-0.012
lves-0.010
zag-0.010
 station-0.010
Token when
Token ID618
Feature activation-9.40e-01

Pos logit contributions
gy+0.337
 bank+0.280
lves+0.257
zag+0.244
 drown+0.241
Neg logit contributions
 ey-0.183
 yogurt-0.164
 honey-0.158
ad-0.153
 goodness-0.144
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
gy+0.106
 bank+0.089
lves+0.082
zag+0.077
 station+0.076
Neg logit contributions
 ey-0.047
 yogurt-0.041
 honey-0.038
ad-0.038
idges-0.037
Token pig
Token ID12967
Feature activation-5.51e+00

Pos logit contributions
 ey+0.003
idges+0.003
ad+0.002
 yogurt+0.002
ement+0.002
Neg logit contributions
gy-0.002
 bank-0.002
lves-0.001
 station-0.001
zag-0.001
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.354
 bank+0.293
lves+0.263
 drown+0.254
 argue+0.237
Neg logit contributions
 ey-0.465
ad-0.433
 yogurt-0.408
idges-0.401
 honey-0.400
Token looked
Token ID3114
Feature activation+4.26e-01

Pos logit contributions
gy+1.348
 bank+1.037
lves+0.988
 drown+0.975
zag+0.934
Neg logit contributions
 ey-1.069
ad-1.003
 yogurt-0.973
 honey-0.957
idges-0.919
Token around
Token ID1088
Feature activation-2.49e+00

Pos logit contributions
 ey+0.039
idges+0.033
ad+0.033
 yogurt+0.032
mmmm+0.031
Neg logit contributions
gy-0.031
 bank-0.025
lves-0.020
 station-0.019
 neither-0.018
Token,
Token ID11
Feature activation+3.21e-01

Pos logit contributions
gy+0.191
 bank+0.152
 station+0.119
 fight+0.111
 argue+0.111
Neg logit contributions
 ey-0.220
idges-0.193
 yogurt-0.180
ad-0.178
mmmm-0.177
Token he
Token ID339
Feature activation+8.01e-01

Pos logit contributions
 ey+0.019
idges+0.016
 yogurt+0.015
ad+0.015
 honey+0.015
Neg logit contributions
gy-0.034
 bank-0.028
lves-0.025
zag-0.024
 station-0.024
Token saw
Token ID2497
Feature activation-1.16e+00

Pos logit contributions
 ey+0.066
idges+0.057
 yogurt+0.057
ad+0.056
 honey+0.055
Neg logit contributions
gy-0.065
 bank-0.051
lves-0.043
zag-0.041
 drown-0.040
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
gy+0.001
 bank+0.001
 station+0.001
zag+0.001
 neither+0.001
Neg logit contributions
 ey-0.001
idges-0.001
 honey-0.001
ad-0.001
ement-0.001
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
gy+0.011
 bank+0.008
zag+0.007
 station+0.007
lves+0.007
Neg logit contributions
 ey-0.011
 honey-0.009
idges-0.009
 yogurt-0.009
ement-0.009
Token"
Token ID1
Feature activation-1.40e+00

Pos logit contributions
gy+0.010
 bank+0.008
lves+0.007
 station+0.007
zag+0.007
Neg logit contributions
 ey-0.008
idges-0.007
 honey-0.007
ement-0.007
 yogurt-0.007
TokenThe
Token ID464
Feature activation-4.25e-01

Pos logit contributions
gy+0.135
 bank+0.114
lves+0.099
zag+0.095
 station+0.095
Neg logit contributions
 ey-0.096
 honey-0.079
idges-0.077
ement-0.076
 yogurt-0.073
Token pig
Token ID12967
Feature activation-5.27e+00

Pos logit contributions
gy+0.035
 bank+0.031
 station+0.025
lves+0.023
 fight+0.023
Neg logit contributions
 ey-0.035
idges-0.031
ad-0.029
ement-0.028
 importantly-0.027
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.472
 bank+0.387
lves+0.337
 drown+0.314
zag+0.311
Neg logit contributions
 ey-0.385
idges-0.324
 yogurt-0.320
ad-0.320
 honey-0.313
Token bank
Token ID3331
Feature activation-1.26e+01

Pos logit contributions
gy+1.415
 bank+1.121
lves+0.998
 drown+0.946
zag+0.945
Neg logit contributions
 ey-1.172
 yogurt-1.004
ad-0.996
idges-0.995
 honey-0.980
Token!"
Token ID2474
Feature activation+3.12e-01

Pos logit contributions
gy+1.124
 bank+0.942
lves+0.748
 station+0.746
zag+0.735
Neg logit contributions
 ey-0.961
idges-0.796
 yogurt-0.771
ad-0.759
 honey-0.758
Token said
Token ID531
Feature activation-5.16e-01

Pos logit contributions
 ey+0.017
 yogurt+0.014
idges+0.013
ad+0.013
 honey+0.013
Neg logit contributions
gy-0.035
 bank-0.029
lves-0.026
zag-0.025
 drown-0.025
Token the
Token ID262
Feature activation-2.69e-02

Pos logit contributions
gy+0.058
 bank+0.051
lves+0.047
zag+0.044
 drown+0.043
Neg logit contributions
 ey-0.024
 yogurt-0.020
ad-0.019
 honey-0.018
idges-0.018
Token little
Token ID1310
Feature activation+1.13e+00

Pos logit contributions
gy+0.002
 bank+0.002
 station+0.002
lves+0.002
 argue+0.001
Neg logit contributions
 ey-0.002
idges-0.002
ad-0.002
ement-0.002
 yogurt-0.002
Token day
Token ID1110
Feature activation-2.71e+00

Pos logit contributions
gy+0.080
 bank+0.064
lves+0.054
 drown+0.049
zag+0.048
Neg logit contributions
 ey-0.084
 yogurt-0.072
ad-0.072
 honey-0.072
idges-0.071
Token onwards
Token ID31719
Feature activation-1.11e+00

Pos logit contributions
gy+0.235
 bank+0.194
lves+0.164
 station+0.150
 argue+0.149
Neg logit contributions
 ey-0.207
idges-0.183
ad-0.183
 yogurt-0.178
 honey-0.177
Token,
Token ID11
Feature activation+1.89e-01

Pos logit contributions
gy+0.101
 bank+0.083
lves+0.070
zag+0.067
 drown+0.067
Neg logit contributions
 ey-0.082
idges-0.070
 yogurt-0.069
 honey-0.068
ad-0.068
Token the
Token ID262
Feature activation+3.77e-03

Pos logit contributions
 ey+0.012
idges+0.010
 yogurt+0.010
 honey+0.010
ad+0.010
Neg logit contributions
gy-0.018
 bank-0.015
lves-0.013
zag-0.013
 drown-0.013
Token pig
Token ID12967
Feature activation-5.38e+00

Pos logit contributions
 ey+0.000
idges+0.000
 yogurt+0.000
ad+0.000
ement+0.000
Neg logit contributions
gy-0.000
 bank-0.000
lves-0.000
 station-0.000
zag-0.000
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.470
 bank+0.389
lves+0.340
 drown+0.321
 argue+0.316
Neg logit contributions
 ey-0.392
ad-0.334
idges-0.331
 yogurt-0.324
 honey-0.320
Token was
Token ID373
Feature activation+9.87e-01

Pos logit contributions
gy+1.458
 bank+1.187
lves+1.037
 drown+0.987
zag+0.974
Neg logit contributions
 ey-1.131
idges-0.957
ad-0.951
 yogurt-0.947
 honey-0.934
Token thankful
Token ID25535
Feature activation+1.54e+00

Pos logit contributions
 ey+0.080
idges+0.069
 yogurt+0.068
ad+0.068
 honey+0.067
Neg logit contributions
gy-0.082
 bank-0.066
lves-0.055
zag-0.051
 station-0.051
Token and
Token ID290
Feature activation-4.76e-01

Pos logit contributions
 ey+0.147
idges+0.127
ement+0.121
 yogurt+0.120
ad+0.118
Neg logit contributions
gy-0.109
 bank-0.083
 neither-0.065
zag-0.062
 station-0.062
Token more
Token ID517
Feature activation+1.60e+00

Pos logit contributions
gy+0.043
 bank+0.034
lves+0.029
 station+0.027
zag+0.027
Neg logit contributions
 ey-0.037
idges-0.031
 yogurt-0.030
ement-0.030
ad-0.029
Token careful
Token ID8161
Feature activation+5.17e-01

Pos logit contributions
 ey+0.120
idges+0.091
ad+0.090
mmmm+0.089
 yogurt+0.088
Neg logit contributions
gy-0.141
 bank-0.116
lves-0.104
house-0.097
 station-0.097
Token the
Token ID262
Feature activation-1.96e-01

Pos logit contributions
gy+0.039
 bank+0.031
lves+0.027
zag+0.025
 drown+0.025
Neg logit contributions
 ey-0.037
 yogurt-0.032
idges-0.031
 honey-0.031
ad-0.031
Token raced
Token ID32897
Feature activation-2.30e+00

Pos logit contributions
gy+0.014
 bank+0.011
 station+0.008
lves+0.008
zag+0.008
Neg logit contributions
 ey-0.018
idges-0.016
ad-0.016
ement-0.015
 yogurt-0.015
Token the
Token ID262
Feature activation-2.19e-01

Pos logit contributions
gy+0.192
 bank+0.151
lves+0.128
zag+0.119
 drown+0.118
Neg logit contributions
 ey-0.189
idges-0.162
 yogurt-0.161
ad-0.160
 honey-0.157
Token s
Token ID264
Feature activation-1.30e+00

Pos logit contributions
gy+0.016
 bank+0.012
lves+0.010
zag+0.009
 station+0.009
Neg logit contributions
 ey-0.020
idges-0.018
 yogurt-0.018
ad-0.017
 honey-0.017
Tokenog
Token ID519
Feature activation-3.56e+00

Pos logit contributions
gy+0.115
 bank+0.095
 station+0.082
zag+0.081
house+0.079
Neg logit contributions
 ey-0.093
 honey-0.079
 sweet-0.074
idges-0.074
 yogurt-0.073
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.181
 bank+0.140
lves+0.129
 drown+0.116
 argue+0.101
Neg logit contributions
 ey-0.333
ad-0.326
 yogurt-0.311
idges-0.309
 honey-0.302
Token race
Token ID3234
Feature activation-5.49e+00

