TOP ACTIVATIONS
MAX = 11.203

" Sorry , honey , we can 't .
, " What 's wrong honey ?" Ana replied , "
and said , " No honey , you can 't catch
ing ? Are you tired honey ?" she said , smiling
the jar and have some honey ," he said to Lily
" Don 't worry , honey ! I 'm going to
" Sure , honey , but be careful .
be eh ive full of honey ! He was so happy
m sorry , honey . I â
. He does not like honey . But he listens to
with me , I love honey too !" But the bird
a little bit sick , honey . But don 't worry
jar . The bear loved honey , so he decided to
It 's an earthquake , honey . It 's when the
and Red went on a honey moon . They sw am
he picked some of the honey to eat . He had
woods . It smelled the honey . It saw the broken
are no more seats , honey . The theater is full
for dinner . She liked honey so much that she did
hive . They made sweet honey . They worked hard every

MIN ACTIVATIONS
MIN = -16.044

T ig gy was so happy and the
day , a little pig gy named Pe ppa went for
that day on , Mag gy was never fearful of boards
together all day . Bug gy learned that being loyal is
body and a w ag gy tail . One day ,
was happy to see Bug gy and they played together all
what was wrong . Bug gy told them about the cart
Tim my had a pig gy bank that was full of
hurt her knee . Dog gy helped Kitty stand up and
After a while , Bug gy was tired and wanted to
Rob pulled out his pig gy bank and emptied it on
and Ben get their pig gy bank and put it in
some money from their pig gy bank . They asked their
One day , the pig gy decided to take a stroll
the raced the s og gy race car around the bowl
and get warm ." Dog gy agreed , and they both
. " Dog gy , you are a bad
her penny in the pig gy bank ever again . She
, a dog named Dog gy , came to play with
met a dog named Dog gy . Dog gy was very

INTERVAL 4.391 - 11.203
CONTAINS 3.471%

She says to the ice cream man , " Can I
little girl said , " Ok ! I 'll put the
smiled and said , " Would you like to share some
that her mom always knew what was best for her .
nap now ." John and the little squirrel stayed

INTERVAL -2.421 - 4.391
CONTAINS 83.033%

, it 's so big and strong !" Ben said ,
and hugged them . " We can learn to be modest
the ground . He saw the scissors and the hat .
can make another car with another box . And you can
is happy . She thinks the lizard is fine . She

INTERVAL -9.232 - -2.421
CONTAINS 13.348%

was always playing . One day he was playing outside when
kind and helpful and not gr umpy . <|endoftext|> S ara
and a bit scary . But the kitten was brave ,
One day , Tim my 's little sister , Sally ,
play room . So one day , Lily asked her grand

INTERVAL -16.044 - -9.232
CONTAINS 0.147%

fastest pig , the smallest one , won the race .
stay with me . The bank is not a safe place
the toes were pink and one of them was black .
so you can manage it one day ." Lisa
there were two stickers , one for Ben and one for
Token
Token ID198
Feature activation+2.30e-01

Pos logit contributions
 ey+0.041
ad+0.037
idges+0.034
odic+0.034
ement+0.032
Neg logit contributions
gy-0.046
 bank-0.038
 neither-0.037
 station-0.035
 drown-0.033
Token
Token ID198
Feature activation+5.00e-01

Pos logit contributions
 ey+0.014
 yogurt+0.012
 honey+0.012
idges+0.011
ad+0.011
Neg logit contributions
gy-0.024
 bank-0.019
lves-0.017
zag-0.017
 station-0.016
Token"
Token ID1
Feature activation-7.62e-01

Pos logit contributions
 ey+0.030
 yogurt+0.024
ad+0.024
idges+0.024
 honey+0.024
Neg logit contributions
gy-0.053
 bank-0.044
lves-0.039
zag-0.038
 drown-0.037
TokenSorry
Token ID14385
Feature activation+2.57e+00

Pos logit contributions
gy+0.081
 bank+0.068
lves+0.061
zag+0.060
 station+0.058
Neg logit contributions
 ey-0.045
 honey-0.035
 yogurt-0.035
idges-0.035
ad-0.035
Token,
Token ID11
Feature activation+7.05e-01

Pos logit contributions
 ey+0.238
idges+0.193
ad+0.190
ement+0.186
 yogurt+0.185
Neg logit contributions
gy-0.198
 bank-0.146
 neither-0.119
 station-0.118
zag-0.116
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.046
idges+0.038
ad+0.037
 yogurt+0.037
 honey+0.036
Neg logit contributions
gy-0.070
 bank-0.058
lves-0.051
zag-0.050
 station-0.049
Token,
Token ID11
Feature activation+5.83e-01

Pos logit contributions
 ey+0.751
 honey+0.664
 yogurt+0.651
ad+0.631
idges+0.625
Neg logit contributions
gy-1.023
 bank-0.847
lves-0.768
zag-0.719
 drown-0.689
Token we
Token ID356
Feature activation-4.02e+00

Pos logit contributions
 ey+0.029
ad+0.024
idges+0.023
ement+0.022
ango+0.021
Neg logit contributions
gy-0.064
 bank-0.055
 drown-0.049
 neither-0.048
 station-0.048
Token can
Token ID460
Feature activation+3.50e+00

Pos logit contributions
gy+0.372
 bank+0.300
lves+0.268
zag+0.263
 station+0.247
Neg logit contributions
 ey-0.287
 yogurt-0.251
 honey-0.249
ad-0.243
idges-0.242
Token't
Token ID470
Feature activation-4.49e+00

Pos logit contributions
 ey+0.267
 yogurt+0.234
 honey+0.232
ad+0.230
idges+0.228
Neg logit contributions
gy-0.301
 bank-0.241
lves-0.219
zag-0.204
 station-0.195
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
gy+0.418
 bank+0.338
lves+0.302
zag+0.292
 station+0.278
Neg logit contributions
 ey-0.319
 yogurt-0.275
 honey-0.273
ad-0.269
idges-0.267
Token,
Token ID11
Feature activation+5.27e-01

Pos logit contributions
 ey+0.026
idges+0.022
ad+0.021
 yogurt+0.020
 honey+0.020
Neg logit contributions
gy-0.041
 bank-0.033
zag-0.029
 station-0.029
lves-0.028
Token "
Token ID366
Feature activation+2.52e+00

Pos logit contributions
 ey+0.038
idges+0.032
ad+0.032
 yogurt+0.031
 honey+0.030
Neg logit contributions
gy-0.049
 bank-0.040
lves-0.034
zag-0.034
 station-0.033
TokenWhat
Token ID2061
Feature activation+7.18e+00

Pos logit contributions
 ey+0.148
 yogurt+0.118
 honey+0.118
idges+0.116
ad+0.115
Neg logit contributions
gy-0.268
 bank-0.224
lves-0.201
zag-0.197
 station-0.190
Token's
Token ID338
Feature activation-5.92e+00

Pos logit contributions
 ey+0.603
ad+0.505
idges+0.504
 honey+0.491
 yogurt+0.488
Neg logit contributions
gy-0.583
 bank-0.458
zag-0.384
lves-0.372
 neither-0.371
Token wrong
Token ID2642
Feature activation-4.10e-01

Pos logit contributions
gy+0.538
 bank+0.434
lves+0.376
zag+0.367
 station+0.353
Neg logit contributions
 ey-0.447
idges-0.370
 yogurt-0.370
ad-0.369
 honey-0.366
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
gy+0.041
 bank+0.033
zag+0.029
lves+0.029
 station+0.028
Neg logit contributions
 ey-0.028
idges-0.022
 yogurt-0.022
ad-0.022
 honey-0.022
Token?"
Token ID1701
Feature activation+9.16e-01

Pos logit contributions
 ey+0.699
 yogurt+0.565
ad+0.557
 honey+0.557
idges+0.557
Neg logit contributions
gy-1.122
 bank-0.926
lves-0.816
zag-0.812
 station-0.778
Token Ana
Token ID17639
Feature activation+1.08e+00

Pos logit contributions
 ey+0.061
idges+0.050
 yogurt+0.049
 honey+0.049
ad+0.048
Neg logit contributions
gy-0.091
 bank-0.074
lves-0.065
zag-0.064
 station-0.062
Token replied
Token ID8712
Feature activation+1.43e+00

Pos logit contributions
 ey+0.081
 yogurt+0.069
idges+0.068
 honey+0.068
ad+0.066
Neg logit contributions
gy-0.096
 bank-0.078
lves-0.066
zag-0.065
 station-0.063
Token,
Token ID11
Feature activation+4.72e-01

Pos logit contributions
 ey+0.131
idges+0.108
 yogurt+0.106
ad+0.106
 honey+0.103
Neg logit contributions
gy-0.114
 bank-0.084
zag-0.070
 neither-0.069
lves-0.066
Token "
Token ID366
Feature activation+2.17e+00

Pos logit contributions
 ey+0.032
idges+0.025
 yogurt+0.025
ad+0.025
 honey+0.025
Neg logit contributions
gy-0.048
 bank-0.039
zag-0.034
lves-0.033
 station-0.033
Token and
Token ID290
Feature activation-1.48e-01

Pos logit contributions
gy+0.073
 bank+0.059
lves+0.054
 drown+0.051
zag+0.050
Neg logit contributions
 ey-0.051
 yogurt-0.048
ad-0.046
 honey-0.045
 sweet-0.043
Token said
Token ID531
Feature activation+1.80e-01

Pos logit contributions
gy+0.013
 bank+0.011
lves+0.009
zag+0.009
 station+0.009
Neg logit contributions
 ey-0.011
idges-0.009
 yogurt-0.009
ad-0.009
 honey-0.009
Token,
Token ID11
Feature activation+8.29e-01

Pos logit contributions
 ey+0.015
idges+0.012
 yogurt+0.012
ad+0.012
 honey+0.012
Neg logit contributions
gy-0.015
 bank-0.012
zag-0.010
lves-0.010
 neither-0.010
Token "
Token ID366
Feature activation+2.50e+00

Pos logit contributions
 ey+0.053
idges+0.043
ad+0.042
 yogurt+0.042
 honey+0.040
Neg logit contributions
gy-0.085
 bank-0.070
zag-0.061
lves-0.060
 station-0.060
TokenNo
Token ID2949
Feature activation+4.42e-02

Pos logit contributions
 ey+0.158
 honey+0.129
 yogurt+0.125
idges+0.124
ad+0.117
Neg logit contributions
gy-0.256
 bank-0.212
lves-0.192
zag-0.187
 station-0.180
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.004
 yogurt+0.003
idges+0.003
ad+0.003
 honey+0.003
Neg logit contributions
gy-0.004
 bank-0.003
zag-0.003
lves-0.003
 drown-0.002
Token,
Token ID11
Feature activation+5.83e-01

Pos logit contributions
 ey+0.742
 honey+0.655
 yogurt+0.647
ad+0.629
idges+0.625
Neg logit contributions
gy-1.019
 bank-0.851
lves-0.762
zag-0.711
 drown-0.692
Token you
Token ID345
Feature activation+2.83e+00

Pos logit contributions
 ey+0.040
ad+0.032
idges+0.032
 yogurt+0.030
ement+0.030
Neg logit contributions
gy-0.056
 bank-0.046
lves-0.040
 neither-0.039
 drown-0.039
Token can
Token ID460
Feature activation+3.50e+00

Pos logit contributions
 ey+0.161
 honey+0.161
 sweet+0.157
 yogurt+0.153
idges+0.146
Neg logit contributions
gy-0.280
 bank-0.228
lves-0.210
zag-0.196
 station-0.190
Token't
Token ID470
Feature activation-4.49e+00

Pos logit contributions
 ey+0.270
 yogurt+0.242
ad+0.242
 honey+0.237
idges+0.234
Neg logit contributions
gy-0.293
 bank-0.232
lves-0.213
zag-0.192
 station-0.188
Token catch
Token ID4929
Feature activation-3.25e+00

Pos logit contributions
gy+0.419
 bank+0.339
lves+0.325
zag+0.297
 station+0.293
Neg logit contributions
 ey-0.279
ad-0.266
 yogurt-0.264
 honey-0.260
idges-0.247
Tokening
Token ID278
Feature activation+2.07e+00

Pos logit contributions
gy+0.041
 bank+0.034
lves+0.030
zag+0.030
 station+0.028
Neg logit contributions
 ey-0.025
 yogurt-0.020
idges-0.019
 honey-0.019
ad-0.019
Token?
Token ID30
Feature activation+2.43e+00

Pos logit contributions
 ey+0.162
 yogurt+0.139
 honey+0.138
ad+0.137
idges+0.136
Neg logit contributions
gy-0.178
 bank-0.141
lves-0.123
zag-0.120
 drown-0.113
Token Are
Token ID4231
Feature activation+4.05e+00

Pos logit contributions
 ey+0.166
 yogurt+0.137
 honey+0.137
idges+0.135
ad+0.134
Neg logit contributions
gy-0.236
 bank-0.193
lves-0.169
zag-0.166
 station-0.160
Token you
Token ID345
Feature activation+3.07e+00

Pos logit contributions
 ey+0.248
 honey+0.191
idges+0.187
ad+0.187
 yogurt+0.187
Neg logit contributions
gy-0.422
 bank-0.348
lves-0.311
zag-0.309
 neither-0.305
Token tired
Token ID10032
Feature activation-3.33e+00

Pos logit contributions
 ey+0.231
 yogurt+0.197
 honey+0.196
ad+0.194
idges+0.193
Neg logit contributions
gy-0.274
 bank-0.221
lves-0.192
zag-0.188
 station-0.179
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
gy+0.333
 bank+0.275
zag+0.242
 drown+0.233
lves+0.233
Neg logit contributions
 ey-0.219
idges-0.176
 yogurt-0.172
 honey-0.172
ad-0.170
Token?"
Token ID1701
Feature activation+9.16e-01

Pos logit contributions
 ey+0.702
 yogurt+0.571
 honey+0.564
idges+0.561
ad+0.560
Neg logit contributions
gy-1.115
 bank-0.921
lves-0.813
zag-0.806
 station-0.770
Token she
Token ID673
Feature activation-9.72e-02

Pos logit contributions
 ey+0.066
idges+0.055
 honey+0.053
 yogurt+0.052
ad+0.051
Neg logit contributions
gy-0.085
 bank-0.070
lves-0.059
 neither-0.057
zag-0.057
Token said
Token ID531
Feature activation-1.28e-01

Pos logit contributions
gy+0.006
 bank+0.005
 argue+0.004
 station+0.004
zag+0.004
Neg logit contributions
 ey-0.009
idges-0.008
mmmm-0.008
 yogurt-0.008
ad-0.008
Token,
Token ID11
Feature activation+4.72e-01

Pos logit contributions
gy+0.010
 bank+0.008
zag+0.006
 neither+0.006
 station+0.006
Neg logit contributions
 ey-0.011
idges-0.010
 yogurt-0.009
 honey-0.009
ad-0.009
Token smiling
Token ID16755
Feature activation+7.64e+00

Pos logit contributions
 ey+0.035
idges+0.029
 yogurt+0.028
ad+0.028
 honey+0.027
Neg logit contributions
gy-0.044
 bank-0.035
zag-0.029
 station-0.029
 neither-0.029
Token the
Token ID262
Feature activation+2.19e-01

Pos logit contributions
 ey+0.030
idges+0.028
ad+0.026
 honey+0.025
heart+0.024
Neg logit contributions
gy-0.034
 bank-0.027
 drown-0.024
 neither-0.022
lves-0.022
Token jar
Token ID17379
Feature activation+4.55e-01

Pos logit contributions
 ey+0.017
idges+0.014
 yogurt+0.014
ad+0.014
 honey+0.014
Neg logit contributions
gy-0.019
 bank-0.016
lves-0.013
zag-0.013
 station-0.013
Token and
Token ID290
Feature activation+1.54e-01

Pos logit contributions
 ey+0.032
 yogurt+0.026
 honey+0.026
idges+0.026
ad+0.026
Neg logit contributions
gy-0.043
 bank-0.035
lves-0.031
zag-0.030
 station-0.029
Token have
Token ID423
Feature activation-2.95e+00

Pos logit contributions
 ey+0.013
idges+0.011
ad+0.011
 yogurt+0.011
 honey+0.010
Neg logit contributions
gy-0.013
 bank-0.010
lves-0.008
zag-0.008
 station-0.008
Token some
Token ID617
Feature activation-3.00e+00

Pos logit contributions
gy+0.249
 bank+0.215
 drowned+0.168
 station+0.165
 neither+0.165
Neg logit contributions
 ey-0.242
idges-0.195
ad-0.187
ango-0.184
ement-0.182
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
gy+0.247
 bank+0.235
 station+0.181
 drown+0.176
 fight+0.175
Neg logit contributions
 ey-0.214
ango-0.180
idges-0.175
ad-0.174
Jamie-0.167
Token,"
Token ID553
Feature activation-1.84e-01

Pos logit contributions
 ey+0.697
 honey+0.647
 yogurt+0.642
 sweet+0.592
ad+0.592
Neg logit contributions
gy-1.038
 bank-0.855
lves-0.796
zag-0.736
 drown-0.731
Token he
Token ID339
Feature activation+1.06e+00

Pos logit contributions
gy+0.018
 bank+0.015
lves+0.013
zag+0.013
 neither+0.012
Neg logit contributions
 ey-0.013
idges-0.010
 honey-0.010
 yogurt-0.010
ad-0.010
Token said
Token ID531
Feature activation-1.28e-01

Pos logit contributions
 ey+0.081
idges+0.067
 yogurt+0.066
ad+0.066
 honey+0.065
Neg logit contributions
gy-0.094
 bank-0.077
zag-0.064
lves-0.064
 station-0.062
Token to
Token ID284
Feature activation+7.18e-01

Pos logit contributions
gy+0.012
 bank+0.010
lves+0.008
zag+0.008
 drown+0.008
Neg logit contributions
 ey-0.009
 yogurt-0.008
 honey-0.008
idges-0.008
ad-0.008
Token Lily
Token ID20037
Feature activation-1.67e+00

Pos logit contributions
 ey+0.046
idges+0.036
 yogurt+0.035
 honey+0.035
 layers+0.033
Neg logit contributions
gy-0.075
 bank-0.061
zag-0.053
 drown-0.052
lves-0.052
Token "
Token ID366
Feature activation+2.25e+00

Pos logit contributions
gy+0.107
 bank+0.088
lves+0.078
zag+0.076
 station+0.073
Neg logit contributions
 ey-0.073
 yogurt-0.059
idges-0.058
 honey-0.058
ad-0.058
TokenDon
Token ID3987
Feature activation+1.26e+00

Pos logit contributions
 ey+0.134
 honey+0.107
idges+0.105
 yogurt+0.105
ad+0.101
Neg logit contributions
gy-0.238
 bank-0.199
lves-0.177
zag-0.174
 station-0.168
Token't
Token ID470
Feature activation-4.13e+00

Pos logit contributions
 ey+0.113
 yogurt+0.098
 honey+0.097
idges+0.096
ad+0.095
Neg logit contributions
gy-0.096
 bank-0.073
zag-0.061
lves-0.061
 station-0.057
Token worry
Token ID5490
Feature activation-4.17e-01

Pos logit contributions
gy+0.379
 bank+0.310
lves+0.274
zag+0.268
 station+0.255
Neg logit contributions
 ey-0.299
ad-0.258
 honey-0.256
 yogurt-0.255
idges-0.247
Token,
Token ID11
Feature activation+7.05e-01

Pos logit contributions
gy+0.034
 bank+0.026
zag+0.021
 neither+0.021
lves+0.021
Neg logit contributions
 ey-0.037
ad-0.030
idges-0.030
 yogurt-0.029
 layers-0.028
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.054
ad+0.044
idges+0.043
ement+0.042
 yogurt+0.042
Neg logit contributions
gy-0.063
 bank-0.050
lves-0.043
 neither-0.043
 station-0.043
Token!
Token ID0
Feature activation+2.54e+00

Pos logit contributions
 ey+0.802
 yogurt+0.674
 honey+0.667
idges+0.663
ad+0.662
Neg logit contributions
gy-1.015
 bank-0.821
lves-0.715
zag-0.704
 station-0.670
Token I
Token ID314
Feature activation+3.68e+00

Pos logit contributions
 ey+0.154
 yogurt+0.123
idges+0.121
ad+0.121
 honey+0.121
Neg logit contributions
gy-0.267
 bank-0.220
lves-0.196
zag-0.193
 drown-0.187
Token'm
Token ID1101
Feature activation-3.05e+00

Pos logit contributions
 ey+0.262
ad+0.237
 honey+0.237
 yogurt+0.231
 sweet+0.229
Neg logit contributions
gy-0.309
 bank-0.250
lves-0.232
zag-0.215
 station-0.204
Token going
Token ID1016
Feature activation+3.08e+00

Pos logit contributions
gy+0.268
 bank+0.213
lves+0.186
 drown+0.180
zag+0.178
Neg logit contributions
 ey-0.238
ad-0.196
idges-0.195
 yogurt-0.195
 honey-0.187
Token to
Token ID284
Feature activation+6.96e-01

Pos logit contributions
 ey+0.197
 yogurt+0.178
 honey+0.177
ad+0.170
idges+0.168
Neg logit contributions
gy-0.289
 bank-0.236
lves-0.219
zag-0.205
 drown-0.199
Token
Token ID198
Feature activation+2.30e-01

Pos logit contributions
 ey+0.275
 honey+0.242
 yogurt+0.237
ad+0.236
 sweet+0.228
Neg logit contributions
gy-0.385
 bank-0.326
lves-0.293
zag-0.278
 station-0.269
Token
Token ID198
Feature activation+5.00e-01

Pos logit contributions
 ey+0.014
 yogurt+0.012
 honey+0.012
idges+0.011
ad+0.011
Neg logit contributions
gy-0.024
 bank-0.019
lves-0.017
zag-0.017
 station-0.016
Token"
Token ID1
Feature activation-7.62e-01

Pos logit contributions
 ey+0.030
 yogurt+0.024
ad+0.024
idges+0.024
 honey+0.024
Neg logit contributions
gy-0.053
 bank-0.044
lves-0.039
zag-0.038
 drown-0.037
TokenSure
Token ID19457
Feature activation+2.02e+00

Pos logit contributions
gy+0.081
 bank+0.068
lves+0.061
zag+0.060
 station+0.058
Neg logit contributions
 ey-0.045
 honey-0.035
 yogurt-0.035
idges-0.035
ad-0.035
Token,
Token ID11
Feature activation+7.05e-01

Pos logit contributions
 ey+0.155
 yogurt+0.130
idges+0.128
 honey+0.128
ad+0.127
Neg logit contributions
gy-0.181
 bank-0.145
lves-0.125
zag-0.123
 station-0.117
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.052
idges+0.041
ad+0.041
 yogurt+0.040
ement+0.040
Neg logit contributions
gy-0.064
 bank-0.052
lves-0.046
 station-0.045
zag-0.043
Token,
Token ID11
Feature activation+5.83e-01

Pos logit contributions
 ey+0.835
 yogurt+0.697
idges+0.693
ad+0.684
 honey+0.684
Neg logit contributions
gy-1.000
 bank-0.799
zag-0.687
lves-0.682
 station-0.650
Token but
Token ID475
Feature activation-1.13e+00

Pos logit contributions
 ey+0.040
ad+0.032
ement+0.031
idges+0.031
odic+0.029
Neg logit contributions
gy-0.055
 bank-0.045
 station-0.040
lves-0.039
 neither-0.039
Token be
Token ID307
Feature activation+3.85e-01

Pos logit contributions
gy+0.101
 bank+0.081
lves+0.069
zag+0.068
 station+0.065
Neg logit contributions
 ey-0.087
idges-0.072
ad-0.072
 yogurt-0.072
 honey-0.070
Token careful
Token ID8161
Feature activation+7.79e-01

Pos logit contributions
 ey+0.031
ad+0.025
idges+0.025
 yogurt+0.025
ango+0.023
Neg logit contributions
gy-0.034
 bank-0.027
lves-0.023
zag-0.022
 neither-0.022
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
 ey+0.060
 yogurt+0.050
ad+0.049
idges+0.049
 honey+0.048
Neg logit contributions
gy-0.071
 bank-0.056
zag-0.049
lves-0.048
 station-0.046
Token be
Token ID307
Feature activation+6.92e-01

Pos logit contributions
 ey+0.032
idges+0.027
ad+0.027
 yogurt+0.027
 honey+0.026
Neg logit contributions
gy-0.042
 bank-0.034
lves-0.030
zag-0.029
 station-0.028
Tokeneh
Token ID17231
Feature activation-3.91e+00

Pos logit contributions
 ey+0.051
ad+0.045
 yogurt+0.045
 honey+0.044
idges+0.043
Neg logit contributions
gy-0.060
 bank-0.049
lves-0.043
 drown-0.041
zag-0.041
Tokenive
Token ID425
Feature activation-5.00e-01

Pos logit contributions
gy+0.321
 bank+0.251
lves+0.219
zag+0.207
 station+0.200
Neg logit contributions
 ey-0.317
 yogurt-0.279
ad-0.276
 honey-0.274
idges-0.268
Token full
Token ID1336
Feature activation+2.17e+00

Pos logit contributions
gy+0.045
 bank+0.036
lves+0.032
zag+0.031
 drown+0.030
Neg logit contributions
 ey-0.037
 yogurt-0.031
 honey-0.031
ad-0.031
idges-0.031
Token of
Token ID286
Feature activation+3.15e+00