Pos logit contributions
gy+0.856
lves+0.540
 drown+0.463
 neither+0.456
 bank+0.443
Neg logit contributions
 ey-1.581
 yogurt-1.489
 honey-1.458
 pasta-1.401
ad-1.397
Token car
Token ID1097
Feature activation-6.98e+00

Pos logit contributions
gy+0.524
 bank+0.422
lves+0.393
 drown+0.363
zag+0.348
Neg logit contributions
 ey-0.353
ad-0.313
 yogurt-0.303
idges-0.298
ement-0.288
Token around
Token ID1088
Feature activation-2.50e+00

Pos logit contributions
gy+0.687
 bank+0.566
lves+0.554
 drown+0.521
 drowned+0.492
Neg logit contributions
 ey-0.361
ad-0.347
 yogurt-0.319
idges-0.311
ement-0.303
Token the
Token ID262
Feature activation-2.59e-01

Pos logit contributions
gy+0.232
 bank+0.189
lves+0.155
 station+0.152
zag+0.149
Neg logit contributions
 ey-0.188
idges-0.157
 yogurt-0.151
 honey-0.148
ad-0.146
Token bowl
Token ID9396
Feature activation+3.59e+00

Pos logit contributions
gy+0.022
 bank+0.017
lves+0.014
zag+0.014
 station+0.013
Neg logit contributions
 ey-0.021
idges-0.018
 yogurt-0.018
ad-0.018
 honey-0.017
Token a
Token ID257
Feature activation+2.67e-01

Pos logit contributions
 ey+0.077
idges+0.065
ement+0.061
ad+0.061
 yogurt+0.059
Neg logit contributions
gy-0.093
 bank-0.074
lves-0.063
 station-0.060
zag-0.058
Token modest
Token ID12949
Feature activation+5.81e-02

Pos logit contributions
 ey+0.017
 yogurt+0.014
idges+0.013
 honey+0.013
ad+0.013
Neg logit contributions
gy-0.028
 bank-0.023
lves-0.020
zag-0.019
 drown-0.019
Token dog
Token ID3290
Feature activation-4.96e+00

Pos logit contributions
 ey+0.004
 yogurt+0.004
 honey+0.004
idges+0.004
ad+0.004
Neg logit contributions
gy-0.005
 bank-0.004
lves-0.003
 drown-0.003
zag-0.003
Token called
Token ID1444
Feature activation-1.76e+00

Pos logit contributions
gy+0.332
 bank+0.278
lves+0.228
 drown+0.224
 argue+0.218
Neg logit contributions
 ey-0.415
ad-0.399
 yogurt-0.397
 honey-0.378
idges-0.377
Token Dog
Token ID8532
Feature activation-5.28e+00

Pos logit contributions
gy+0.160
 bank+0.130
lves+0.110
zag+0.104
 station+0.103
Neg logit contributions
 ey-0.131
idges-0.110
 yogurt-0.108
ad-0.107
 honey-0.106
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.204
 bank+0.198
 drown+0.151
lves+0.139
 argue+0.131
Neg logit contributions
ad-0.520
 ey-0.495
ango-0.491
 sweet-0.488
 honey-0.485
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
gy+1.529
 bank+1.254
lves+1.198
 drown+1.139
 argue+1.092
Neg logit contributions
 ey-0.917
ad-0.830
 yogurt-0.826
 honey-0.796
ummy-0.768
Token One
Token ID1881
Feature activation-5.49e+00

Pos logit contributions
 ey+0.001
ad+0.001
 honey+0.001
idges+0.001
 sweet+0.001
Neg logit contributions
gy-0.001
 bank-0.001
lves-0.001
 drown-0.001
zag-0.001
Token day
Token ID1110
Feature activation-2.55e+00

Pos logit contributions
gy+0.444
 bank+0.365
lves+0.303
 drown+0.280
 argue+0.280
Neg logit contributions
 ey-0.451
 yogurt-0.394
ad-0.387
 honey-0.385
idges-0.381
Token,
Token ID11
Feature activation+3.01e-01

Pos logit contributions
gy+0.239
 bank+0.205
lves+0.176
 station+0.165
 drown+0.165
Neg logit contributions
 ey-0.169
idges-0.146
 honey-0.145
 yogurt-0.144
ad-0.139
Token Dog
Token ID8532
Feature activation-5.25e+00

Pos logit contributions
 ey+0.021
 honey+0.021
 sweet+0.020
idges+0.020
 importantly+0.019
Neg logit contributions
gy-0.024
 bank-0.021
lves-0.017
 drown-0.017
 argue-0.016
Token cookies
Token ID14746
Feature activation+4.69e+00

Pos logit contributions
gy+0.548
 bank+0.447
lves+0.380
zag+0.360
 station+0.358
Neg logit contributions
 ey-0.437
idges-0.365
 yogurt-0.358
ad-0.353
 honey-0.349
Token got
Token ID1392
Feature activation-5.25e+00

Pos logit contributions
 ey+0.335
idges+0.289
ad+0.285
 yogurt+0.284
 honey+0.284
Neg logit contributions
gy-0.430
 bank-0.327
lves-0.305
zag-0.271
 argue-0.261
Token all
Token ID477
Feature activation-3.91e+00

Pos logit contributions
gy+0.455
 bank+0.370
lves+0.315
zag+0.308
 station+0.299
Neg logit contributions
 ey-0.387
 honey-0.347
idges-0.343
 yogurt-0.339
ad-0.332
Token s
Token ID264
Feature activation-1.37e+00

Pos logit contributions
gy+0.340
 bank+0.279
lves+0.241
zag+0.220
 station+0.217
Neg logit contributions
 ey-0.293
 yogurt-0.254
 honey-0.252
idges-0.251
ad-0.251
Tokenog
Token ID519
Feature activation-3.64e+00

Pos logit contributions
gy+0.114
 bank+0.085
lves+0.074
zag+0.069
 drowned+0.067
Neg logit contributions
 ey-0.112
 honey-0.098
 yogurt-0.095
 importantly-0.090
 sweet-0.090
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.015
 bank-0.009
lves-0.035
 drown-0.052
 argue-0.059
Neg logit contributions
 ey-0.508
ad-0.492
idges-0.484
 honey-0.477
 yogurt-0.472
Token and
Token ID290
Feature activation-5.00e-01

Pos logit contributions
gy+1.479
 bank+1.165
lves+1.153
 drown+1.015
 station+1.010
Neg logit contributions
 ey-0.996
 honey-0.895
 yogurt-0.873
 sweet-0.842
ad-0.832
Token Jerry
Token ID13075
Feature activation-1.31e+00

Pos logit contributions
gy+0.044
 bank+0.035
lves+0.030
zag+0.029
 station+0.028
Neg logit contributions
 ey-0.038
 yogurt-0.032
idges-0.032
 honey-0.032
ad-0.031
Token was
Token ID373
Feature activation+9.66e-01

Pos logit contributions
gy+0.114
 bank+0.092
lves+0.083
 station+0.077
zag+0.077
Neg logit contributions
 ey-0.085
ad-0.079
 honey-0.077
 yogurt-0.075
idges-0.074
Token in
Token ID287
Feature activation+1.18e+00

Pos logit contributions
 ey+0.066
 honey+0.059
ad+0.058
idges+0.058
 sweet+0.057
Neg logit contributions
gy-0.087
 bank-0.072
lves-0.061
zag-0.058
 station-0.058
Token a
Token ID257
Feature activation+1.20e-01

Pos logit contributions
 ey+0.078
 yogurt+0.062
ad+0.062
idges+0.062
 honey+0.061
Neg logit contributions
gy-0.119
 bank-0.098
lves-0.086
zag-0.083
 station-0.081
Token there
Token ID612
Feature activation-1.42e+00

Pos logit contributions
 ey+0.025
 yogurt+0.021
idges+0.021
 honey+0.021
ad+0.020
Neg logit contributions
gy-0.032
 bank-0.028
lves-0.023
 station-0.022
 drown-0.022
Token was
Token ID373
Feature activation+1.12e+00

Pos logit contributions
gy+0.119
 bank+0.091
lves+0.073
 station+0.072
zag+0.072
Neg logit contributions
 ey-0.121
idges-0.105
 honey-0.099
 yogurt-0.098
ement-0.095
Token a
Token ID257
Feature activation+4.05e-01

Pos logit contributions
 ey+0.082
idges+0.069
ement+0.065
ad+0.064
 yogurt+0.064
Neg logit contributions
gy-0.105
 bank-0.084
lves-0.072
 station-0.069
zag-0.067
Token generous
Token ID14431
Feature activation+4.81e+00

Pos logit contributions
 ey+0.024
 yogurt+0.019
 honey+0.019
idges+0.019
 sweet+0.018
Neg logit contributions
gy-0.043
 bank-0.036
lves-0.031
zag-0.030
 drown-0.030
Token pig
Token ID12967
Feature activation-5.23e+00

Pos logit contributions
 ey+0.392
idges+0.334
 yogurt+0.328
ad+0.324
 honey+0.320
Neg logit contributions
gy-0.406
 bank-0.324
lves-0.269
zag-0.254
 station-0.253
Tokengy
Token ID1360
Feature activation-1.61e+01

Pos logit contributions
gy+0.314
 bank+0.311
 drown+0.299
 argue+0.279
lves+0.279
Neg logit contributions
ad-0.394
 ey-0.349
ummy-0.348
 sweet-0.338
 goodness-0.335
Token.
Token ID13
Feature activation+1.37e-01

Pos logit contributions
gy+1.289
 drown+1.006
lves+1.006
 bank+0.973
 argue+0.956
Neg logit contributions
 ey-1.001
ad-0.979
 yogurt-0.961
 honey-0.939
ummy-0.930
Token He
Token ID679
Feature activation+2.79e+00

Pos logit contributions
 ey+0.010
idges+0.009
 yogurt+0.008
ement+0.008
 honey+0.008
Neg logit contributions
gy-0.013
 bank-0.010
lves-0.008
 station-0.008
zag-0.008
Token wanted
Token ID2227
Feature activation-1.29e+00

Pos logit contributions
 ey+0.203
 yogurt+0.170
idges+0.169
ad+0.169
 honey+0.165
Neg logit contributions
gy-0.254
 bank-0.208
lves-0.178
 drown-0.169
zag-0.169
Token to
Token ID284
Feature activation+6.57e-01

Pos logit contributions
gy+0.088
 bank+0.072
 station+0.051
lves+0.048
 drown+0.047
Neg logit contributions
 ey-0.129
ement-0.114
idges-0.112
ad-0.105
 importantly-0.104
Token give
Token ID1577
Feature activation-1.33e+00

Pos logit contributions
 ey+0.055
idges+0.048
 yogurt+0.046
ement+0.046
ad+0.045
Neg logit contributions
gy-0.054
 bank-0.043
lves-0.034
 station-0.033
zag-0.033
Token.
Token ID13
Feature activation+7.60e-02

Pos logit contributions
 ey+0.226
idges+0.190
 yogurt+0.187
ad+0.184
 honey+0.182
Neg logit contributions
gy-0.271
 bank-0.220
lves-0.186
zag-0.176
 station-0.175
Token
Token ID198
Feature activation+7.72e-02

Pos logit contributions
 ey+0.005
idges+0.005
ad+0.004
 yogurt+0.004
 honey+0.004
Neg logit contributions
gy-0.007
 bank-0.006
lves-0.005
 station-0.005
zag-0.005
Token
Token ID198
Feature activation+7.42e-02

Pos logit contributions
 ey+0.006
idges+0.005
 yogurt+0.005
 honey+0.005
ad+0.005
Neg logit contributions
gy-0.007
 bank-0.006
lves-0.005
zag-0.005
 station-0.005
TokenMom
Token ID29252
Feature activation+4.02e+00

Pos logit contributions
 ey+0.004
idges+0.003
 yogurt+0.003
ad+0.003
ement+0.003
Neg logit contributions
gy-0.008
 bank-0.007
lves-0.006
 drown-0.006
zag-0.006
Token and
Token ID290
Feature activation-4.34e-01

Pos logit contributions
 ey+0.351
idges+0.304
 yogurt+0.298
 importantly+0.297
mmmm+0.296
Neg logit contributions
gy-0.298
 bank-0.233
 station-0.209
zag-0.190
 argue-0.180
Token Dad
Token ID17415
Feature activation+5.35e+00

Pos logit contributions
gy+0.043
 bank+0.037
 argue+0.032
 station+0.032
 neither+0.032
Neg logit contributions
 ey-0.028
ement-0.023
idges-0.023
ad-0.022
odic-0.021
Token hear
Token ID3285
Feature activation-3.24e-01

Pos logit contributions
 ey+0.424
idges+0.358
 yogurt+0.347
ement+0.342
 importantly+0.339
Neg logit contributions
gy-0.457
 bank-0.379
 station-0.309
 argue-0.308
lves-0.300
Token them
Token ID606
Feature activation-8.74e-01

Pos logit contributions
gy+0.027
 bank+0.022
 station+0.018
lves+0.018
 argue+0.017
Neg logit contributions
 ey-0.027
idges-0.022
 yogurt-0.021
ement-0.021
ad-0.021
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
gy+0.084
 bank+0.070
lves+0.063
zag+0.057
 drown+0.055
Neg logit contributions
 ey-0.058
ad-0.049
 yogurt-0.048
idges-0.048
 honey-0.048
Token They
Token ID1119
Feature activation-3.90e+00

Pos logit contributions
 ey+0.012
idges+0.010
ad+0.010
 yogurt+0.010
 honey+0.010
Neg logit contributions
gy-0.008
 bank-0.006
lves-0.004
 station-0.004
zag-0.004
Token are
Token ID389
Feature activation+1.97e-02

Pos logit contributions
gy+0.328
 bank+0.263
lves+0.216
 station+0.208
 argue+0.206
Neg logit contributions
 ey-0.317
idges-0.271
 yogurt-0.268
ement-0.261
 honey-0.260
Token the
Token ID262
Feature activation-2.09e-02

Pos logit contributions
 ey+0.086
idges+0.070
 yogurt+0.069
ad+0.068
 honey+0.067
Neg logit contributions
gy-0.128
 bank-0.106
lves-0.091
zag-0.087
 station-0.086
Token city
Token ID1748
Feature activation-4.46e+00

Pos logit contributions
gy+0.002
 bank+0.002
lves+0.001
zag+0.001
 drown+0.001
Neg logit contributions
 ey-0.002
idges-0.001
 yogurt-0.001
ad-0.001
 honey-0.001
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
gy+0.452
 bank+0.365
lves+0.343
 drown+0.318
 drowned+0.302
Neg logit contributions
 ey-0.266
 yogurt-0.227
ad-0.226
 honey-0.223
ement-0.223
Token They
Token ID1119
Feature activation-3.79e+00

Pos logit contributions
 ey+0.022
idges+0.020
ad+0.019
 yogurt+0.019
 honey+0.019
Neg logit contributions
gy-0.015
 bank-0.011
lves-0.008
 station-0.008
 drown-0.008
Token say
Token ID910
Feature activation+1.51e+00

Pos logit contributions
gy+0.350
 bank+0.275
lves+0.243
zag+0.222
 station+0.214
Neg logit contributions
 ey-0.285
ad-0.237
 yogurt-0.234
idges-0.233
 honey-0.230
Token hello
Token ID23748
Feature activation+5.62e+00

Pos logit contributions
 ey+0.117
idges+0.095
ad+0.091
 yogurt+0.090
ement+0.089
Neg logit contributions
gy-0.133
 bank-0.110
 station-0.091
zag-0.090
 argue-0.089
Token to
Token ID284
Feature activation+6.89e-01

Pos logit contributions
 ey+0.400
 yogurt+0.335
idges+0.334
 honey+0.333
ad+0.331
Neg logit contributions
gy-0.510
 bank-0.426
lves-0.370
 drown-0.342
zag-0.336
Token the
Token ID262
Feature activation+3.50e-02

Pos logit contributions
 ey+0.046
idges+0.039
 yogurt+0.039
 honey+0.038
ad+0.038
Neg logit contributions
gy-0.067
 bank-0.055
lves-0.048
zag-0.046
 drown-0.044
Token people
Token ID661
Feature activation+6.32e-01

Pos logit contributions
 ey+0.002
idges+0.002
 yogurt+0.002
ad+0.002
 honey+0.002
Neg logit contributions
gy-0.003
 bank-0.003
lves-0.002
 station-0.002
zag-0.002
Token and
Token ID290
Feature activation-3.05e-01

Pos logit contributions
 ey+0.042
idges+0.036
 yogurt+0.036
ad+0.035
 honey+0.035
Neg logit contributions
gy-0.061
 bank-0.050
lves-0.044
 drown-0.041
zag-0.040
Token the
Token ID262
Feature activation+2.51e-02

Pos logit contributions
gy+0.030
 bank+0.024
lves+0.021
zag+0.020
 drown+0.020
Neg logit contributions
 ey-0.021
 yogurt-0.017
idges-0.017
 honey-0.017
ad-0.016
Token're
Token ID821
Feature activation-2.38e+00

Pos logit contributions
 ey+0.181
ad+0.161
idges+0.156
 honey+0.153
 yogurt+0.148
Neg logit contributions
gy-0.281
 bank-0.237
lves-0.204
zag-0.195
 station-0.191
Token the
Token ID262
Feature activation+3.69e-02

Pos logit contributions
gy+0.230
 bank+0.190
lves+0.162
zag+0.155
 station+0.154
Neg logit contributions
 ey-0.168
idges-0.139
 yogurt-0.136
ad-0.134
 honey-0.132
Token best
Token ID1266
Feature activation-6.84e-01

Pos logit contributions
 ey+0.002
 honey+0.002
ad+0.002
 sweet+0.002
 yogurt+0.002
Neg logit contributions
gy-0.004
 bank-0.003
lves-0.002
zag-0.002
 argue-0.002
Token at
Token ID379
Feature activation-2.99e+00

Pos logit contributions
gy+0.062
 bank+0.054
lves+0.047
 banks+0.042
 argue+0.042
Neg logit contributions
 ey-0.045
 honey-0.042
ummy-0.041
ad-0.041
 yogurt-0.041
Token calling
Token ID4585
Feature activation+1.11e+00

Pos logit contributions
gy+0.285
 bank+0.236
lves+0.205
 station+0.187
zag+0.187
Neg logit contributions
 ey-0.209
idges-0.175
 yogurt-0.173
 honey-0.172
ad-0.172
Token birds
Token ID10087
Feature activation+5.23e+00

Pos logit contributions
 ey+0.081
idges+0.064
 yogurt+0.062
ement+0.061
ad+0.060
Neg logit contributions
gy-0.107
 bank-0.087
lves-0.073
 station-0.073
zag-0.071
Token!"
Token ID2474
Feature activation+4.88e-01

Pos logit contributions
 ey+0.279
 honey+0.265
idges+0.250
 yogurt+0.245
 sweet+0.241
Neg logit contributions
gy-0.516
 bank-0.440
lves-0.392
zag-0.349
 station-0.346
Token Max
Token ID5436
Feature activation+8.54e-02

Pos logit contributions
 ey+0.036
idges+0.030
 yogurt+0.030
ad+0.029
 honey+0.029
Neg logit contributions
gy-0.045
 bank-0.037
lves-0.031
zag-0.029
 station-0.029
Token bark
Token ID21405
Feature activation-3.08e+00

Pos logit contributions
 ey+0.006
ad+0.005
 yogurt+0.005
 honey+0.005
idges+0.005
Neg logit contributions
gy-0.008
 bank-0.007
lves-0.006
 drown-0.006
 station-0.005
Tokened
Token ID276
Feature activation-1.37e+00

Pos logit contributions
gy+0.285
 bank+0.237
lves+0.203
 station+0.195
 drown+0.195
Neg logit contributions
 ey-0.210
ad-0.182
idges-0.178
ement-0.177
 yogurt-0.177
Token happily
Token ID18177
Feature activation+3.55e-01

Pos logit contributions
gy+0.124
 bank+0.101
lves+0.087
zag+0.084
 station+0.082
Neg logit contributions
 ey-0.101
 honey-0.084
 yogurt-0.084
idges-0.084
ad-0.083
Token looking
Token ID2045
Feature activation+3.32e+00

Pos logit contributions
gy+0.426
 bank+0.352
lves+0.302
zag+0.294
 station+0.290
Neg logit contributions
 ey-0.286
 yogurt-0.246
 honey-0.245
idges-0.239
ad-0.238
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
 ey+0.256
idges+0.216
 yogurt+0.212
ad+0.209
 honey+0.207
Neg logit contributions
gy-0.296
 bank-0.239
lves-0.201
zag-0.191
 station-0.189
Token But
Token ID887
Feature activation-3.05e+00