Pos logit contributions
 ey+0.155
idges+0.121
ango+0.113
ad+0.111
 subtract+0.111
Neg logit contributions
gy-0.192
 bank-0.169
 station-0.137
zag-0.135
 neither-0.134
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.226
idges+0.180
ement+0.176
ango+0.174
ad+0.173
Neg logit contributions
gy-0.276
 bank-0.247
lves-0.198
 drown-0.197
 station-0.186
Token!
Token ID0
Feature activation+2.48e+00

Pos logit contributions
 ey+0.808
 yogurt+0.667
idges+0.661
ad+0.660
 honey+0.652
Neg logit contributions
gy-1.011
 bank-0.819
zag-0.704
lves-0.702
 station-0.667
Token He
Token ID679
Feature activation+3.01e+00

Pos logit contributions
 ey+0.166
idges+0.136
 yogurt+0.135
 honey+0.134
ad+0.133
Neg logit contributions
gy-0.244
 bank-0.200
lves-0.176
zag-0.173
 station-0.166
Token was
Token ID373
Feature activation+1.33e+00

Pos logit contributions
 ey+0.248
idges+0.211
 yogurt+0.207
ad+0.205
 honey+0.199
Neg logit contributions
gy-0.252
 bank-0.203
zag-0.166
lves-0.165
 station-0.153
Token so
Token ID523
Feature activation+7.38e-01

Pos logit contributions
 ey+0.108
idges+0.090
 yogurt+0.087
ad+0.086
 honey+0.083
Neg logit contributions
gy-0.115
 bank-0.091
lves-0.076
zag-0.076
 drown-0.073
Token happy
Token ID3772
Feature activation+9.74e-01

Pos logit contributions
 ey+0.066
idges+0.056
ad+0.055
 yogurt+0.053
ango+0.052
Neg logit contributions
gy-0.056
 bank-0.043
lves-0.036
 drown-0.036
zag-0.035
Token
Token ID26391
Feature activation-1.31e+00

Pos logit contributions
gy+0.497
 bank+0.400
lves+0.359
zag+0.341
 station+0.328
Neg logit contributions
 ey-0.416
ad-0.374
 yogurt-0.347
idges-0.345
 honey-0.338
Token
Token ID8151
Feature activation-4.15e+00

Pos logit contributions
gy+0.122
 bank+0.103
lves+0.092
 station+0.086
zag+0.084
Neg logit contributions
 ey-0.087
ad-0.074
 yogurt-0.074
 honey-0.070
idges-0.070
Tokenm
Token ID76
Feature activation+2.07e+00

Pos logit contributions
gy+0.320
 bank+0.248
lves+0.210
zag+0.197
 station+0.193
Neg logit contributions
 ey-0.355
 yogurt-0.314
ad-0.309
idges-0.307
 honey-0.304
Token sorry
Token ID7926
Feature activation+1.66e+00

Pos logit contributions
 ey+0.161
 yogurt+0.135
 honey+0.134
idges+0.133
ad+0.130
Neg logit contributions
gy-0.184
 bank-0.144
zag-0.126
lves-0.123
 drown-0.119
Token,
Token ID11
Feature activation+6.34e-01

Pos logit contributions
 ey+0.130
idges+0.108
 yogurt+0.107
ad+0.107
 honey+0.105
Neg logit contributions
gy-0.146
 bank-0.117
zag-0.100
lves-0.098
 station-0.094
Token honey
Token ID12498
Feature activation+1.10e+01

Pos logit contributions
 ey+0.045
idges+0.037
ad+0.036
 yogurt+0.036
 honey+0.035
Neg logit contributions
gy-0.059
 bank-0.049
lves-0.042
zag-0.041
 station-0.041
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
 ey+0.758
 honey+0.655
 yogurt+0.653
ad+0.635
idges+0.629
Neg logit contributions
gy-1.015
 bank-0.832
lves-0.751
zag-0.707
 drown-0.679
Token I
Token ID314
Feature activation+3.64e+00

Pos logit contributions
 ey+0.024
idges+0.019
 honey+0.019
 yogurt+0.019
ad+0.019
Neg logit contributions
gy-0.037
 bank-0.030
lves-0.027
zag-0.026
 station-0.026
Tokenâ
Token ID22940
Feature activation-5.69e+00

Pos logit contributions
 ey+0.271
 yogurt+0.240
 honey+0.237
ad+0.237
 sweet+0.229
Neg logit contributions
gy-0.315
 bank-0.249
lves-0.227
zag-0.215
 station-0.202
Token
Token ID26391
Feature activation-1.66e+00

Pos logit contributions
gy+0.513
 bank+0.413
lves+0.359
zag+0.352
 drown+0.335
Neg logit contributions
 ey-0.427
 yogurt-0.362
 honey-0.359
ad-0.356
idges-0.355
Token
Token ID8151
Feature activation-4.55e+00

Pos logit contributions
gy+0.139
 bank+0.118
lves+0.104
 station+0.094
zag+0.093
Neg logit contributions
 ey-0.118
 yogurt-0.107
ad-0.103
 goodness-0.102
idges-0.100
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
 ey+0.395
idges+0.328
 yogurt+0.321
ad+0.318
 honey+0.316
Neg logit contributions
gy-0.455
 bank-0.365
zag-0.310
lves-0.303
 station-0.295
Token He
Token ID679
Feature activation+3.05e+00

Pos logit contributions
 ey+0.027
idges+0.026
ad+0.024
illy+0.022
inges+0.022
Neg logit contributions
gy-0.030
 bank-0.024
 drown-0.021
 neither-0.019
zag-0.019
Token does
Token ID857
Feature activation+4.59e+00

Pos logit contributions
 ey+0.216
idges+0.190
ad+0.188
 importantly+0.178
mmmm+0.176
Neg logit contributions
gy-0.267
 bank-0.232
lves-0.185
 station-0.181
 drown-0.180
Token not
Token ID407
Feature activation-2.97e+00

Pos logit contributions
 ey+0.435
idges+0.367
ad+0.367
 yogurt+0.365
 honey+0.361
Neg logit contributions
gy-0.325
 bank-0.251
zag-0.202
lves-0.197
 drown-0.196
Token like
Token ID588
Feature activation+1.71e+00

Pos logit contributions
gy+0.252
 bank+0.201
lves+0.170
zag+0.167
 drown+0.162
Neg logit contributions
 ey-0.239
idges-0.202
 yogurt-0.201
 honey-0.199
ad-0.198
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.124
ement+0.101
idges+0.100
ad+0.099
odic+0.095
Neg logit contributions
gy-0.150
 bank-0.128
 drown-0.108
 neither-0.106
lves-0.105
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
 ey+0.782
 honey+0.701
 yogurt+0.697
ad+0.670
idges+0.662
Neg logit contributions
gy-0.972
 bank-0.784
lves-0.707
zag-0.673
 drown-0.641
Token But
Token ID887
Feature activation-2.98e+00

Pos logit contributions
 ey+0.031
idges+0.029
ad+0.028
illy+0.025
ement+0.024
Neg logit contributions
gy-0.032
 bank-0.025
 drown-0.022
 neither-0.022
house-0.020
Token he
Token ID339
Feature activation+1.09e+00

Pos logit contributions
gy+0.263
 bank+0.212
 neither+0.196
zag+0.183
 drown+0.180
Neg logit contributions
 ey-0.229
idges-0.189
ad-0.184
 layers-0.170
ement-0.168
Token listens
Token ID35019
Feature activation+2.71e+00

Pos logit contributions
 ey+0.078
idges+0.066
ad+0.065
 yogurt+0.062
 honey+0.061
Neg logit contributions
gy-0.097
 bank-0.082
lves-0.068
zag-0.067
 drown-0.067
Token to
Token ID284
Feature activation+8.10e-01

Pos logit contributions
 ey+0.271
idges+0.225
ad+0.223
 yogurt+0.210
 honey+0.206
Neg logit contributions
gy-0.184
 bank-0.143
zag-0.121
 neither-0.107
 station-0.106
Token with
Token ID351
Feature activation+1.13e-01

Pos logit contributions
 ey+0.683
 yogurt+0.637
 honey+0.635
 sweet+0.589
ad+0.576
Neg logit contributions
gy-1.046
 bank-0.862
lves-0.806
zag-0.741
 drown-0.735
Token me
Token ID502
Feature activation+6.08e+00

Pos logit contributions
 ey+0.006
ement+0.004
 yogurt+0.004
idges+0.004
ad+0.004
Neg logit contributions
gy-0.013
 bank-0.011
lves-0.009
 drowned-0.009
 neither-0.009
Token,
Token ID11
Feature activation+5.31e-01

Pos logit contributions
 ey+0.452
 yogurt+0.378
 honey+0.375
idges+0.373
ad+0.373
Neg logit contributions
gy-0.556
 bank-0.447
lves-0.388
zag-0.384
 station-0.363
Token I
Token ID314
Feature activation+3.69e+00

Pos logit contributions
 ey+0.040
ad+0.034
idges+0.033
 yogurt+0.032
ement+0.032
Neg logit contributions
gy-0.046
 bank-0.037
 station-0.033
lves-0.032
 drown-0.031
Token love
Token ID1842
Feature activation+4.54e+00

Pos logit contributions
 ey+0.235
 yogurt+0.222
 sweet+0.214
 honey+0.212
ad+0.207
Neg logit contributions
gy-0.334
 bank-0.271
lves-0.256
zag-0.243
 station-0.234
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.356
ement+0.301
ad+0.285
idges+0.275
Jamie+0.267
Neg logit contributions
gy-0.384
 bank-0.316
lves-0.258
 neither-0.250
house-0.245
Token too
Token ID1165
Feature activation-8.64e-01

Pos logit contributions
 ey+0.715
 honey+0.644
 yogurt+0.640
ad+0.602
idges+0.601
Neg logit contributions
gy-1.036
 bank-0.855
lves-0.773
zag-0.733
 drown-0.714
Token!"
Token ID2474
Feature activation+6.48e-01

Pos logit contributions
gy+0.079
 bank+0.064
lves+0.055
zag+0.055
 drown+0.052
Neg logit contributions
 ey-0.064
 yogurt-0.053
ad-0.053
idges-0.052
 honey-0.052
Token But
Token ID887
Feature activation-2.98e+00

Pos logit contributions
 ey+0.042
 yogurt+0.036
 honey+0.036
ad+0.035
idges+0.034
Neg logit contributions
gy-0.063
 bank-0.051
lves-0.046
zag-0.046
 drown-0.044
Token the
Token ID262
Feature activation+2.48e-01

Pos logit contributions
gy+0.318
 bank+0.276
zag+0.255
lves+0.252
 drown+0.241
Neg logit contributions
 ey-0.140
 honey-0.128
 yogurt-0.125
 sweet-0.123
ad-0.122
Token bird
Token ID6512
Feature activation-2.85e+00

Pos logit contributions
 ey+0.024
idges+0.021
ad+0.020
 yogurt+0.020
 honey+0.019
Neg logit contributions
gy-0.018
 bank-0.014
zag-0.011
lves-0.011
 station-0.010
Token a
Token ID257
Feature activation+4.42e-01

Pos logit contributions
gy+0.221
 bank+0.173
lves+0.154
 drown+0.145
zag+0.144
Neg logit contributions
 ey-0.191
idges-0.163
ad-0.162
 yogurt-0.157
 honey-0.153
Token little
Token ID1310
Feature activation+1.34e+00

Pos logit contributions
 ey+0.029
 yogurt+0.025
 honey+0.025
 sweet+0.024
ad+0.023
Neg logit contributions
gy-0.044
 bank-0.036
lves-0.032
zag-0.031
 drown-0.029
Token bit
Token ID1643
Feature activation-5.96e+00

Pos logit contributions
 ey+0.108
 honey+0.105
 sweet+0.103
 yogurt+0.102
 mirror+0.093
Neg logit contributions
gy-0.108
 bank-0.082
zag-0.075
lves-0.074
 drown-0.063
Token sick
Token ID6639
Feature activation-7.33e+00

Pos logit contributions
gy+0.477
 bank+0.380
lves+0.324
zag+0.304
 drown+0.299
Neg logit contributions
 ey-0.504
ad-0.428
idges-0.425
 yogurt-0.420
 honey-0.409
Token,
Token ID11
Feature activation+5.40e-01

Pos logit contributions
gy+0.609
 bank+0.487
lves+0.393
zag+0.393
 station+0.386
Neg logit contributions
 ey-0.607
idges-0.511
ad-0.500
 yogurt-0.499
 honey-0.485
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.048
ad+0.043
idges+0.040
ango+0.039
odic+0.038
Neg logit contributions
gy-0.037
 bank-0.029
 neither-0.028
house-0.025
 station-0.024
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
 ey+0.725
 honey+0.665
 yogurt+0.643
ad+0.616
 sweet+0.612
Neg logit contributions
gy-1.008
 bank-0.834
lves-0.765
zag-0.714
 drown-0.691
Token But
Token ID887
Feature activation-2.98e+00