Pos logit contributions
 ey+0.013
idges+0.011
 yogurt+0.010
ad+0.010
 honey+0.010
Neg logit contributions
gy-0.025
 bank-0.021
lves-0.018
 station-0.017
zag-0.017
Token Tommy
Token ID19919
Feature activation+9.98e-01

Pos logit contributions
gy+0.311
 bank+0.266
lves+0.240
zag+0.236
 drown+0.235
Neg logit contributions
 ey-0.162
 yogurt-0.150
ad-0.143
 honey-0.139
 himself-0.136
Token caught
Token ID4978
Feature activation-2.11e+00

Pos logit contributions
 ey+0.063
ad+0.058
 yogurt+0.056
 honey+0.055
idges+0.055
Neg logit contributions
gy-0.086
 bank-0.070
 drown-0.065
lves-0.064
zag-0.061
Token him
Token ID683
Feature activation+6.53e+00

Pos logit contributions
gy+0.204
 bank+0.167
lves+0.143
 station+0.133
zag+0.132
Neg logit contributions
 ey-0.151
idges-0.124
 yogurt-0.119
ad-0.118
 honey-0.116
Token and
Token ID290
Feature activation-2.26e-01

Pos logit contributions
 ey+0.420
 yogurt+0.359
 honey+0.352
ad+0.349
idges+0.345
Neg logit contributions
gy-0.625
 bank-0.509
lves-0.463
 drown-0.438
 station-0.427
Token got
Token ID1392
Feature activation-5.08e+00

Pos logit contributions
gy+0.020
 bank+0.016
lves+0.014
zag+0.014
 drown+0.013
Neg logit contributions
 ey-0.016
 yogurt-0.015
 honey-0.015
idges-0.014
ad-0.014
Token very
Token ID845
Feature activation-7.19e-01

Pos logit contributions
gy+0.481
 bank+0.381
zag+0.339
lves+0.333
 station+0.324
Neg logit contributions
 ey-0.358
 yogurt-0.313
ad-0.302
 honey-0.301
idges-0.299
Token upset
Token ID9247
Feature activation-4.84e+00

Pos logit contributions
gy+0.064
 bank+0.049
lves+0.043
 station+0.042
zag+0.042
Neg logit contributions
 ey-0.057
 yogurt-0.049
idges-0.047
ad-0.047
 honey-0.047
Token.
Token ID13
Feature activation+2.21e-01

Pos logit contributions
gy+0.368
 bank+0.292
 neither+0.222
lves+0.214
 station+0.214
Neg logit contributions
 ey-0.448
idges-0.375
ad-0.354
 yogurt-0.353
mmmm-0.351
Token y
Token ID331
Feature activation+4.38e+00

Pos logit contributions
 ey+0.002
idges+0.002
ad+0.002
 yogurt+0.002
ement+0.002
Neg logit contributions
gy-0.003
 bank-0.003
 station-0.002
lves-0.002
 fight-0.002
Tokenummy
Token ID13513
Feature activation+8.82e+00

Pos logit contributions
 ey+0.129
idges+0.081
ad+0.065
 importantly+0.060
 yogurt+0.060
Neg logit contributions
gy-0.597
 bank-0.523
lves-0.455
 station-0.453
house-0.447
Token sugar
Token ID7543
Feature activation+7.82e+00

Pos logit contributions
 ey+0.578
idges+0.490
ad+0.456
 importantly+0.452
ango+0.439
Neg logit contributions
gy-0.861
 bank-0.748
 station-0.624
 fight-0.620
house-0.605
Token for
Token ID329
Feature activation-1.54e+00

Pos logit contributions
 ey+0.462
 yogurt+0.427
 honey+0.409
ummy+0.395
ad+0.380
Neg logit contributions
gy-0.770
 bank-0.630
lves-0.613
 drown-0.551
 drowned-0.536
Token the
Token ID262
Feature activation+5.79e-02

Pos logit contributions
gy+0.153
 bank+0.130
 drown+0.105
 neither+0.104
 drowned+0.104
Neg logit contributions
 ey-0.110
idges-0.082
ement-0.078
 importantly-0.072
ad-0.072
Token cake
Token ID12187
Feature activation+4.98e+00

Pos logit contributions
 ey+0.005
idges+0.004
ad+0.004
ement+0.004
 yogurt+0.004
Neg logit contributions
gy-0.005
 bank-0.004
lves-0.003
 station-0.003
 fight-0.003
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
 ey+0.326
 yogurt+0.283
 honey+0.273
idges+0.270
ad+0.267
Neg logit contributions
gy-0.478
 bank-0.392
lves-0.358
 drown-0.328
zag-0.322
Token
Token ID198
Feature activation+1.24e-01

Pos logit contributions
 ey+0.029
idges+0.025
ement+0.023
ad+0.023
 yogurt+0.023
Neg logit contributions
gy-0.031
 bank-0.025
lves-0.019
zag-0.019
 station-0.019
Token
Token ID198
Feature activation+1.31e-01

Pos logit contributions
 ey+0.010
idges+0.008
 yogurt+0.008
 honey+0.008
ement+0.008
Neg logit contributions
gy-0.011
 bank-0.009
zag-0.007
lves-0.007
 station-0.007
TokenThe
Token ID464
Feature activation-2.28e-01

Pos logit contributions
 ey+0.009
ement+0.008
idges+0.008
 yogurt+0.008
 honey+0.007
Neg logit contributions
gy-0.013
 bank-0.011
lves-0.009
zag-0.009
 station-0.009
Token bear
Token ID6842
Feature activation-7.12e-01

Pos logit contributions
gy+0.017
 bank+0.013
 station+0.010
 fight+0.010
lves+0.010
Neg logit contributions
 ey-0.021
idges-0.019
ad-0.018
ement-0.018
mmmm-0.018
Token back
Token ID736
Feature activation-5.46e-01

Pos logit contributions
gy+0.410
 bank+0.330
lves+0.300
 drown+0.279
 station+0.270
Neg logit contributions
 ey-0.347
 yogurt-0.314
 honey-0.309
ad-0.294
idges-0.290
Token on
Token ID319
Feature activation-1.26e+00

Pos logit contributions
gy+0.043
 bank+0.034
lves+0.027
zag+0.026
 station+0.025
Neg logit contributions
 ey-0.048
idges-0.041
 yogurt-0.040
ad-0.040
 honey-0.040
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
gy+0.116
 bank+0.096
 station+0.077
lves+0.076
zag+0.075
Neg logit contributions
 ey-0.093
idges-0.080
 yogurt-0.072
ement-0.072
 importantly-0.072
Token scale
Token ID5046
Feature activation+2.99e+00

Pos logit contributions
 ey+0.011
idges+0.010
ement+0.009
 importantly+0.009
ad+0.009
Neg logit contributions
gy-0.012
 bank-0.010
 station-0.008
lves-0.007
zag-0.007
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
 ey+0.200
 yogurt+0.168
ad+0.165
 honey+0.162
ement+0.161
Neg logit contributions
gy-0.284
 bank-0.227
lves-0.217
 drown-0.198
 drowned-0.191
Token She
Token ID1375
Feature activation+1.57e+00

Pos logit contributions
 ey+0.013
idges+0.012
ad+0.011
ement+0.011
 honey+0.011
Neg logit contributions
gy-0.013
 bank-0.010
 station-0.008
lves-0.008
house-0.008
Token and
Token ID290
Feature activation-2.85e-01

Pos logit contributions
 ey+0.120
idges+0.101
 yogurt+0.099
ad+0.097
 honey+0.096
Neg logit contributions
gy-0.141
 bank-0.114
lves-0.096
zag-0.092
 station-0.091
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
gy+0.029
 bank+0.024
lves+0.020
 station+0.020
 argue+0.020
Neg logit contributions
 ey-0.018
idges-0.015
ement-0.014
ad-0.014
 yogurt-0.013
Token Daddy
Token ID26926
Feature activation+4.99e+00

Pos logit contributions
 ey+0.096
idges+0.086
mmmm+0.084
ad+0.080
ention+0.078
Neg logit contributions
gy-0.079
 bank-0.062
 jet-0.047
 station-0.046
lves-0.045
Token smiled
Token ID13541
Feature activation+6.18e+00

Pos logit contributions
 ey+0.393
idges+0.341
 yogurt+0.340
ad+0.340
 honey+0.331
Neg logit contributions
gy-0.415
 bank-0.330
lves-0.281
 drown-0.264
zag-0.263
Token at
Token ID379
Feature activation-3.21e+00

Pos logit contributions
 ey+0.537
idges+0.460
 yogurt+0.445
ad+0.434
 honey+0.423
Neg logit contributions
gy-0.512
 bank-0.392
lves-0.315
 station-0.311
zag-0.306
Token He
Token ID679
Feature activation+2.93e+00

Pos logit contributions
 ey+0.020
idges+0.019
ement+0.018
 honey+0.017
illy+0.016
Neg logit contributions
gy-0.024
 bank-0.019
 station-0.016
house-0.015
zag-0.015
Token found
Token ID1043
Feature activation-3.09e+00

Pos logit contributions
 ey+0.227
 yogurt+0.192
idges+0.190
ad+0.188
 honey+0.184
Neg logit contributions
gy-0.256
 bank-0.206
lves-0.175
zag-0.165
 drown-0.164
Token a
Token ID257
Feature activation+5.36e-01

Pos logit contributions
gy+0.202
 bank+0.160
lves+0.121
 crashed+0.119
 neither+0.118
Neg logit contributions
 ey-0.291
idges-0.262
ement-0.261
mmmm-0.259
mmm-0.254
Token big
Token ID1263
Feature activation+1.17e+00

Pos logit contributions
 ey+0.040
idges+0.036
ad+0.035
ement+0.034
mmmm+0.032
Neg logit contributions
gy-0.047
 bank-0.039
 station-0.032
lves-0.032
zag-0.032
Token bowl
Token ID9396
Feature activation+3.73e+00

Pos logit contributions
 ey+0.096
idges+0.088
ad+0.082
ement+0.081
 importantly+0.080
Neg logit contributions
gy-0.096
 bank-0.077
 station-0.061
lves-0.059
 fight-0.058
Token on
Token ID319
Feature activation-1.01e+00

Pos logit contributions
 ey+0.244
idges+0.201
 yogurt+0.187
 honey+0.187
ad+0.187
Neg logit contributions
gy-0.378
 bank-0.314
lves-0.263
 station-0.260
zag-0.260
Token the
Token ID262
Feature activation+3.14e-01

Pos logit contributions
gy+0.093
 bank+0.078
lves+0.062
 station+0.061
 argue+0.058
Neg logit contributions
 ey-0.077
idges-0.066
ement-0.062
 importantly-0.062
ad-0.060
Token floor
Token ID4314
Feature activation+7.22e-01

Pos logit contributions
 ey+0.025
idges+0.022
ad+0.020
ement+0.020
 importantly+0.020
Neg logit contributions
gy-0.028
 bank-0.023
 station-0.019
lves-0.018
zag-0.018
Token.
Token ID13
Feature activation+3.02e-01

Pos logit contributions
 ey+0.057
idges+0.048
 yogurt+0.046
 honey+0.046
ad+0.046
Neg logit contributions
gy-0.064
 bank-0.052
lves-0.042
zag-0.041
 station-0.041
Token It
Token ID632
Feature activation+1.41e+00

Pos logit contributions
 ey+0.024
idges+0.023
ement+0.022
illy+0.021
ocol+0.021
Neg logit contributions
gy-0.026
 bank-0.021
 station-0.016
house-0.016
lves-0.015
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
 ey+0.111
idges+0.094
 yogurt+0.089
ad+0.089
ement+0.089
Neg logit contributions
gy-0.127
 bank-0.102
lves-0.083
zag-0.081
 station-0.080
Token saw
Token ID2497
Feature activation-1.16e+00

Pos logit contributions
gy+0.018
 bank+0.014
lves+0.013
 drown+0.012
zag+0.012
Neg logit contributions
 ey-0.019
 yogurt-0.017
ad-0.016
idges-0.016
 honey-0.016
Token a
Token ID257
Feature activation+3.16e-01

Pos logit contributions
gy+0.097
 bank+0.079
 station+0.063
lves+0.063
 neither+0.062
Neg logit contributions
 ey-0.097
idges-0.081
ement-0.079
mmmm-0.075
 importantly-0.075
Token small
Token ID1402
Feature activation+3.00e-01

Pos logit contributions
 ey+0.022
idges+0.019
ad+0.019
ement+0.018
 yogurt+0.017
Neg logit contributions
gy-0.029
 bank-0.025
lves-0.021
 station-0.021
zag-0.020
Token black
Token ID2042
Feature activation+3.11e-01

Pos logit contributions
 ey+0.024
idges+0.020
ad+0.019
 yogurt+0.019
ement+0.019
Neg logit contributions
gy-0.026
 bank-0.021
lves-0.017
 station-0.017
zag-0.016
Token thing
Token ID1517
Feature activation-2.80e+00

Pos logit contributions
 ey+0.026
idges+0.024
 importantly+0.023
ement+0.022
ad+0.021
Neg logit contributions
gy-0.025
 bank-0.020
 station-0.016
zag-0.015
house-0.015
Token on
Token ID319
Feature activation-1.12e+00

Pos logit contributions
gy+0.213
 bank+0.166
zag+0.132
 station+0.131
lves+0.127
Neg logit contributions
 ey-0.247
idges-0.215
ad-0.203
ement-0.202
mmmm-0.200
Token the
Token ID262
Feature activation+5.26e-02

Pos logit contributions
gy+0.112
 bank+0.093
lves+0.080
zag+0.077
 station+0.076
Neg logit contributions
 ey-0.074
idges-0.061
 yogurt-0.059
ad-0.058
 honey-0.057
Token ground
Token ID2323
Feature activation+9.10e-01

Pos logit contributions
 ey+0.004
idges+0.004
ement+0.004
 importantly+0.004
ad+0.004
Neg logit contributions
gy-0.004
 bank-0.004
 station-0.003
lves-0.003
zag-0.003
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
 ey+0.076
idges+0.066
 honey+0.063
 yogurt+0.062
ement+0.061
Neg logit contributions
gy-0.075
 bank-0.061
 station-0.048
zag-0.048
lves-0.045
Token It
Token ID632
Feature activation+1.28e+00

Pos logit contributions
 ey+0.013
idges+0.012
ad+0.011
ement+0.011
 importantly+0.011
Neg logit contributions
gy-0.016
 bank-0.013
house-0.011
lves-0.010
 station-0.010
Token had
Token ID550
Feature activation-9.24e-01

Pos logit contributions
 ey+0.106
idges+0.092
ement+0.088
 yogurt+0.087
 honey+0.086
Neg logit contributions
gy-0.109
 bank-0.085
lves-0.069
zag-0.067
 station-0.066
Token slide
Token ID10649
Feature activation-1.68e+00

Pos logit contributions
 ey+0.046
 yogurt+0.040
ad+0.039
idges+0.039
 honey+0.038
Neg logit contributions
gy-0.040
 bank-0.031
lves-0.027
zag-0.024
 drown-0.023
Token,
Token ID11
Feature activation+5.99e-02

Pos logit contributions
gy+0.175
 bank+0.145
 drown+0.138
lves+0.133
 drowned+0.125
Neg logit contributions
 ey-0.093
 yogurt-0.086
 sweet-0.079
 honey-0.079
ement-0.076
Token swing
Token ID9628
Feature activation-1.53e+00

Pos logit contributions
 ey+0.005
 yogurt+0.004
idges+0.004
 honey+0.004
ad+0.004
Neg logit contributions
gy-0.005
 bank-0.004
lves-0.003
zag-0.003
 drown-0.003
Token and
Token ID290
Feature activation-5.32e-01

Pos logit contributions
gy+0.152
 bank+0.124
lves+0.116
 drown+0.112
 argue+0.105
Neg logit contributions
 ey-0.095
 yogurt-0.080
 honey-0.079
ad-0.078
idges-0.077
Token run
Token ID1057
Feature activation-1.63e+00

Pos logit contributions
gy+0.044
 bank+0.033
lves+0.030
zag+0.028
 station+0.026
Neg logit contributions
 ey-0.044
 yogurt-0.039
 honey-0.037
ad-0.037
idges-0.036
Token on
Token ID319
Feature activation-1.28e+00

Pos logit contributions
gy+0.181
lves+0.146
 bank+0.143
 drown+0.140
 station+0.134
Neg logit contributions
 ey-0.060
 sweet-0.057
 yogurt-0.056
ad-0.055
 himself-0.051
Token the
Token ID262
Feature activation-6.71e-02

Pos logit contributions
gy+0.119
 bank+0.100
lves+0.082
 station+0.080
 argue+0.079
Neg logit contributions
 ey-0.093
idges-0.078
ad-0.074
 yogurt-0.073
ement-0.073
Token grass
Token ID8701
Feature activation+4.15e+00

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
 station+0.004
zag+0.004
Neg logit contributions
 ey-0.005
idges-0.005
 importantly-0.005
ad-0.005
ement-0.005
Token.
Token ID13
Feature activation-8.53e-02

Pos logit contributions
 ey+0.189
 yogurt+0.176
ad+0.170
ummy+0.165
 honey+0.163
Neg logit contributions
gy-0.440
lves-0.372
 bank-0.359
 drown-0.338
 drowned-0.333
Token It
Token ID632
Feature activation+1.19e+00

Pos logit contributions
gy+0.008
 bank+0.007
lves+0.006
zag+0.006
 drown+0.006
Neg logit contributions
 ey-0.005
 yogurt-0.005
 honey-0.004
idges-0.004
ummy-0.004
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
 ey+0.054
 yogurt+0.045
ad+0.044
 honey+0.041
 sweet+0.041
Neg logit contributions
gy-0.132
 bank-0.111
lves-0.105
 drown-0.100
 argue-0.098
Token little
Token ID1310
Feature activation+1.03e+00

Pos logit contributions
 ey+0.013
 yogurt+0.010
idges+0.010
 honey+0.010
ad+0.010
Neg logit contributions
gy-0.020
 bank-0.017
lves-0.015
zag-0.014
 drown-0.014
Token girl
Token ID2576
Feature activation-1.24e+00

Pos logit contributions
 ey+0.075
 yogurt+0.064
 honey+0.064
ummy+0.060
 sweet+0.060
Neg logit contributions
gy-0.095
 bank-0.079
lves-0.066
zag-0.065
 drown-0.064
Token named
Token ID3706
Feature activation-6.66e+00

Pos logit contributions
gy+0.080
 bank+0.068
lves+0.054
 drown+0.052
zag+0.050
Neg logit contributions
 ey-0.115
 yogurt-0.104
ad-0.104
 honey-0.101
 sweet-0.100
Token Lily
Token ID20037
Feature activation-2.07e+00

Pos logit contributions
gy+0.648
 bank+0.547
lves+0.464
zag+0.445
 drown+0.441
Neg logit contributions
 ey-0.449
 yogurt-0.385
 honey-0.378
idges-0.376
ad-0.356
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
gy+0.196
 bank+0.166
lves+0.143
zag+0.136
 drown+0.136
Neg logit contributions
 ey-0.140
ad-0.116
 yogurt-0.115
idges-0.114
 honey-0.111
Token Lily
Token ID20037
Feature activation-2.09e+00

Pos logit contributions
gy+0.002
 bank+0.001
house+0.001
 argue+0.001
 station+0.001
Neg logit contributions
 ey-0.001
idges-0.001
ement-0.001
ad-0.001
ango-0.001
Token loved
Token ID6151
Feature activation+2.36e+00

Pos logit contributions
gy+0.197
 bank+0.164
lves+0.141
 drown+0.134
zag+0.134
Neg logit contributions
 ey-0.146
 yogurt-0.120
idges-0.120
ad-0.118
 honey-0.116
Token to
Token ID284
Feature activation+4.93e-01

Pos logit contributions
 ey+0.221
ement+0.209
idges+0.194
ad+0.188
 importantly+0.183
Neg logit contributions
gy-0.164
 bank-0.132
 fight-0.098
 station-0.097
lves-0.096
Token pick
Token ID2298
Feature activation+8.74e-01

Pos logit contributions
 ey+0.049
ement+0.046
idges+0.044
 importantly+0.043
ummy+0.041
Neg logit contributions
gy-0.033
 bank-0.024
 fight-0.019
 argue-0.018
 station-0.017
Token flowers
Token ID12734
Feature activation+3.26e+00

Pos logit contributions
 ey+0.060
idges+0.050
ad+0.047
ement+0.047
 importantly+0.047
Neg logit contributions
gy-0.084
 bank-0.071
lves-0.061
 station-0.056
zag-0.055
Token in
Token ID287
Feature activation+1.25e+00