Pos logit contributions
 ey+0.028
ad+0.024
idges+0.023
 yogurt+0.022
ement+0.021
Neg logit contributions
gy-0.037
 bank-0.029
lves-0.026
 station-0.025
house-0.025
Token don
Token ID836
Feature activation-2.53e+00

Pos logit contributions
gy+0.258
 bank+0.200
 neither+0.182
 station+0.168
lves+0.167
Neg logit contributions
 ey-0.235
ad-0.199
idges-0.191
ango-0.184
ement-0.184
Token't
Token ID470
Feature activation-4.40e+00

Pos logit contributions
gy+0.216
 bank+0.172
lves+0.148
zag+0.141
 station+0.135
Neg logit contributions
 ey-0.200
idges-0.174
 honey-0.174
 yogurt-0.174
ad-0.171
Token worry
Token ID5490
Feature activation-6.30e-01

Pos logit contributions
gy+0.365
 bank+0.288
lves+0.244
zag+0.238
 drown+0.229
Neg logit contributions
 ey-0.364
 yogurt-0.310
idges-0.309
ad-0.308
 honey-0.306
Token jar
Token ID17379
Feature activation+1.86e-01

Pos logit contributions
 ey+0.737
 yogurt+0.634
 honey+0.631
ad+0.608
idges+0.590
Neg logit contributions
gy-1.032
 bank-0.833
lves-0.768
zag-0.722
 drown-0.710
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
 ey+0.013
 yogurt+0.011
 honey+0.011
ad+0.011
idges+0.011
Neg logit contributions
gy-0.018
 bank-0.014
lves-0.013
zag-0.012
 drown-0.012
Token The
Token ID383
Feature activation-2.49e+00

Pos logit contributions
 ey+0.024
idges+0.020
ad+0.019
 yogurt+0.019
 honey+0.019
Neg logit contributions
gy-0.036
 bank-0.030
lves-0.026
zag-0.025
 station-0.025
Token bear
Token ID6842
Feature activation-9.05e-01

Pos logit contributions
gy+0.202
 bank+0.164
lves+0.132
 station+0.128
zag+0.127
Neg logit contributions
 ey-0.217
idges-0.187
ad-0.183
 yogurt-0.180
 honey-0.172
Token loved
Token ID6151
Feature activation+2.63e+00

Pos logit contributions
gy+0.086
 bank+0.069
lves+0.065
 drown+0.062
zag+0.061
Neg logit contributions
 ey-0.057
 yogurt-0.050
 honey-0.049
ad-0.049
 sweet-0.048
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.207
ement+0.177
idges+0.168
ad+0.163
odic+0.157
Neg logit contributions
gy-0.227
 bank-0.191
lves-0.157
 fight-0.150
 neither-0.149
Token,
Token ID11
Feature activation+5.52e-01

Pos logit contributions
 ey+0.826
idges+0.680
ad+0.666
 yogurt+0.665
 honey+0.651
Neg logit contributions
gy-1.001
 bank-0.806
zag-0.686
lves-0.680
 station-0.652
Token so
Token ID523
Feature activation+8.41e-01

Pos logit contributions
 ey+0.046
idges+0.039
ad+0.038
ement+0.037
 yogurt+0.036
Neg logit contributions
gy-0.044
 bank-0.037
lves-0.029
 neither-0.029
 station-0.029
Token he
Token ID339
Feature activation+1.08e+00

Pos logit contributions
 ey+0.047
 yogurt+0.038
 honey+0.037
ad+0.036
idges+0.036
Neg logit contributions
gy-0.092
 bank-0.078
lves-0.070
zag-0.069
 station-0.066
Token decided
Token ID3066
Feature activation-9.75e-01

Pos logit contributions
 ey+0.082
 honey+0.077
 yogurt+0.075
ad+0.073
 sweet+0.072
Neg logit contributions
gy-0.091
 bank-0.069
lves-0.063
zag-0.061
 drown-0.059
Token to
Token ID284
Feature activation+8.02e-01

Pos logit contributions
gy+0.084
 bank+0.067
lves+0.057
zag+0.056
 drown+0.053
Neg logit contributions
 ey-0.079
 yogurt-0.066
idges-0.066
 honey-0.066
ad-0.066
TokenIt
Token ID1026
Feature activation+4.42e+00

Pos logit contributions
gy+0.123
 bank+0.105
lves+0.093
zag+0.092
 station+0.089
Neg logit contributions
 ey-0.054
 yogurt-0.043
idges-0.041
ad-0.041
 honey-0.040
Token's
Token ID338
Feature activation-6.18e+00

Pos logit contributions
 ey+0.341
 honey+0.332
 sweet+0.314
 yogurt+0.305
idges+0.303
Neg logit contributions
gy-0.325
 bank-0.284
lves-0.243
 drown-0.219
zag-0.216
Token an
Token ID281
Feature activation-3.01e+00

Pos logit contributions
gy+0.603
 bank+0.507
lves+0.448
zag+0.438
 drown+0.414
Neg logit contributions
 ey-0.408
 honey-0.353
 yogurt-0.346
ad-0.334
idges-0.332
Token earthquake
Token ID16295
Feature activation-1.23e+00

Pos logit contributions
gy+0.288
 bank+0.233
lves+0.209
zag+0.208
 drown+0.199
Neg logit contributions
 ey-0.207
 honey-0.178
 yogurt-0.176
ad-0.176
idges-0.168
Token,
Token ID11
Feature activation+5.37e-01

Pos logit contributions
gy+0.118
 bank+0.098
lves+0.087
zag+0.084
 drown+0.081
Neg logit contributions
 ey-0.083
 yogurt-0.069
 honey-0.069
ad-0.068
idges-0.068
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.038
ad+0.032
idges+0.030
odic+0.030
 subtract+0.030
Neg logit contributions
gy-0.047
 bank-0.038
 neither-0.036
 station-0.034
 drown-0.034
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
 ey+0.681
 honey+0.615
 yogurt+0.584
ad+0.569
 sweet+0.558
Neg logit contributions
gy-1.039
 bank-0.877
lves-0.817
zag-0.740
 drown-0.719
Token It
Token ID632
Feature activation+1.41e+00

Pos logit contributions
 ey+0.025
 yogurt+0.021
idges+0.021
 honey+0.020
ad+0.020
Neg logit contributions
gy-0.040
 bank-0.032
lves-0.028
zag-0.028
 drown-0.027
Token's
Token ID338
Feature activation-6.15e+00

Pos logit contributions
 ey+0.091
 honey+0.084
idges+0.078
 sweet+0.077
ad+0.075
Neg logit contributions
gy-0.128
 bank-0.112
lves-0.095
zag-0.093
suits-0.089
Token when
Token ID618
Feature activation-6.71e-01

Pos logit contributions
gy+0.572
 bank+0.487
lves+0.420
zag+0.411
 station+0.382
Neg logit contributions
 ey-0.417
 honey-0.384
 sweet-0.357
 yogurt-0.355
idges-0.351
Token the
Token ID262
Feature activation+2.48e-01

Pos logit contributions
gy+0.067
 bank+0.055
lves+0.049
zag+0.048
 station+0.045
Neg logit contributions
 ey-0.044
 yogurt-0.037
 honey-0.037
idges-0.036
ad-0.035
Token and
Token ID290
Feature activation-1.46e-01

Pos logit contributions
gy+0.288
 bank+0.244
lves+0.230
 drown+0.227
 neither+0.220
Neg logit contributions
 ey-0.165
ad-0.156
 honey-0.154
 sweet-0.152
 yogurt-0.145
Token Red
Token ID2297
Feature activation-2.41e+00

Pos logit contributions
gy+0.013
 bank+0.010
zag+0.010
 drown+0.009
lves+0.009
Neg logit contributions
 ey-0.010
 honey-0.009
 sweet-0.009
 yogurt-0.009
ad-0.009
Token went
Token ID1816
Feature activation-8.23e-01

Pos logit contributions
gy+0.197
lves+0.163
 bank+0.159
zag+0.158
 drown+0.157
Neg logit contributions
ad-0.138
 sweet-0.132
 yogurt-0.125
 honey-0.124
 ey-0.116
Token on
Token ID319
Feature activation-8.21e-01

Pos logit contributions
gy+0.077
lves+0.063
 bank+0.062
 neither+0.058
 drown+0.055
Neg logit contributions
 ey-0.048
 yogurt-0.048
 honey-0.046
 sweet-0.043
 pasta-0.043
Token a
Token ID257
Feature activation+4.60e-01

Pos logit contributions
gy+0.090
 bank+0.075
lves+0.071
zag+0.069
 drown+0.066
Neg logit contributions
 ey-0.041
 yogurt-0.037
 honey-0.035
 sweet-0.034
ad-0.034
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 sweet+0.026
 yogurt+0.025
 honey+0.024
 pasta+0.023
 delicious+0.023
Neg logit contributions
gy-0.047
 neither-0.035
 bank-0.034
lves-0.034
ung-0.032
Tokenmoon
Token ID22977
Feature activation-5.67e+00

Pos logit contributions
 honey+0.628
 yogurt+0.621
ad+0.604
 ey+0.596
 pasta+0.593
Neg logit contributions
gy-0.932
lves-0.797
 bank-0.730
 drown-0.715
 argue-0.686
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
gy+0.603
lves+0.509
 bank+0.500
 drown+0.489
 argue+0.448
Neg logit contributions
ad-0.239
 sweet-0.225
 honey-0.225
 ey-0.206
 yogurt-0.204
Token They
Token ID1119
Feature activation-3.59e+00

Pos logit contributions
 ey+0.025
 honey+0.022
 sweet+0.022
 yogurt+0.022
 cereal+0.022
Neg logit contributions
gy-0.035
 bank-0.027
zag-0.026
lves-0.026
 drown-0.025
Token sw
Token ID1509
Feature activation-5.35e+00

Pos logit contributions
gy+0.334
 bank+0.254
zag+0.253
 drown+0.240
lves+0.238
Neg logit contributions
 yogurt-0.215
 honey-0.214
 ey-0.214
 sweet-0.204
ad-0.204
Tokenam
Token ID321
Feature activation-1.64e+00

Pos logit contributions
gy+0.439
 bank+0.369
lves+0.324
 drown+0.316
 station+0.312
Neg logit contributions
 ey-0.402
idges-0.351
ad-0.351
 honey-0.345
 yogurt-0.336
Token he
Token ID339
Feature activation+1.06e+00

Pos logit contributions
gy+0.013
 bank+0.011
lves+0.009
 neither+0.009
zag+0.009
Neg logit contributions
 ey-0.012
idges-0.010
ad-0.010
ement-0.010
 yogurt-0.010
Token picked
Token ID6497
Feature activation+1.86e+00

Pos logit contributions
 ey+0.084
idges+0.070
 yogurt+0.070
ad+0.069
 honey+0.068
Neg logit contributions
gy-0.093
 bank-0.075
lves-0.064
zag-0.062
 station-0.058
Token some
Token ID617
Feature activation-3.18e+00

Pos logit contributions
 ey+0.172
 importantly+0.143
idges+0.142
ad+0.134
 subtract+0.134
Neg logit contributions
gy-0.141
 bank-0.114
lves-0.088
 neither-0.084
zag-0.080
Token of
Token ID286
Feature activation+3.05e+00

Pos logit contributions
 bank+0.237
gy+0.233
 away+0.190
 bit+0.189
 after+0.180
Neg logit contributions
 ey-0.226
Adam-0.188
Jake-0.187
David-0.185
ad-0.184
Token the
Token ID262
Feature activation+2.28e-01

Pos logit contributions
 ey+0.249
idges+0.203
ement+0.199
 subtract+0.194
ention+0.194
Neg logit contributions
gy-0.251
 bank-0.204
 neither-0.168
 drown-0.164
lves-0.160
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.010
ad+0.008
idges+0.008
Adam+0.007
 subtract+0.007
Neg logit contributions
gy-0.026
 bank-0.023
lves-0.020
zag-0.020
house-0.019
Token to
Token ID284
Feature activation+7.98e-01

Pos logit contributions
 ey+0.836
idges+0.696
 yogurt+0.693
ad+0.691
 honey+0.683
Neg logit contributions
gy-0.980
 bank-0.790
zag-0.670
lves-0.669
 station-0.632
Token eat
Token ID4483
Feature activation+1.91e+00

Pos logit contributions
 ey+0.076
idges+0.066
ement+0.066
ango+0.064
 importantly+0.063
Neg logit contributions
gy-0.055
 bank-0.045
 drown-0.032
house-0.031
 fight-0.030
Token.
Token ID13
Feature activation+3.86e-01

Pos logit contributions
 ey+0.180
idges+0.147
ad+0.141
 importantly+0.140
 subtract+0.140
Neg logit contributions
gy-0.137
 bank-0.121
 neither-0.084
 station-0.081
house-0.080
Token He
Token ID679
Feature activation+3.07e+00

Pos logit contributions
 ey+0.027
idges+0.022
ad+0.022
 honey+0.021
 yogurt+0.021
Neg logit contributions
gy-0.038
 bank-0.032
lves-0.027
zag-0.026
 station-0.026
Token had
Token ID550
Feature activation-7.26e-01