Pos logit contributions
 ey+0.226
 yogurt+0.192
idges+0.190
 honey+0.189
ad+0.184
Neg logit contributions
gy-0.311
 bank-0.252
lves-0.220
 drown-0.215
zag-0.210
Token.
Token ID13
Feature activation+3.87e-01

Pos logit contributions
gy+0.068
 bank+0.056
lves+0.053
 drown+0.049
zag+0.047
Neg logit contributions
 ey-0.039
 yogurt-0.035
 honey-0.035
ad-0.034
 goodness-0.033
Token He
Token ID679
Feature activation+3.01e+00

Pos logit contributions
 ey+0.027
idges+0.023
ad+0.022
 yogurt+0.022
ement+0.021
Neg logit contributions
gy-0.037
 bank-0.030
lves-0.026
 station-0.025
zag-0.024
Token will
Token ID481
Feature activation+1.17e+00

Pos logit contributions
 ey+0.229
idges+0.193
 yogurt+0.192
ad+0.189
 honey+0.188
Neg logit contributions
gy-0.267
 bank-0.214
lves-0.183
zag-0.172
 drown-0.170
Token look
Token ID804
Feature activation-2.39e-01

Pos logit contributions
 ey+0.093
idges+0.079
ad+0.078
 yogurt+0.078
 honey+0.077
Neg logit contributions
gy-0.099
 bank-0.079
lves-0.067
zag-0.062
 station-0.062
Token at
Token ID379
Feature activation-3.01e+00

Pos logit contributions
gy+0.019
 bank+0.015
lves+0.013
 station+0.012
 drown+0.011
Neg logit contributions
 ey-0.021
idges-0.017
ad-0.017
 yogurt-0.017
ement-0.017
Token their
Token ID511
Feature activation-5.33e+00

Pos logit contributions
gy+0.279
 bank+0.230
lves+0.194
 station+0.183
 neither+0.179
Neg logit contributions
 ey-0.224
idges-0.182
ement-0.176
ad-0.174
 yogurt-0.171
Token eyes
Token ID2951
Feature activation+8.64e+00

Pos logit contributions
gy+0.468
 bank+0.379
lves+0.316
zag+0.300
 station+0.299
Neg logit contributions
 ey-0.416
idges-0.352
 yogurt-0.344
ad-0.341
 honey-0.335
Token and
Token ID290
Feature activation-1.48e-01

Pos logit contributions
 ey+0.715
idges+0.600
ad+0.578
 yogurt+0.578
 honey+0.564
Neg logit contributions
gy-0.731
 bank-0.589
lves-0.469
zag-0.468
 station-0.467
Token give
Token ID1577
Feature activation-1.32e+00

Pos logit contributions
gy+0.012
 bank+0.010
lves+0.008
 drown+0.008
 station+0.008
Neg logit contributions
 ey-0.012
idges-0.010
 yogurt-0.010
ement-0.010
ad-0.010
Token them
Token ID606
Feature activation-7.38e-01

Pos logit contributions
gy+0.129
 bank+0.108
lves+0.092
 station+0.087
 drown+0.086
Neg logit contributions
 ey-0.091
idges-0.074
 yogurt-0.070
ad-0.070
ement-0.070
Token stickers
Token ID28568
Feature activation+4.19e+00

Pos logit contributions
gy+0.069
 bank+0.057
lves+0.048
 station+0.046
zag+0.046
Neg logit contributions
 ey-0.053
idges-0.044
 yogurt-0.043
ad-0.042
ement-0.042
Token Mom
Token ID11254
Feature activation+4.00e+00

Pos logit contributions
gy+0.035
 bank+0.030
lves+0.026
zag+0.025
 station+0.025
Neg logit contributions
 ey-0.019
idges-0.015
 yogurt-0.015
ad-0.015
 honey-0.015
Tokenmy
Token ID1820
Feature activation+3.19e+00

Pos logit contributions
 ey+0.351
idges+0.288
mmmm+0.278
 yogurt+0.273
 importantly+0.269
Neg logit contributions
gy-0.356
 bank-0.250
 station-0.212
zag-0.211
 argue-0.202
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
 ey+0.276
idges+0.231
 yogurt+0.224
mmmm+0.215
 honey+0.214
Neg logit contributions
gy-0.273
 bank-0.207
zag-0.165
 station-0.162
lves-0.162
Token "
Token ID366
Feature activation+2.22e+00

Pos logit contributions
 ey+0.010
idges+0.008
ad+0.008
ement+0.008
 honey+0.008
Neg logit contributions
gy-0.010
 bank-0.008
 station-0.007
zag-0.007
 neither-0.006
TokenLet
Token ID5756
Feature activation+2.50e+00

Pos logit contributions
 ey+0.148
idges+0.121
 honey+0.119
 yogurt+0.117
ad+0.116
Neg logit contributions
gy-0.213
 bank-0.177
lves-0.160
 drown-0.148
 neither-0.148
Token's
Token ID338
Feature activation-6.04e+00

Pos logit contributions
 ey+0.211
idges+0.189
 honey+0.186
ad+0.185
 yogurt+0.185
Neg logit contributions
gy-0.199
 bank-0.154
lves-0.128
zag-0.124
 station-0.117
Token go
Token ID467
Feature activation+2.55e-01

Pos logit contributions
gy+0.500
 bank+0.400
lves+0.362
zag+0.325
 station+0.311
Neg logit contributions
 ey-0.473
 yogurt-0.411
idges-0.407
ad-0.405
 honey-0.399
Token and
Token ID290
Feature activation-1.08e-01

Pos logit contributions
 ey+0.016
 yogurt+0.015
ad+0.015
 honey+0.014
idges+0.014
Neg logit contributions
gy-0.022
 bank-0.018
lves-0.017
 sank-0.016
 neither-0.016
Token buy
Token ID2822
Feature activation-1.85e+00

Pos logit contributions
gy+0.009
 bank+0.007
lves+0.007
zag+0.006
 sank+0.006
Neg logit contributions
 ey-0.008
 yogurt-0.007
 honey-0.007
idges-0.006
ad-0.006
Token another
Token ID1194
Feature activation-2.29e+00

Pos logit contributions
gy+0.147
 bank+0.126
lves+0.099
 neither+0.094
 station+0.093
Neg logit contributions
 ey-0.161
idges-0.130
ad-0.125
ement-0.125
 importantly-0.124
Token one
Token ID530
Feature activation-9.11e+00

Pos logit contributions
gy+0.215
 bank+0.173
lves+0.152
 drown+0.142
zag+0.142
Neg logit contributions
 ey-0.163
 yogurt-0.138
 honey-0.134
idges-0.133
ad-0.130
TokenL
Token ID43
Feature activation-3.75e+00

Pos logit contributions
 ey+0.015
idges+0.013
ement+0.013
 yogurt+0.013
ad+0.013
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.012
 station-0.011
zag-0.011
Tokenily
Token ID813
Feature activation+2.45e+00

Pos logit contributions
gy+0.369
 bank+0.282
zag+0.267
lves+0.261
 station+0.255
Neg logit contributions
 ey-0.233
idges-0.184
 yogurt-0.179
 importantly-0.179
 creamy-0.177
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
 ey+0.211
idges+0.200
 importantly+0.197
ocol+0.194
mmmm+0.192
Neg logit contributions
gy-0.174
 bank-0.138
 station-0.105
zag-0.104
 argue-0.102
Token Ben
Token ID3932
Feature activation+2.22e+00

Pos logit contributions
gy+0.020
 bank+0.016
 station+0.014
lves+0.013
 argue+0.013
Neg logit contributions
 ey-0.014
idges-0.012
ement-0.012
 importantly-0.011
ad-0.011
Token look
Token ID804
Feature activation-4.16e-01

Pos logit contributions
 ey+0.180
idges+0.165
 importantly+0.164
ummy+0.157
ement+0.155
Neg logit contributions
gy-0.175
 bank-0.150
 argue-0.124
 fight-0.116
 station-0.114
Token at
Token ID379
Feature activation-3.15e+00

Pos logit contributions
gy+0.034
 bank+0.027
lves+0.022
zag+0.021
 station+0.021
Neg logit contributions
 ey-0.035
idges-0.030
 yogurt-0.029
ad-0.029
 honey-0.029
Token each
Token ID1123
Feature activation-2.77e+00

Pos logit contributions
gy+0.281
 bank+0.227
lves+0.190
 station+0.180
zag+0.179
Neg logit contributions
 ey-0.245
idges-0.207
 yogurt-0.203
ad-0.200
 honey-0.198
Token other
Token ID584
Feature activation-1.40e+00

Pos logit contributions
gy+0.278
 bank+0.221
lves+0.198
zag+0.185
 drown+0.184
Neg logit contributions
 ey-0.186
 yogurt-0.161
idges-0.154
 honey-0.154
ad-0.151
Token.
Token ID13
Feature activation+4.27e-01

Pos logit contributions
gy+0.132
 bank+0.107
lves+0.094
zag+0.089
 drown+0.087
Neg logit contributions
 ey-0.099
 yogurt-0.083
idges-0.082
 honey-0.081
ad-0.081
Token They
Token ID1119
Feature activation-3.70e+00

Pos logit contributions
 ey+0.043
idges+0.038
ad+0.037
 yogurt+0.037
 honey+0.036
Neg logit contributions
gy-0.028
 bank-0.021
lves-0.016
 station-0.015
zag-0.014
Token feel
Token ID1254
Feature activation-2.11e+00

Pos logit contributions
gy+0.264
 bank+0.218
 argue+0.175
 fight+0.167
 drown+0.162
Neg logit contributions
 ey-0.322
idges-0.298
ement-0.293
ummy-0.292
 importantly-0.290
Token to
Token ID284
Feature activation+4.62e-01

Pos logit contributions
gy+0.084
 bank+0.066
lves+0.052
zag+0.052
 drown+0.050
Neg logit contributions
 ey-0.089
idges-0.077
 yogurt-0.074
ad-0.074
ement-0.074
Token land
Token ID1956
Feature activation-4.68e+00

Pos logit contributions
 ey+0.042
idges+0.036
 yogurt+0.035
ad+0.035
 honey+0.035
Neg logit contributions
gy-0.035
 bank-0.027
lves-0.022
zag-0.021
 station-0.020
Token but
Token ID475
Feature activation-1.56e+00

Pos logit contributions
gy+0.380
 bank+0.295
zag+0.235
 neither+0.228
lves+0.223
Neg logit contributions
 ey-0.407
idges-0.349
 importantly-0.335
 yogurt-0.335
ummy-0.327
Token he
Token ID339
Feature activation+8.60e-01

Pos logit contributions
gy+0.169
 bank+0.142
lves+0.127
 station+0.121
zag+0.120
Neg logit contributions
 ey-0.086
 yogurt-0.069
 honey-0.067
idges-0.067
ad-0.066
Token couldn
Token ID3521
Feature activation-2.55e-02

Pos logit contributions
 ey+0.064
ad+0.055
idges+0.055
 yogurt+0.055
 honey+0.054
Neg logit contributions
gy-0.075
 bank-0.061
lves-0.052
 station-0.050
 argue-0.048
Token't
Token ID470
Feature activation-4.66e+00

Pos logit contributions
gy+0.002
 bank+0.002
lves+0.001
 station+0.001
zag+0.001
Neg logit contributions
 ey-0.002
idges-0.002
ad-0.002
 yogurt-0.002
ement-0.002
Token reach
Token ID3151
Feature activation-4.89e-01

Pos logit contributions
gy+0.397
 bank+0.317
lves+0.279
 station+0.258
zag+0.249
Neg logit contributions
 ey-0.355
ad-0.324
idges-0.303
 honey-0.303
 yogurt-0.299
Token it
Token ID340
Feature activation-8.46e-02

Pos logit contributions
gy+0.045
 bank+0.037
lves+0.031
 drown+0.030
zag+0.030
Neg logit contributions
 ey-0.037
idges-0.030
 yogurt-0.029
ad-0.029
ement-0.028
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
gy+0.008
 bank+0.007
lves+0.006
 station+0.005
 drown+0.005
Neg logit contributions
 ey-0.006
ad-0.005
 yogurt-0.005
 honey-0.005
idges-0.005
Token He
Token ID679
Feature activation+2.76e+00

Pos logit contributions
 ey+0.008
idges+0.006
 yogurt+0.006
ad+0.006
 honey+0.006
Neg logit contributions
gy-0.018
 bank-0.016
lves-0.014
zag-0.013
 station-0.013
Token got
Token ID1392
Feature activation-5.27e+00

Pos logit contributions
 ey+0.194
ad+0.173
 honey+0.169
 yogurt+0.165
idges+0.161
Neg logit contributions
gy-0.245
 bank-0.192
lves-0.171
 station-0.167
 drown-0.165
Token horse
Token ID8223
Feature activation-4.56e+00

Pos logit contributions
gy+0.017
 bank+0.013
lves+0.011
 station+0.010
zag+0.010
Neg logit contributions
 ey-0.019
idges-0.016
ad-0.016
 yogurt-0.016
ement-0.015
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
gy+0.476
lves+0.408
 bank+0.393
ene+0.356
zag+0.355
Neg logit contributions
 honey-0.192
 yogurt-0.186
 sweet-0.174
 ey-0.171
ad-0.164
Token She
Token ID1375
Feature activation+1.58e+00

Pos logit contributions
 ey+0.015
idges+0.014
 yogurt+0.012
ad+0.012
ement+0.012
Neg logit contributions
gy-0.022
 bank-0.018
lves-0.015
 neither-0.015
 station-0.015
Token did
Token ID750
Feature activation+2.89e+00

Pos logit contributions
 ey+0.122
 yogurt+0.103
idges+0.102
ad+0.102
 honey+0.101
Neg logit contributions
gy-0.139
 bank-0.110
lves-0.094
zag-0.091
 drown-0.089
Token not
Token ID407
Feature activation-3.01e+00

Pos logit contributions
 ey+0.192
 yogurt+0.170
idges+0.169
 honey+0.168
 sweet+0.167
Neg logit contributions
gy-0.276
 bank-0.228
lves-0.200
 station-0.189
zag-0.178
Token want
Token ID765
Feature activation-3.10e+00

Pos logit contributions
gy+0.265
 bank+0.217
lves+0.188
zag+0.174
 station+0.171
Neg logit contributions
 ey-0.228
ad-0.200
 yogurt-0.194
 honey-0.194
idges-0.193
Token to
Token ID284
Feature activation+5.60e-01

Pos logit contributions
gy+0.237
 bank+0.190
 drown+0.145
 station+0.144
lves+0.144
Neg logit contributions
 ey-0.279
idges-0.237
ement-0.233
ad-0.223
 importantly-0.223
Token be
Token ID307
Feature activation+2.54e-01

Pos logit contributions
 ey+0.042
ad+0.039
 yogurt+0.037
 honey+0.036
idges+0.036
Neg logit contributions
gy-0.047
 bank-0.037
lves-0.035
zag-0.031
 station-0.030
Token punished
Token ID16851
Feature activation-4.17e+00

Pos logit contributions
 ey+0.016
 sweet+0.016
 honey+0.015
 yogurt+0.015
ad+0.015
Neg logit contributions
gy-0.023
 bank-0.019
lves-0.016
zag-0.016
 station-0.016
Token.
Token ID13
Feature activation+1.26e-01

Pos logit contributions
gy+0.383
 bank+0.312
lves+0.266
zag+0.252
 station+0.249
Neg logit contributions
 ey-0.308
idges-0.258
 yogurt-0.255
ad-0.252
 honey-0.249
Token She
Token ID1375
Feature activation+1.53e+00

Pos logit contributions
 ey+0.009
idges+0.008
ad+0.007
 yogurt+0.007
ement+0.007
Neg logit contributions
gy-0.012
 bank-0.010
lves-0.008
 neither-0.008
 drown-0.008
Token that
Token ID326
Feature activation-1.21e+00

Pos logit contributions
gy+0.076
 bank+0.064
 neither+0.053
 crashed+0.052
 station+0.052
Neg logit contributions
 ey-0.076
idges-0.060
ad-0.058
ement-0.057
ango-0.056
Token the
Token ID262
Feature activation-1.86e-01

Pos logit contributions
gy+0.106
 bank+0.089
 station+0.072
lves+0.072
 neither+0.071
Neg logit contributions
 ey-0.091
idges-0.076
ement-0.074
ad-0.072
ummy-0.070
Token people
Token ID661
Feature activation+5.81e-01

Pos logit contributions
gy+0.012
 bank+0.008
lves+0.007
zag+0.006
 drown+0.006
Neg logit contributions
 ey-0.019
ement-0.017
ad-0.017
idges-0.016
 sweet-0.016
Token in
Token ID287
Feature activation+1.13e+00

Pos logit contributions
 ey+0.047
idges+0.040
 yogurt+0.039
ad+0.039
 honey+0.038
Neg logit contributions
gy-0.049
 bank-0.039
lves-0.033
zag-0.031
 station-0.030
Token the
Token ID262
Feature activation-1.90e-01

Pos logit contributions
 ey+0.080
idges+0.067
 yogurt+0.065
ad+0.064
 honey+0.063
Neg logit contributions
gy-0.107
 bank-0.088
lves-0.075
 station-0.071
zag-0.071
Token jet
Token ID12644
Feature activation-1.13e+01

Pos logit contributions
gy+0.019
 bank+0.015
lves+0.013
zag+0.013
 drown+0.013
Neg logit contributions
 ey-0.013
 yogurt-0.010
ad-0.010
idges-0.010
 honey-0.010
Token must
Token ID1276
Feature activation-6.35e-01

Pos logit contributions
gy+0.975
 bank+0.775
lves+0.691
 drown+0.635
zag+0.623
Neg logit contributions
 ey-0.841
idges-0.725
ad-0.725
 yogurt-0.716
 honey-0.711
Token feel
Token ID1254
Feature activation-2.29e+00

Pos logit contributions
gy+0.051
 bank+0.040
lves+0.033
zag+0.031
 station+0.030
Neg logit contributions
 ey-0.054
idges-0.047
 yogurt-0.046
ad-0.046
 honey-0.045
Token proud
Token ID6613
Feature activation+6.82e-01

Pos logit contributions
gy+0.177
 bank+0.150
lves+0.119
 drown+0.119
 neither+0.113
Neg logit contributions
 ey-0.198
idges-0.169
ad-0.163
ango-0.161
ement-0.159
Token too
Token ID1165
Feature activation-1.05e+00

Pos logit contributions
 ey+0.062
idges+0.051
mmmm+0.049
ango+0.049
ad+0.048
Neg logit contributions
gy-0.046
 bank-0.038
 neither-0.032
 station-0.031
 fight-0.029
Token because
Token ID780
Feature activation-6.68e+00

Pos logit contributions
gy+0.095
 bank+0.077
lves+0.065
zag+0.062
 station+0.061
Neg logit contributions
 ey-0.079
idges-0.066
 yogurt-0.065
ad-0.064
 honey-0.063
Token rabbit
Token ID22746
Feature activation-2.15e+00

Pos logit contributions
 ey+0.007
 yogurt+0.006
idges+0.006
ad+0.005
 honey+0.005
Neg logit contributions
gy-0.007
 bank-0.005
lves-0.004
zag-0.004
 drown-0.004
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
gy+0.199
 bank+0.163
lves+0.141
 station+0.133
zag+0.133
Neg logit contributions
 ey-0.153
idges-0.128
 yogurt-0.127
ad-0.126
 honey-0.125
Token The
Token ID383
Feature activation-2.56e+00

Pos logit contributions
 ey+0.006
 yogurt+0.005
ad+0.005
idges+0.005
 honey+0.005
Neg logit contributions
gy-0.010
 bank-0.009
lves-0.008
zag-0.007
 drown-0.007
Token rh
Token ID9529
Feature activation-6.23e+00

Pos logit contributions
gy+0.215
 bank+0.169
lves+0.142
zag+0.137
 drown+0.134
Neg logit contributions
 ey-0.209
 yogurt-0.176
idges-0.175
 honey-0.174
ad-0.174
Tokenin
Token ID259
Feature activation+2.43e+00

Pos logit contributions
gy+0.720
 bank+0.613
lves+0.544
zag+0.524
 station+0.520
Neg logit contributions
 ey-0.315
idges-0.238
 yogurt-0.232
ad-0.225
 honey-0.223
Tokenoc
Token ID420
Feature activation-1.08e+01

Pos logit contributions
 ey+0.231
ad+0.206
idges+0.203
 honey+0.201
 yogurt+0.200
Neg logit contributions
gy-0.154
 bank-0.118
lves-0.095
 drown-0.094
 argue-0.087
Tokeneros
Token ID27498
Feature activation-2.50e+00

Pos logit contributions
gy+0.932
 bank+0.736
lves+0.597
zag+0.554
 station+0.532
Neg logit contributions
 ey-0.900
idges-0.768
 yogurt-0.763
 importantly-0.747
 honey-0.737
Token explained
Token ID4893
Feature activation-1.81e+00