Pos logit contributions
 ey+0.256
idges+0.216
 yogurt+0.213
ad+0.212
 honey+0.209
Neg logit contributions
gy-0.255
 bank-0.204
lves-0.169
zag-0.165
 station-0.156
Token woods
Token ID16479
Feature activation-6.21e-01

Pos logit contributions
 ey+0.016
idges+0.015
ad+0.014
 yogurt+0.014
 honey+0.014
Neg logit contributions
gy-0.018
 bank-0.015
lves-0.012
zag-0.012
 station-0.012
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
gy+0.062
 bank+0.050
lves+0.046
zag+0.044
 drown+0.042
Neg logit contributions
 ey-0.040
 yogurt-0.033
ad-0.033
 honey-0.033
idges-0.032
Token It
Token ID632
Feature activation+1.38e+00

Pos logit contributions
 ey+0.027
idges+0.025
ad+0.023
 honey+0.022
heart+0.022
Neg logit contributions
gy-0.033
 bank-0.026
 drown-0.022
 station-0.021
lves-0.021
Token smelled
Token ID37609
Feature activation+3.80e+00

Pos logit contributions
 ey+0.116
idges+0.100
 yogurt+0.098
 honey+0.096
ad+0.095
Neg logit contributions
gy-0.116
 bank-0.090
zag-0.076
lves-0.075
 station-0.070
Token the
Token ID262
Feature activation+2.22e-01

Pos logit contributions
 ey+0.334
idges+0.298
 subtract+0.289
ango+0.286
ement+0.276
Neg logit contributions
gy-0.252
 bank-0.228
 drown-0.205
 neither-0.186
 drowned-0.178
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.014
idges+0.013
ad+0.013
mmmm+0.012
Jamie+0.012
Neg logit contributions
gy-0.020
 bank-0.019
 drown-0.015
lves-0.015
 station-0.015
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
 ey+0.815
idges+0.677
 yogurt+0.673
ad+0.667
 honey+0.660
Neg logit contributions
gy-1.001
 bank-0.811
zag-0.695
lves-0.682
 station-0.658
Token It
Token ID632
Feature activation+1.41e+00

Pos logit contributions
 ey+0.029
idges+0.027
ad+0.025
 honey+0.023
heart+0.023
Neg logit contributions
gy-0.032
 bank-0.025
 drown-0.022
 neither-0.021
 station-0.020
Token saw
Token ID2497
Feature activation-8.52e-01

Pos logit contributions
 ey+0.121
idges+0.106
 yogurt+0.101
ummy+0.100
ad+0.100
Neg logit contributions
gy-0.116
 bank-0.090
zag-0.074
lves-0.074
 sank-0.071
Token the
Token ID262
Feature activation+2.38e-01

Pos logit contributions
gy+0.064
 bank+0.053
lves+0.046
 neither+0.044
 drown+0.044
Neg logit contributions
 ey-0.070
idges-0.060
 subtract-0.057
mmmm-0.057
ad-0.057
Token broken
Token ID5445
Feature activation-1.83e+00

Pos logit contributions
 ey+0.018
idges+0.017
ad+0.016
mmmm+0.015
ement+0.015
Neg logit contributions
gy-0.020
 bank-0.017
lves-0.014
 drown-0.014
 station-0.014
Token are
Token ID389
Feature activation+4.65e-01

Pos logit contributions
gy+0.138
 bank+0.112
lves+0.105
zag+0.100
 drown+0.096
Neg logit contributions
 ey-0.070
 honey-0.059
 yogurt-0.058
ad-0.058
idges-0.057
Token no
Token ID645
Feature activation-4.47e+00

Pos logit contributions
 ey+0.031
 honey+0.027
 yogurt+0.026
ad+0.025
idges+0.025
Neg logit contributions
gy-0.045
 bank-0.037
lves-0.033
zag-0.032
 drown-0.031
Token more
Token ID517
Feature activation+1.98e+00

Pos logit contributions
gy+0.465
 bank+0.377
lves+0.344
zag+0.333
 drown+0.317
Neg logit contributions
 ey-0.273
 honey-0.235
 yogurt-0.232
ad-0.224
idges-0.222
Token seats
Token ID8632
Feature activation-1.23e+00

Pos logit contributions
 ey+0.128
 yogurt+0.106
 honey+0.106
idges+0.104
ad+0.103
Neg logit contributions
gy-0.199
 bank-0.163
lves-0.146
zag-0.142
 drown-0.136
Token,
Token ID11
Feature activation+5.31e-01

Pos logit contributions
gy+0.115
 bank+0.093
lves+0.084
zag+0.080
 drown+0.077
Neg logit contributions
 ey-0.086
 yogurt-0.075
 honey-0.074
ad-0.073
idges-0.072
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.039
ad+0.033
idges+0.032
 yogurt+0.032
 honey+0.032
Neg logit contributions
gy-0.048
 bank-0.039
lves-0.034
zag-0.033
 station-0.032
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
 ey+0.622
 honey+0.599
 yogurt+0.572
 sweet+0.539
ad+0.536
Neg logit contributions
gy-1.047
 bank-0.866
lves-0.842
zag-0.751
 drown-0.738
Token The
Token ID383
Feature activation-2.47e+00

Pos logit contributions
 ey+0.027
 yogurt+0.022
 honey+0.022
idges+0.022
ad+0.022
Neg logit contributions
gy-0.036
 bank-0.029
lves-0.025
zag-0.025
 station-0.024
Token theater
Token ID13766
Feature activation+1.21e+00

Pos logit contributions
gy+0.221
 bank+0.188
 station+0.160
zag+0.160
lves+0.155
Neg logit contributions
 ey-0.182
idges-0.152
ad-0.150
 yogurt-0.148
 honey-0.144
Token is
Token ID318
Feature activation+1.96e+00

Pos logit contributions
 ey+0.070
 yogurt+0.058
 honey+0.058
idges+0.056
ad+0.055
Neg logit contributions
gy-0.128
 bank-0.105
lves-0.097
zag-0.092
 drown-0.090
Token full
Token ID1336
Feature activation+2.02e+00

Pos logit contributions
 ey+0.137
 honey+0.119
 yogurt+0.118
ad+0.113
idges+0.113
Neg logit contributions
gy-0.184
 bank-0.149
lves-0.133
zag-0.129
 drown-0.122
Token for
Token ID329
Feature activation-1.56e+00

Pos logit contributions
gy+0.061
 bank+0.049
lves+0.043
zag+0.042
 drown+0.040
Neg logit contributions
 ey-0.051
 yogurt-0.044
 honey-0.043
ad-0.042
idges-0.042
Token dinner
Token ID8073
Feature activation+2.48e+00

Pos logit contributions
gy+0.128
 bank+0.109
 fight+0.089
 argue+0.089
 drown+0.087
Neg logit contributions
 ey-0.128
idges-0.097
ement-0.096
elling-0.091
ad-0.089
Token.
Token ID13
Feature activation+3.61e-01

Pos logit contributions
 ey+0.170
 yogurt+0.144
 honey+0.143
ad+0.140
idges+0.140
Neg logit contributions
gy-0.237
 bank-0.193
lves-0.171
zag-0.167
 drown-0.160
Token She
Token ID1375
Feature activation+1.94e+00

Pos logit contributions
 ey+0.032
ad+0.029
idges+0.029
odic+0.027
 honey+0.027
Neg logit contributions
gy-0.026
 bank-0.020
lves-0.016
house-0.016
zag-0.015
Token liked
Token ID8288
Feature activation+1.39e+00

Pos logit contributions
 ey+0.144
 yogurt+0.126
 honey+0.125
ad+0.122
idges+0.120
Neg logit contributions
gy-0.173
 bank-0.138
lves-0.122
zag-0.119
 drown-0.114
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.146
ement+0.130
ad+0.125
idges+0.120
mmmm+0.116
Neg logit contributions
gy-0.079
 bank-0.059
 neither-0.045
 fight-0.044
 argue-0.042
Token so
Token ID523
Feature activation+8.19e-01

Pos logit contributions
 ey+0.856
idges+0.700
ad+0.697
 yogurt+0.695
 honey+0.670
Neg logit contributions
gy-0.972
 bank-0.772
zag-0.666
lves-0.650
 station-0.625
Token much
Token ID881
Feature activation-1.66e+00

Pos logit contributions
 ey+0.074
idges+0.060
ad+0.060
 yogurt+0.058
 honey+0.058
Neg logit contributions
gy-0.061
 bank-0.046
lves-0.039
zag-0.039
 neither-0.038
Token that
Token ID326
Feature activation-5.79e-01

Pos logit contributions
gy+0.096
 bank+0.077
zag+0.066
 neither+0.063
 they+0.062
Neg logit contributions
 ey-0.162
idges-0.134
ad-0.132
ement-0.128
Jamie-0.127
Token she
Token ID673
Feature activation-7.37e-02

Pos logit contributions
gy+0.054
 bank+0.044
 neither+0.038
zag+0.037
lves+0.037
Neg logit contributions
 ey-0.042
idges-0.034
ad-0.034
ement-0.032
 yogurt-0.031
Token did
Token ID750
Feature activation+3.13e+00

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
zag+0.004
 drown+0.004
Neg logit contributions
 ey-0.006
 honey-0.005
 yogurt-0.005
ad-0.005
idges-0.005
Token hive
Token ID35881
Feature activation-2.18e+00

Pos logit contributions
 ey+0.015
 honey+0.014
 yogurt+0.013
 sweet+0.013
ad+0.012
Neg logit contributions
gy-0.018
 bank-0.014
lves-0.013
zag-0.013
 drown-0.012
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
gy+0.217
 bank+0.180
lves+0.168
zag+0.155
 drown+0.154
Neg logit contributions
 ey-0.135
 yogurt-0.116
 honey-0.115
ad-0.111
 sweet-0.109
Token They
Token ID1119
Feature activation-3.62e+00

Pos logit contributions
 ey+0.030
idges+0.026
ad+0.025
 honey+0.025
 yogurt+0.025
Neg logit contributions
gy-0.029
 bank-0.023
lves-0.019
zag-0.019
 station-0.019
Token made
Token ID925
Feature activation-1.18e+00

Pos logit contributions
gy+0.349
 bank+0.282
lves+0.259
zag+0.255
 drown+0.244
Neg logit contributions
 ey-0.228
 honey-0.206
 yogurt-0.205
ad-0.199
 sweet-0.198
Token sweet
Token ID6029
Feature activation+9.49e+00

Pos logit contributions
gy+0.119
 bank+0.100
lves+0.087
zag+0.084
 drown+0.083
Neg logit contributions
 ey-0.077
ad-0.060
idges-0.060
 yogurt-0.059
ement-0.055
Token honey
Token ID12498
Feature activation+1.09e+01

Pos logit contributions
 ey+0.701
ad+0.578
idges+0.563
 subtract+0.538
 yogurt+0.534
Neg logit contributions
gy-0.846
 bank-0.706
lves-0.571
 station-0.552
zag-0.551
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
 honey+0.666
 ey+0.653
 sweet+0.617
 yogurt+0.584
ad+0.547
Neg logit contributions
gy-1.029
 bank-0.857
lves-0.842
 drowned-0.740
zag-0.739
Token They
Token ID1119
Feature activation-3.60e+00

Pos logit contributions
 ey+0.030
idges+0.025
ad+0.025
 honey+0.025
 yogurt+0.024
Neg logit contributions
gy-0.032
 bank-0.025
lves-0.021
zag-0.021
 station-0.021
Token worked
Token ID3111
Feature activation-7.05e-01

Pos logit contributions
gy+0.333
 bank+0.266
lves+0.244
zag+0.239
 drown+0.226
Neg logit contributions
 ey-0.247
 honey-0.223
 yogurt-0.222
ad-0.213
 sweet-0.210
Token hard
Token ID1327
Feature activation+1.64e+00

Pos logit contributions
gy+0.065
 bank+0.053
lves+0.048
 drown+0.045
zag+0.045
Neg logit contributions
 ey-0.049
 honey-0.043
 yogurt-0.043
 sweet-0.042
idges-0.042
Token every
Token ID790
Feature activation-2.60e+00

Pos logit contributions
 ey+0.089
 honey+0.082
ad+0.079
 yogurt+0.079
 sweet+0.077
Neg logit contributions
gy-0.164
 bank-0.135
lves-0.130
 drown-0.121
 station-0.118
Token
Token ID220
Feature activation-1.28e+00

Pos logit contributions
 ey+0.135
 honey+0.112
 yogurt+0.112
ad+0.110
idges+0.106
Neg logit contributions
gy-0.222
 bank-0.184
lves-0.164
zag-0.163
 drown-0.156
Token
Token ID198
Feature activation-5.44e-02

Pos logit contributions
gy+0.126
 bank+0.101
zag+0.090
lves+0.089
 drown+0.085
Neg logit contributions
 ey-0.089
 yogurt-0.073
 honey-0.072
idges-0.071
ad-0.071
Token
Token ID198
Feature activation-5.55e-02

Pos logit contributions
gy+0.005
 bank+0.004
zag+0.004
lves+0.004
 drown+0.003
Neg logit contributions
 ey-0.004
 yogurt-0.003
idges-0.003
 honey-0.003
ad-0.003
TokenT
Token ID51
Feature activation-2.32e+00

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
zag+0.004
 drown+0.004
Neg logit contributions
 ey-0.004
 honey-0.003
 yogurt-0.003
ad-0.003
idges-0.003
Tokenig
Token ID328
Feature activation-3.99e+00

Pos logit contributions
gy+0.252
 bank+0.209
lves+0.188
zag+0.186
 station+0.178
Neg logit contributions
 ey-0.132
 yogurt-0.106
 honey-0.104
idges-0.103
ad-0.101
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.298
 bank+0.239
lves+0.206
 drown+0.190
 station+0.186
Neg logit contributions
 ey-0.340
ad-0.302
 honey-0.298
 yogurt-0.297
idges-0.295
Token was
Token ID373
Feature activation+1.09e+00

Pos logit contributions
gy+1.512
 bank+1.223
lves+1.095
zag+1.068
 drown+1.036
Neg logit contributions
 ey-1.092
 yogurt-0.928
ad-0.926
 honey-0.923
idges-0.902
Token so
Token ID523
Feature activation+5.34e-01

Pos logit contributions
 ey+0.084
idges+0.070
 yogurt+0.069
 honey+0.067
ad+0.066
Neg logit contributions
gy-0.099
 bank-0.079
zag-0.068
lves-0.068
 drown-0.065
Token happy
Token ID3772
Feature activation+7.94e-01

Pos logit contributions
 ey+0.046
idges+0.039
 yogurt+0.038
 honey+0.038
ad+0.038
Neg logit contributions
gy-0.041
 bank-0.032
zag-0.028
 drown-0.028
 neither-0.027
Token and
Token ID290
Feature activation-4.31e-01

Pos logit contributions
 ey+0.069
idges+0.057
 yogurt+0.055
ad+0.054
 layers+0.053
Neg logit contributions
gy-0.065
 bank-0.050
zag-0.042
 neither-0.040
lves-0.040
Token the
Token ID262
Feature activation-5.80e-02

Pos logit contributions
gy+0.040
 bank+0.032
lves+0.028
zag+0.027
 neither+0.026
Neg logit contributions
 ey-0.032
idges-0.026
 yogurt-0.026
ad-0.026
 honey-0.025
Token day
Token ID1110
Feature activation-2.92e+00

Pos logit contributions
gy+0.473
 bank+0.415
lves+0.369
 drown+0.348
 argue+0.343
Neg logit contributions
 ey-0.373
 sweet-0.372
 honey-0.365
 yogurt-0.354
ad-0.340
Token,
Token ID11
Feature activation+2.42e-01

Pos logit contributions
gy+0.242
 bank+0.188
zag+0.159
lves+0.157
 neither+0.149
Neg logit contributions
 ey-0.244
idges-0.205
ad-0.204
 honey-0.202
 yogurt-0.202
Token a
Token ID257
Feature activation+1.69e-01

Pos logit contributions
 ey+0.017
idges+0.014
ad+0.013
 yogurt+0.013
 honey+0.013
Neg logit contributions
gy-0.024
 bank-0.019
lves-0.017
zag-0.017
 neither-0.016
Token little
Token ID1310
Feature activation+1.05e+00

Pos logit contributions
 ey+0.009
 honey+0.008
 sweet+0.008
 yogurt+0.008
idges+0.007
Neg logit contributions
gy-0.018
 bank-0.015
lves-0.014
zag-0.014
 drown-0.013
Token pig
Token ID12967
Feature activation-5.40e+00

Pos logit contributions
 honey+0.058
 sweet+0.056
 ey+0.056
 yogurt+0.050
ummy+0.045
Neg logit contributions
gy-0.105
 bank-0.089
zag-0.083
 drown-0.080
 drowned-0.080
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.420
 bank+0.411
lves+0.394
 drown+0.392
 argue+0.370
Neg logit contributions
ad-0.302
 ey-0.292
 yogurt-0.251
 sweet-0.239
 honey-0.233
Token named
Token ID3706
Feature activation-6.48e+00

Pos logit contributions
gy+1.458
 drown+1.246
lves+1.236
zag+1.226
 argue+1.190
Neg logit contributions
ad-0.749
 honey-0.687
 sweet-0.686
 ey-0.659
 yogurt-0.658
Token Pe
Token ID2631
Feature activation-2.75e+00

Pos logit contributions
gy+0.628
 bank+0.515
lves+0.453
zag+0.446
 drown+0.425
Neg logit contributions
 ey-0.446
 yogurt-0.373
 honey-0.370
ad-0.365
idges-0.364
Tokenppa
Token ID44989
Feature activation-3.78e+00

Pos logit contributions
gy+0.240
 bank+0.200
 drown+0.172
zag+0.167
lves+0.167
Neg logit contributions
 ey-0.189
idges-0.171
 honey-0.170
ad-0.168
 yogurt-0.164
Token went
Token ID1816
Feature activation-1.11e+00

Pos logit contributions
gy+0.336
 bank+0.296
lves+0.275
 drown+0.267
zag+0.262
Neg logit contributions
 ey-0.221
ad-0.206
 yogurt-0.199
 honey-0.195
 sweet-0.183
Token for
Token ID329
Feature activation-1.84e+00

Pos logit contributions
gy+0.111
 bank+0.092
lves+0.091
 neither+0.084
 drown+0.083
Neg logit contributions
 ey-0.059
 honey-0.057
 yogurt-0.054
 sweet-0.050
ad-0.049
Token that
Token ID326
Feature activation-8.72e-01

Pos logit contributions
 ey+0.078
 yogurt+0.065
idges+0.064
 honey+0.063
 layers+0.061
Neg logit contributions
gy-0.083
 bank-0.065
lves-0.057
zag-0.054
 station-0.053
Token day
Token ID1110
Feature activation-2.92e+00

Pos logit contributions
gy+0.071
 bank+0.057
lves+0.050
 drown+0.046
zag+0.045
Neg logit contributions
 ey-0.071
 honey-0.063
ad-0.063
 yogurt-0.062
 sweet-0.062
Token on
Token ID319
Feature activation-1.11e+00

Pos logit contributions
gy+0.275
 bank+0.242
lves+0.205
 drown+0.196
 station+0.190
Neg logit contributions
 ey-0.184
ad-0.171
idges-0.164
 honey-0.161
 importantly-0.157
Token,
Token ID11
Feature activation+2.42e-01

Pos logit contributions
gy+0.103
 bank+0.084
lves+0.075
zag+0.072
 drown+0.070
Neg logit contributions
 ey-0.079
 honey-0.067
 yogurt-0.066
ad-0.066
idges-0.065
Token Mag
Token ID2944
Feature activation-5.23e+00

Pos logit contributions
 ey+0.014
ad+0.014
 sweet+0.014
 honey+0.013
idges+0.013
Neg logit contributions
gy-0.022
 bank-0.019
 drown-0.016
 argue-0.016
zag-0.016
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.035
 bank+0.028
 drown-0.039
 argue-0.045
 neither-0.052
Neg logit contributions
 ey-0.748
ad-0.702
idges-0.685
ummy-0.661
ement-0.656
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
gy+1.515
 bank+1.246
lves+1.174
 drown+1.113
zag+1.101
Neg logit contributions
 ey-0.958
ad-0.892
 honey-0.843
 yogurt-0.840
 sweet-0.815
Token never
Token ID1239
Feature activation-4.90e+00

Pos logit contributions
 ey+0.085
 honey+0.076
ad+0.076
 yogurt+0.075
idges+0.074
Neg logit contributions
gy-0.090
 bank-0.072
lves-0.062
zag-0.060
 drown-0.057
Token fearful
Token ID26844
Feature activation-4.69e+00

Pos logit contributions
gy+0.420
 bank+0.342
zag+0.296
lves+0.291
 station+0.275
Neg logit contributions
 ey-0.375
 honey-0.331
 yogurt-0.329
ad-0.321
 sweet-0.314
Token of
Token ID286
Feature activation+2.76e+00

Pos logit contributions
gy+0.427
 bank+0.344
lves+0.302
zag+0.295
 drown+0.286
Neg logit contributions
 ey-0.346
 yogurt-0.283
idges-0.282
ad-0.278
 honey-0.277
Token boards
Token ID11490
Feature activation+9.65e-02

Pos logit contributions
 ey+0.194
idges+0.159
 yogurt+0.157
ad+0.155
 honey+0.151
Neg logit contributions
gy-0.258
 bank-0.212
lves-0.184
zag-0.179
 drown-0.176
Token together
Token ID1978
Feature activation-3.59e+00

Pos logit contributions
gy+0.015
 bank+0.011
lves+0.009
zag+0.009
 station+0.008
Neg logit contributions
 ey-0.021
 yogurt-0.018
 honey-0.018
idges-0.018
ad-0.018
Token all
Token ID477
Feature activation-3.96e+00

Pos logit contributions
gy+0.352
 bank+0.278
lves+0.274
 drown+0.250
zag+0.243
Neg logit contributions
 ey-0.217
 honey-0.201
 yogurt-0.200
ad-0.195
 sweet-0.188
Token day
Token ID1110
Feature activation-2.92e+00

Pos logit contributions
gy+0.320
 bank+0.268
lves+0.228
 drown+0.223
zag+0.215
Neg logit contributions
 ey-0.308
ad-0.280
 honey-0.274
 yogurt-0.268
 sweet-0.266
Token.
Token ID13
Feature activation+8.16e-02

Pos logit contributions
gy+0.314
lves+0.254
 bank+0.251
 drown+0.238
 station+0.236
Neg logit contributions
 sweet-0.124
 ey-0.121
 honey-0.115
 yogurt-0.114
ummy-0.109
Token Bug
Token ID15217
Feature activation-3.34e+00

Pos logit contributions
 ey+0.004
 honey+0.004
ad+0.004
 yogurt+0.004
 sweet+0.004
Neg logit contributions
gy-0.008
 bank-0.007
zag-0.006
lves-0.006
 argue-0.006
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.040
 bank+0.017
lves-0.016
 drown-0.017
 station-0.026
Neg logit contributions
 ey-0.450
 honey-0.432
ad-0.432
 sweet-0.426
idges-0.416
Token learned
Token ID4499
Feature activation-2.34e+00

Pos logit contributions
gy+1.530
 bank+1.245
lves+1.188
 drown+1.133
zag+1.120
Neg logit contributions
 ey-0.911
ad-0.871
 honey-0.849
 sweet-0.829
 yogurt-0.825
Token that
Token ID326
Feature activation-8.81e-01

Pos logit contributions
gy+0.203
 bank+0.164
zag+0.139
lves+0.138
 station+0.129
Neg logit contributions
 ey-0.188
 yogurt-0.153
idges-0.152
ad-0.148
 honey-0.148
Token being
Token ID852
Feature activation+1.97e+00

Pos logit contributions
gy+0.081
 bank+0.065
lves+0.057
zag+0.056
 station+0.053
Neg logit contributions
 ey-0.065
 yogurt-0.055
 honey-0.054
idges-0.054
ad-0.054
Token loyal
Token ID9112
Feature activation-8.71e-01

Pos logit contributions
 ey+0.112
 honey+0.090
 yogurt+0.090
idges+0.088
ad+0.087
Neg logit contributions
gy-0.213
 bank-0.180
lves-0.159
zag-0.158
 station-0.152
Token is
Token ID318
Feature activation+1.65e+00

Pos logit contributions
gy+0.081
 bank+0.067
lves+0.059
zag+0.058
 drown+0.055
Neg logit contributions
 ey-0.061
 honey-0.052
 yogurt-0.051
ad-0.050
idges-0.050
Token body
Token ID1767
Feature activation-1.01e+00

Pos logit contributions
gy+0.043
lves+0.035
 bank+0.034
zag+0.031
 drown+0.030
Neg logit contributions
 ey-0.039
 honey-0.035
 sweet-0.034
 yogurt-0.034
ad-0.032
Token and
Token ID290
Feature activation-4.30e-01

Pos logit contributions
gy+0.103
 bank+0.086
lves+0.084
 drown+0.079
 argue+0.076
Neg logit contributions
 ey-0.055
 yogurt-0.047
ad-0.046
 honey-0.044
 sweet-0.044
Token a
Token ID257
Feature activation+1.66e-01

Pos logit contributions
gy+0.037
 bank+0.029
zag+0.025
lves+0.023
 neither+0.023
Neg logit contributions
 ey-0.035
idges-0.030
ement-0.029
ad-0.029
 yogurt-0.028
Token w
Token ID266
Feature activation+1.51e+00