Pos logit contributions
gy+0.242
 bank+0.199
lves+0.173
 drown+0.164
zag+0.164
Neg logit contributions
 ey-0.168
idges-0.140
 yogurt-0.138
ad-0.137
 honey-0.134
Token his
Token ID465
Feature activation+1.08e+00

Pos logit contributions
gy+0.152
 bank+0.123
lves+0.097
 neither+0.096
 argue+0.094
Neg logit contributions
 ey-0.152
idges-0.124
 yogurt-0.120
 importantly-0.117
ement-0.116
Token problem
Token ID1917
Feature activation-4.69e+00

Pos logit contributions
 ey+0.078
idges+0.067
 yogurt+0.063
ad+0.062
ement+0.061
Neg logit contributions
gy-0.103
 bank-0.085
zag-0.069
lves-0.069
 drown-0.067
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
gy+0.408
 bank+0.326
zag+0.268
 station+0.257
 neither+0.254
Neg logit contributions
 ey-0.377
idges-0.311
 yogurt-0.300
ement-0.297
 honey-0.296
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
 ey+0.012
idges+0.010
ement+0.010
 yogurt+0.010
 honey+0.010
Neg logit contributions
gy-0.013
 bank-0.011
lves-0.009
zag-0.009
 drown-0.008
TokenShe
Token ID3347
Feature activation+2.97e+00

Pos logit contributions
 ey+0.009
idges+0.007
 yogurt+0.007
ad+0.007
 honey+0.006
Neg logit contributions
gy-0.018
 bank-0.015
lves-0.013
zag-0.013
 station-0.013
Token pushed
Token ID7121
Feature activation-2.25e+00

Pos logit contributions
 ey+0.205
 yogurt+0.183
ad+0.177
 honey+0.167
idges+0.166
Neg logit contributions
gy-0.275
 bank-0.210
lves-0.195
 drown-0.189
zag-0.179
Token the
Token ID262
Feature activation-2.56e-01

Pos logit contributions
gy+0.228
 bank+0.189
lves+0.163
zag+0.156
 station+0.155
Neg logit contributions
 ey-0.148
idges-0.121
 yogurt-0.119
ad-0.117
 honey-0.116
Token red
Token ID2266
Feature activation+1.04e+00

Pos logit contributions
gy+0.020
 bank+0.014
lves+0.013
 drown+0.012
 drowned+0.011
Neg logit contributions
 ey-0.023
 honey-0.019
 sweet-0.019
 yogurt-0.019
ad-0.019
Token train
Token ID4512
Feature activation-9.83e+00

Pos logit contributions
 ey+0.099
ad+0.089
 yogurt+0.086
 honey+0.085
idges+0.083
Neg logit contributions
gy-0.068
 bank-0.047
lves-0.046
 drown-0.044
 drowned-0.041
Token and
Token ID290
Feature activation-2.41e-01

Pos logit contributions
gy+0.920
lves+0.756
 bank+0.701
 drown+0.664
 drowned+0.654
Neg logit contributions
 ey-0.576
ad-0.528
 honey-0.516
 sweet-0.494
 yogurt-0.488
Token made
Token ID925
Feature activation-1.41e+00

Pos logit contributions
gy+0.023
 bank+0.018
lves+0.016
zag+0.015
 drown+0.015
Neg logit contributions
 ey-0.017
 yogurt-0.015
 honey-0.015
 sweet-0.014
ad-0.014
Token it
Token ID340
Feature activation-9.78e-03

Pos logit contributions
gy+0.127
 bank+0.105
lves+0.087
 station+0.084
 drown+0.083
Neg logit contributions
 ey-0.107
idges-0.089
ement-0.085
 yogurt-0.084
ummy-0.083
Token go
Token ID467
Feature activation+1.81e-01

Pos logit contributions
gy+0.001
 bank+0.001
lves+0.001
 station+0.001
 drowned+0.001
Neg logit contributions
 ey-0.001
 honey-0.001
 yogurt-0.001
ad-0.001
 sweet-0.001
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
 sweet+0.008
ad+0.008
 ey+0.007
 himself+0.007
 honey+0.007
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.014
 drown-0.013
 drowned-0.012
Token and
Token ID290
Feature activation-3.72e-01

Pos logit contributions
gy+0.134
 bank+0.106
lves+0.087
 station+0.082
zag+0.082
Neg logit contributions
 ey-0.129
idges-0.110
 yogurt-0.106
ad-0.104
ement-0.102
Token bark
Token ID21405
Feature activation-3.29e+00

Pos logit contributions
gy+0.034
 bank+0.028
lves+0.025
 station+0.023
zag+0.023
Neg logit contributions
 ey-0.026
 honey-0.022
 yogurt-0.022
ad-0.021
idges-0.021
Tokened
Token ID276
Feature activation-1.68e+00

Pos logit contributions
gy+0.301
 bank+0.247
lves+0.213
 station+0.203
 drown+0.202
Neg logit contributions
 ey-0.227
idges-0.196
ad-0.195
 yogurt-0.193
 honey-0.192
Token,
Token ID11
Feature activation+3.54e-01

Pos logit contributions
gy+0.145
 bank+0.116
lves+0.095
zag+0.090
 station+0.089
Neg logit contributions
 ey-0.138
idges-0.116
 yogurt-0.113
ad-0.112
ement-0.109
Token but
Token ID475
Feature activation-1.50e+00

Pos logit contributions
 ey+0.026
idges+0.022
 yogurt+0.022
ad+0.021
ement+0.021
Neg logit contributions
gy-0.033
 bank-0.027
lves-0.022
zag-0.021
 station-0.021
Token Wh
Token ID854
Feature activation-9.62e+00

Pos logit contributions
gy+0.151
 bank+0.128
lves+0.112
zag+0.106
 drown+0.105
Neg logit contributions
 ey-0.091
 yogurt-0.078
 honey-0.077
idges-0.076
ad-0.074
Tokenisk
Token ID1984
Feature activation-8.01e+00

Pos logit contributions
gy+0.601
 bank+0.406
lves+0.300
zag+0.287
 station+0.270
Neg logit contributions
 ey-1.032
 yogurt-0.906
idges-0.905
 honey-0.887
ad-0.877
Tokeners
Token ID364
Feature activation+3.63e+00

Pos logit contributions
gy+0.855
 bank+0.689
zag+0.607
lves+0.601
 station+0.567
Neg logit contributions
 ey-0.528
 yogurt-0.404
ummy-0.390
 importantly-0.384
idges-0.383
Token did
Token ID750
Feature activation+2.93e+00

Pos logit contributions
 ey+0.234
ad+0.212
idges+0.206
 yogurt+0.206
 honey+0.198
Neg logit contributions
gy-0.334
 bank-0.258
lves-0.241
 drown-0.223
zag-0.223
Token not
Token ID407
Feature activation-3.07e+00

Pos logit contributions
 ey+0.243
idges+0.213
 yogurt+0.210
ad+0.208
 honey+0.206
Neg logit contributions
gy-0.239
 bank-0.189
lves-0.160
 station-0.147
zag-0.145
Token care
Token ID1337
Feature activation-1.20e+00

Pos logit contributions
gy+0.278
 bank+0.227
lves+0.194
zag+0.181
 station+0.180
Neg logit contributions
 ey-0.227
idges-0.194
ad-0.193
 yogurt-0.192
 honey-0.192
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
gy+0.014
 bank+0.011
lves+0.010
zag+0.009
 station+0.009
Neg logit contributions
 ey-0.012
idges-0.010
 yogurt-0.010
ad-0.010
 honey-0.009
Token she
Token ID673
Feature activation-4.98e-01

Pos logit contributions
 ey+0.012
idges+0.010
 yogurt+0.009
ad+0.009
ement+0.009
Neg logit contributions
gy-0.014
 bank-0.012
lves-0.010
 station-0.010
 neither-0.009
Token was
Token ID373
Feature activation+1.00e+00

Pos logit contributions
gy+0.040
 bank+0.032
lves+0.026
zag+0.025
 station+0.024
Neg logit contributions
 ey-0.043
idges-0.036
 yogurt-0.036
ad-0.035
 honey-0.035
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
 ey+0.083
idges+0.070
 yogurt+0.067
ad+0.067
ement+0.066
Neg logit contributions
gy-0.085
 bank-0.067
lves-0.055
zag-0.053
 drown-0.053
Token only
Token ID691
Feature activation-2.65e+00

Pos logit contributions
 ey+0.002
idges+0.002
 yogurt+0.002
ad+0.002
 honey+0.002
Neg logit contributions
gy-0.002
 bank-0.002
lves-0.001
 station-0.001
zag-0.001
Token one
Token ID530
Feature activation-9.32e+00

Pos logit contributions
gy+0.208
 bank+0.162
lves+0.131
zag+0.125
 station+0.124
Neg logit contributions
 ey-0.232
idges-0.201
 yogurt-0.196
ad-0.194
 honey-0.191
Token rocking
Token ID38059
Feature activation+5.66e+00

Pos logit contributions
gy+0.814
 bank+0.666
lves+0.555
 station+0.543
zag+0.541
Neg logit contributions
 ey-0.732
idges-0.606
ad-0.585
 yogurt-0.578
 honey-0.566
Token.
Token ID13
Feature activation+9.29e-02

Pos logit contributions
 ey+0.457
idges+0.388
 yogurt+0.384
ad+0.379
 honey+0.374
Neg logit contributions
gy-0.479
 bank-0.382
lves-0.321
zag-0.299
 drown-0.297
Token Everyone
Token ID11075
Feature activation-5.53e-01

Pos logit contributions
 ey+0.007
idges+0.006
 honey+0.006
 yogurt+0.006
ad+0.006
Neg logit contributions
gy-0.008
 bank-0.006
lves-0.005
 station-0.005
zag-0.005
Token around
Token ID1088
Feature activation-2.44e+00

Pos logit contributions
gy+0.047
 bank+0.039
lves+0.032
 station+0.031
zag+0.030
Neg logit contributions
 ey-0.044
idges-0.037
 yogurt-0.036
 honey-0.036
ad-0.035
Token her
Token ID607
Feature activation+1.04e+00

Pos logit contributions
gy+0.218
 bank+0.177
lves+0.148
 station+0.141
zag+0.141
Neg logit contributions
 ey-0.186
idges-0.157
 yogurt-0.153
ad-0.150
 honey-0.149