Pos logit contributions
 ey+0.011
 honey+0.009
 yogurt+0.009
 sweet+0.009
ad+0.008
Neg logit contributions
gy-0.016
 bank-0.013
lves-0.012
zag-0.011
 drown-0.011
Tokenag
Token ID363
Feature activation-1.19e+00

Pos logit contributions
 ey+0.095
 yogurt+0.079
 honey+0.078
idges+0.075
ad+0.074
Neg logit contributions
gy-0.152
 bank-0.125
zag-0.112
lves-0.112
 drown-0.106
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.085
 bank+0.078
lves+0.067
 drown+0.062
 station+0.061
Neg logit contributions
 ey-0.095
ad-0.089
 yogurt-0.079
 honey-0.079
idges-0.079
Token tail
Token ID7894
Feature activation-2.81e+00

Pos logit contributions
gy+1.253
lves+0.999
 drown+0.944
 neither+0.903
 bank+0.891
Neg logit contributions
 ey-1.180
 honey-1.092
 yogurt-1.085
 sweet-1.053
ad-1.008
Token.
Token ID13
Feature activation+7.72e-02

Pos logit contributions
gy+0.281
 bank+0.229
lves+0.213
zag+0.200
 drown+0.198
Neg logit contributions
 ey-0.173
 yogurt-0.148
ad-0.146
 honey-0.145
idges-0.138
Token One
Token ID1881
Feature activation-5.54e+00

Pos logit contributions
 ey+0.007
idges+0.006
 honey+0.006
ad+0.006
illy+0.006
Neg logit contributions
gy-0.006
 bank-0.005
 station-0.004
zag-0.003
house-0.003
Token day
Token ID1110
Feature activation-2.92e+00

Pos logit contributions
gy+0.436
 bank+0.354
lves+0.304
zag+0.275
 drown+0.275
Neg logit contributions
 ey-0.469
 yogurt-0.421
 honey-0.417
ad-0.408
 sweet-0.404
Token,
Token ID11
Feature activation+2.44e-01

Pos logit contributions
gy+0.240
 bank+0.184
zag+0.156
lves+0.153
 neither+0.147
Neg logit contributions
 ey-0.248
idges-0.210
ad-0.208
 honey-0.207
 yogurt-0.205
Token was
Token ID373
Feature activation+1.11e+00

Pos logit contributions
gy+0.371
 bank+0.257
zag+0.213
lves+0.209
 station+0.184
Neg logit contributions
 ey-0.518
 yogurt-0.457
idges-0.443
 honey-0.438
ad-0.438
Token happy
Token ID3772
Feature activation+7.98e-01

Pos logit contributions
 ey+0.081
 yogurt+0.067
idges+0.067
 honey+0.066
ad+0.065
Neg logit contributions
gy-0.104
 bank-0.084
lves-0.073
zag-0.072
 station-0.069
Token to
Token ID284
Feature activation+4.81e-01

Pos logit contributions
 ey+0.075
idges+0.062
 yogurt+0.061
ad+0.060
 layers+0.059
Neg logit contributions
gy-0.061
 bank-0.044
 neither-0.036
lves-0.036
zag-0.036
Token see
Token ID766
Feature activation+7.86e-01

Pos logit contributions
 ey+0.035
ad+0.032
 honey+0.030
 yogurt+0.030
 sweet+0.029
Neg logit contributions
gy-0.042
 bank-0.035
lves-0.032
zag-0.029
 station-0.028
Token Bug
Token ID15217
Feature activation-3.33e+00

Pos logit contributions
 ey+0.068
 yogurt+0.055
ad+0.053
idges+0.053
 subtract+0.052
Neg logit contributions
gy-0.066
 bank-0.051
lves-0.047
 neither-0.040
 drown-0.040
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.012
 bank-0.013
lves-0.041
 drown-0.051
zag-0.056
Neg logit contributions
 ey-0.472
 honey-0.461
ad-0.456
 sweet-0.454
 yogurt-0.443
Token and
Token ID290
Feature activation-4.34e-01

Pos logit contributions
gy+1.434
 bank+1.134
lves+1.029
zag+0.994
 drown+0.939
Neg logit contributions
 ey-1.173
 yogurt-1.015
 honey-1.013
ad-0.995
idges-0.978
Token they
Token ID484
Feature activation-7.28e+00

Pos logit contributions
gy+0.041
 bank+0.033
lves+0.029
zag+0.029
 station+0.028
Neg logit contributions
 ey-0.030
 honey-0.026
 yogurt-0.025
ad-0.025
idges-0.025
Token played
Token ID2826
Feature activation-2.14e-01

Pos logit contributions
gy+0.666
 bank+0.559
zag+0.504
 drown+0.496
lves+0.492
Neg logit contributions
 ey-0.427
ad-0.425
 honey-0.413
 sweet-0.401
 yogurt-0.380
Token together
Token ID1978
Feature activation-3.59e+00

Pos logit contributions
gy+0.015
 bank+0.011
lves+0.009
zag+0.009
 station+0.008
Neg logit contributions
 ey-0.021
 yogurt-0.018
 honey-0.018
idges-0.018
ad-0.018
Token all
Token ID477
Feature activation-3.96e+00

Pos logit contributions
gy+0.352
 bank+0.278
lves+0.274
 drown+0.250
zag+0.243
Neg logit contributions
 ey-0.217
 honey-0.201
 yogurt-0.200
ad-0.195
 sweet-0.188
Token what
Token ID644
Feature activation+5.14e+00

Pos logit contributions
 ey+0.053
 yogurt+0.040
ad+0.038
idges+0.037
ement+0.037
Neg logit contributions
gy-0.085
 bank-0.068
lves-0.063
 drown-0.059
 neither-0.058
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
 ey+0.428
idges+0.347
 yogurt+0.344
 honey+0.344
ad+0.339
Neg logit contributions
gy-0.443
 bank-0.340
zag-0.291
lves-0.290
 neither-0.283
Token wrong
Token ID2642
Feature activation-8.79e-01

Pos logit contributions
 ey+0.089
 yogurt+0.076
 honey+0.076
idges+0.075
ad+0.075
Neg logit contributions
gy-0.094
 bank-0.074
lves-0.064
zag-0.063
 station-0.059
Token.
Token ID13
Feature activation+8.53e-02

Pos logit contributions
gy+0.087
 bank+0.073
lves+0.067
zag+0.063
 drown+0.061
Neg logit contributions
 ey-0.055
 honey-0.047
 yogurt-0.047
ad-0.046
idges-0.044
Token Bug
Token ID15217
Feature activation-3.33e+00

Pos logit contributions
 ey+0.005
 honey+0.005
 sweet+0.005
idges+0.005
 yogurt+0.004
Neg logit contributions
gy-0.008
 bank-0.006
zag-0.006
lves-0.006
 station-0.005
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.025
 bank+0.008
lves-0.018
 drown-0.023
 station-0.032
Neg logit contributions
 ey-0.449
ad-0.435
 honey-0.431
 sweet-0.426
idges-0.415
Token told
Token ID1297
Feature activation-3.61e+00

Pos logit contributions
gy+1.480
 bank+1.174
lves+1.096
zag+1.073
 drown+1.039
Neg logit contributions
 ey-1.052
ad-0.944
 honey-0.941
 yogurt-0.931
idges-0.898
Token them
Token ID606
Feature activation-9.40e-01

Pos logit contributions
gy+0.385
 bank+0.318
lves+0.281
zag+0.272
 drown+0.269
Neg logit contributions
 ey-0.225
 yogurt-0.180
idges-0.172
ad-0.166
 honey-0.164
Token about
Token ID546
Feature activation+4.46e+00

Pos logit contributions
gy+0.089
 bank+0.072
lves+0.062
zag+0.061
 drown+0.059
Neg logit contributions
 ey-0.067
 yogurt-0.055
ad-0.054
idges-0.054
 honey-0.053
Token the
Token ID262
Feature activation-6.13e-02

Pos logit contributions
 ey+0.306
ad+0.240
idges+0.239
 yogurt+0.233
ement+0.230
Neg logit contributions
gy-0.442
 bank-0.364
lves-0.312
 drown-0.305
 neither-0.303
Token cart
Token ID6383
Feature activation-4.62e+00

Pos logit contributions
gy+0.006
 bank+0.004
lves+0.004
zag+0.004
 station+0.004
Neg logit contributions
 ey-0.005
 yogurt-0.004
 honey-0.004
idges-0.004
ad-0.004
Token Tim
Token ID5045
Feature activation-3.99e-01

Pos logit contributions
 ey+0.008
idges+0.007
 honey+0.007
ad+0.006
 yogurt+0.006
Neg logit contributions
gy-0.008
 bank-0.006
zag-0.005
house-0.005
 station-0.005
Tokenmy
Token ID1820
Feature activation+2.99e+00

Pos logit contributions
gy+0.040
 bank+0.031
lves+0.027
zag+0.027
 station+0.026
Neg logit contributions
 ey-0.028
idges-0.024
 honey-0.023
 yogurt-0.022
ad-0.022
Token had
Token ID550
Feature activation-1.04e+00

Pos logit contributions
 ey+0.174
 yogurt+0.149
ad+0.145
 sweet+0.140
 honey+0.136
Neg logit contributions
gy-0.296
 bank-0.258
lves-0.236
 drown-0.226
zag-0.225
Token a
Token ID257
Feature activation+1.76e-01

Pos logit contributions
gy+0.104
 bank+0.085
lves+0.075
zag+0.073
 station+0.070
Neg logit contributions
 ey-0.070
idges-0.057
 honey-0.056
 yogurt-0.055
ad-0.055
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
 ey+0.012
 yogurt+0.010
 honey+0.010
 sweet+0.010
 pasta+0.009
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.013
zag-0.012
 drown-0.012
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.281
 drown+0.269
 bank+0.260
lves+0.250
 argue+0.233
Neg logit contributions
ad-0.438
 ey-0.427
 sweet-0.425
 yogurt-0.417
 honey-0.401
Token bank
Token ID3331
Feature activation-1.24e+01

Pos logit contributions
gy+1.038
lves+0.824
 drown+0.751
 bank+0.716
zag+0.705
Neg logit contributions
 ey-1.346
 yogurt-1.310
 honey-1.300
 sweet-1.253
ad-1.221
Token that
Token ID326
Feature activation-8.77e-01

Pos logit contributions
gy+1.194
 bank+0.985
lves+0.848
zag+0.841
 station+0.806
Neg logit contributions
 ey-0.873
 honey-0.713
idges-0.710
 yogurt-0.708
ad-0.697
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
gy+0.093
 bank+0.078
lves+0.071
zag+0.070
 drown+0.067
Neg logit contributions
 ey-0.050
 yogurt-0.042
 honey-0.041
ad-0.040
idges-0.039
Token full
Token ID1336
Feature activation+1.71e+00

Pos logit contributions
 ey+0.080
 yogurt+0.070
 honey+0.069
ad+0.067
idges+0.066
Neg logit contributions
gy-0.100
 bank-0.081
lves-0.072
zag-0.071
 drown-0.067
Token of
Token ID286
Feature activation+2.76e+00

Pos logit contributions
 ey+0.122
idges+0.095
ad+0.090
Jamie+0.088
 yogurt+0.086
Neg logit contributions
gy-0.161
 bank-0.141
 station-0.120
zag-0.111
lves-0.110
Token hurt
Token ID5938
Feature activation-4.94e+00

Pos logit contributions
gy+0.036
 bank+0.028
zag+0.027
 station+0.026
lves+0.025
Neg logit contributions
 honey-0.031
 sweet-0.030
 yogurt-0.030
 ey-0.030
ad-0.027
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
gy+0.558
 bank+0.467
lves+0.420
zag+0.414
 drown+0.398
Neg logit contributions
 ey-0.268
 yogurt-0.208
idges-0.204
 honey-0.203
ad-0.198
Token knee
Token ID10329
Feature activation-7.69e-01

Pos logit contributions
 ey+0.070
 honey+0.063
 yogurt+0.062
 sweet+0.061
ad+0.058
Neg logit contributions
gy-0.092
 bank-0.075
lves-0.073
zag-0.067
 station-0.065
Token.
Token ID13
Feature activation+8.08e-02

Pos logit contributions
gy+0.081
 bank+0.067
lves+0.066
 station+0.061
zag+0.060
Neg logit contributions
 ey-0.035
 sweet-0.035
 honey-0.034
 yogurt-0.032
ad-0.031
Token Dog
Token ID8532
Feature activation-5.04e+00

Pos logit contributions
 ey+0.005
 yogurt+0.004
 honey+0.004
ad+0.004
idges+0.004
Neg logit contributions
gy-0.008
 bank-0.007
lves-0.006
zag-0.006
 drown-0.006
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.012
 bank-0.009
 drown-0.057
lves-0.061
 station-0.078
Neg logit contributions
 ey-0.696
ad-0.687
 honey-0.677
 sweet-0.676
idges-0.651
Token helped
Token ID4193
Feature activation+2.06e+00

Pos logit contributions
gy+1.539
 bank+1.213
lves+1.180
zag+1.165
 station+1.093
Neg logit contributions
 ey-0.927
 honey-0.885
 yogurt-0.865
ad-0.850
 sweet-0.847
Token Kitty
Token ID21168
Feature activation-3.30e+00

Pos logit contributions
 ey+0.088
 honey+0.083
ad+0.081
 sweet+0.075
idges+0.071
Neg logit contributions
gy-0.226
 bank-0.201
lves-0.183
zag-0.181
 drown-0.175
Token stand
Token ID1302
Feature activation+3.06e+00

Pos logit contributions
gy+0.268
 bank+0.212
lves+0.199
zag+0.183
 station+0.177
Neg logit contributions
 ey-0.250
 honey-0.231
 yogurt-0.226
ad-0.222
 sweet-0.218
Token up
Token ID510
Feature activation-2.41e-01

Pos logit contributions
 ey+0.208
 honey+0.184
 yogurt+0.183
ad+0.172
 sweet+0.172
Neg logit contributions
gy-0.285
 bank-0.236
lves-0.214
zag-0.203
 station-0.200
Token and
Token ID290
Feature activation-4.29e-01

Pos logit contributions
gy+0.023
 bank+0.019
lves+0.016
zag+0.016
 drown+0.015
Neg logit contributions
 ey-0.017
 yogurt-0.014
 honey-0.014
ad-0.014
idges-0.014
TokenAfter
Token ID3260
Feature activation+1.84e+00

Pos logit contributions
gy+0.005
 bank+0.004
zag+0.004
lves+0.004
 station+0.004
Neg logit contributions
 ey-0.003
idges-0.002
 honey-0.002
 yogurt-0.002
ad-0.002
Token a
Token ID257
Feature activation+1.61e-01

Pos logit contributions
 ey+0.117
 yogurt+0.096
 honey+0.095
idges+0.094
ad+0.094
Neg logit contributions
gy-0.186
 bank-0.154
lves-0.137
zag-0.135
 station-0.129
Token while
Token ID981
Feature activation-2.07e+00

Pos logit contributions
 ey+0.012
 honey+0.012
 sweet+0.012
 yogurt+0.011
idges+0.010
Neg logit contributions
gy-0.014
 bank-0.011
lves-0.009
zag-0.009
 drown-0.009
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
gy+0.215
 bank+0.182
lves+0.168
zag+0.165
 station+0.156
Neg logit contributions
 ey-0.109
 honey-0.104
 sweet-0.096
ad-0.095
 yogurt-0.094
Token Bug
Token ID15217
Feature activation-3.34e+00

Pos logit contributions
 honey+0.015
 sweet+0.014
 ey+0.014
 yogurt+0.013
 goodness+0.013
Neg logit contributions
gy-0.022
 bank-0.018
zag-0.018
 station-0.016
lves-0.016
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.010
 bank-0.000
lves-0.028
 argue-0.032
 drown-0.032
Neg logit contributions
 ey-0.447
ad-0.441
 honey-0.435
 sweet-0.434
 himself-0.416
Token was
Token ID373
Feature activation+1.11e+00

Pos logit contributions
gy+1.478
 bank+1.158
lves+1.127
 drown+1.105
zag+1.075
Neg logit contributions
ad-0.929
 ey-0.919
 honey-0.854
 yogurt-0.844
 sweet-0.836
Token tired
Token ID10032
Feature activation-3.78e+00

Pos logit contributions
 ey+0.083
 yogurt+0.072
 honey+0.072
ad+0.072
idges+0.070
Neg logit contributions
gy-0.098
 bank-0.080
lves-0.070
zag-0.066
 station-0.064
Token and
Token ID290
Feature activation-4.23e-01

Pos logit contributions
gy+0.350
 bank+0.283
lves+0.248
zag+0.243
 drown+0.231
Neg logit contributions
 ey-0.275
 yogurt-0.232
 honey-0.231
ad-0.228
idges-0.227
Token wanted
Token ID2227
Feature activation-1.49e+00

Pos logit contributions
gy+0.036
 bank+0.028
lves+0.025
zag+0.025
 station+0.023
Neg logit contributions
 ey-0.033
 yogurt-0.029
 honey-0.029
ad-0.028
idges-0.028
Token to
Token ID284
Feature activation+4.98e-01

Pos logit contributions
gy+0.118
 bank+0.094
lves+0.074
zag+0.074
 drown+0.072
Neg logit contributions
 ey-0.134
idges-0.111
ad-0.109
 yogurt-0.107
 honey-0.106
Token Rob
Token ID3851
Feature activation-1.43e-01

Pos logit contributions
 ey+0.006
 yogurt+0.005
 honey+0.004
idges+0.004
ad+0.004
Neg logit contributions
gy-0.009
 bank-0.008
lves-0.007
zag-0.007
 station-0.007
Token pulled
Token ID5954
Feature activation-1.53e+00

Pos logit contributions
gy+0.013
 bank+0.010
 drown+0.010
lves+0.010
zag+0.009
Neg logit contributions
 ey-0.009
ad-0.009
 yogurt-0.008
 honey-0.008
 sweet-0.008
Token out
Token ID503
Feature activation-3.48e+00

Pos logit contributions
gy+0.142
 bank+0.116
lves+0.101
zag+0.099
 station+0.095
Neg logit contributions
 ey-0.111
 yogurt-0.092
idges-0.091
 honey-0.091
ad-0.090
Token his
Token ID465
Feature activation+9.02e-01

Pos logit contributions
gy+0.333
 bank+0.276
lves+0.232
zag+0.230
 station+0.228
Neg logit contributions
 ey-0.243
idges-0.197
 yogurt-0.194
 honey-0.192
ad-0.188
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
 ey+0.069
 yogurt+0.060
 honey+0.059
ad+0.057
 sweet+0.057
Neg logit contributions
gy-0.079
 bank-0.061
lves-0.056
zag-0.055
 drown-0.052
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.272
lves+0.206
 bank+0.192
 drown+0.191
zag+0.169
Neg logit contributions
 ey-0.510
 honey-0.480
ad-0.472
 yogurt-0.468
 sweet-0.465
Tokenbank
Token ID17796
Feature activation-9.09e+00

Pos logit contributions
gy+0.561
lves+0.254
zag+0.204
 bank+0.198
 drown+0.197
Neg logit contributions
 ey-1.933
 yogurt-1.831
 honey-1.817
 sweet-1.746
ad-1.745
Token and
Token ID290
Feature activation-4.20e-01

Pos logit contributions
gy+0.800
 bank+0.646
zag+0.536
lves+0.526
 station+0.513
Neg logit contributions
 ey-0.721
idges-0.597
 yogurt-0.593
 honey-0.587
ad-0.585
Token emptied
Token ID46705
Feature activation+6.48e-01

Pos logit contributions
gy+0.039
 bank+0.031
lves+0.029
zag+0.029
 drown+0.028
Neg logit contributions
 ey-0.027
 yogurt-0.025
 honey-0.025
ad-0.024
 sweet-0.023
Token it
Token ID340
Feature activation-8.80e-02

Pos logit contributions
 ey+0.041
 yogurt+0.034
 honey+0.034
ad+0.033
idges+0.033
Neg logit contributions
gy-0.066
 bank-0.054
lves-0.048
zag-0.047
 drown-0.045
Token on
Token ID319
Feature activation-1.10e+00

Pos logit contributions
gy+0.008
 bank+0.006
lves+0.005
zag+0.005
 drown+0.005
Neg logit contributions
 ey-0.007
 yogurt-0.006
 honey-0.006
ad-0.006
idges-0.006
Token and
Token ID290
Feature activation-4.26e-01

Pos logit contributions
 ey+0.134
 yogurt+0.110
 honey+0.108
ad+0.106
idges+0.104
Neg logit contributions
gy-0.214
 bank-0.173
lves-0.159
zag-0.154
 drown-0.150
Token Ben
Token ID3932
Feature activation+1.97e+00

Pos logit contributions
gy+0.044
 bank+0.036
lves+0.032
zag+0.031
 station+0.031
Neg logit contributions
 ey-0.027
idges-0.022
 honey-0.021
ad-0.021
 yogurt-0.021
Token get
Token ID651
Feature activation-3.51e+00

Pos logit contributions
 ey+0.149
 yogurt+0.128
 honey+0.126
ad+0.126
idges+0.123
Neg logit contributions
gy-0.177
 bank-0.137
lves-0.124
zag-0.123
 drown-0.112
Token their
Token ID511
Feature activation-5.52e+00

Pos logit contributions
gy+0.352
zag+0.280
 bank+0.267
lves+0.259
 drown+0.232
Neg logit contributions
 yogurt-0.216
 ey-0.214
 honey-0.202
 sweet-0.192
 pasta-0.191
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
gy+0.538
lves+0.402
zag+0.402
 bank+0.399
 drown+0.363
Neg logit contributions
 ey-0.368
 yogurt-0.342
 honey-0.315
 sweet-0.305
 pasta-0.297
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
lves+0.313
gy+0.291
 drown+0.283
nes+0.269
zag+0.266
Neg logit contributions
 sweet-0.376
 honey-0.370
 himself-0.369
 yogurt-0.365
ad-0.355
Token bank
Token ID3331
Feature activation-1.24e+01

Pos logit contributions
gy+0.582
lves+0.355
zag+0.271
 drown+0.230
 neither+0.189
Neg logit contributions
 ey-1.848
 yogurt-1.827
 honey-1.782
 cereal-1.745
 pasta-1.712
Token and
Token ID290
Feature activation-4.36e-01

Pos logit contributions
gy+1.151
 bank+0.942
lves+0.810
zag+0.800
 station+0.766
Neg logit contributions
 ey-0.905
 yogurt-0.754
 honey-0.751
idges-0.747
ad-0.742
Token put
Token ID1234
Feature activation+6.05e-01

Pos logit contributions
gy+0.039
zag+0.030
lves+0.030
 bank+0.029
 drown+0.025
Neg logit contributions
 ey-0.031
 yogurt-0.029
 honey-0.029
ad-0.026
 sweet-0.026
Token it
Token ID340
Feature activation-1.03e-01

Pos logit contributions
 ey+0.033
 yogurt+0.031
 honey+0.031
ad+0.028
 sweet+0.028
Neg logit contributions
gy-0.063
 bank-0.051
zag-0.049
lves-0.048
 drown-0.046
Token in
Token ID287
Feature activation+1.20e+00

Pos logit contributions
gy+0.010
 bank+0.008
lves+0.008
 drown+0.007
zag+0.007
Neg logit contributions
 ey-0.006
 yogurt-0.006
 honey-0.006
 sweet-0.005
 cereal-0.005
Token some
Token ID617
Feature activation-3.46e+00

Pos logit contributions
gy+0.107
 bank+0.088
lves+0.080
zag+0.078
 drown+0.075
Neg logit contributions
 ey-0.064
 yogurt-0.054
 honey-0.053
ad-0.052
idges-0.051
Token money
Token ID1637
Feature activation-2.95e+00

Pos logit contributions
gy+0.308
 bank+0.265
 station+0.223
zag+0.218
house+0.212
Neg logit contributions
 ey-0.241
idges-0.211
ad-0.207
mmmm-0.202
ango-0.200
Token from
Token ID422
Feature activation-1.49e+00

Pos logit contributions
gy+0.280
 bank+0.228
lves+0.210
zag+0.198
 drown+0.196
Neg logit contributions
 ey-0.196
 yogurt-0.173
 honey-0.169
ad-0.165
idges-0.163
Token their
Token ID511
Feature activation-5.52e+00

Pos logit contributions
gy+0.143
 bank+0.117
lves+0.105
zag+0.104
 drown+0.099
Neg logit contributions
 ey-0.101
 yogurt-0.088
 honey-0.086
ad-0.085
idges-0.082
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
gy+0.485
 bank+0.387
lves+0.338
zag+0.331
 drown+0.313
Neg logit contributions
 ey-0.427
 yogurt-0.365
 honey-0.362
ad-0.355
idges-0.354
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.126
 drown+0.114
lves+0.112
 bank+0.085
 neither+0.070
Neg logit contributions
 ey-0.566
 honey-0.563
 sweet-0.552
 yogurt-0.548
ad-0.544
Token bank
Token ID3331
Feature activation-1.24e+01

Pos logit contributions
gy+1.054
lves+0.786
 bank+0.715
 drown+0.708
zag+0.695
Neg logit contributions
 ey-1.400
 yogurt-1.318
 honey-1.304
ad-1.234
 cereal-1.227
Token.
Token ID13
Feature activation+7.82e-02

Pos logit contributions
gy+1.124
 bank+0.922
zag+0.776
lves+0.769
 station+0.747
Neg logit contributions
 ey-0.938
 yogurt-0.777
idges-0.776
 honey-0.775
ad-0.768
Token They
Token ID1119
Feature activation-3.91e+00

Pos logit contributions
 ey+0.005
 yogurt+0.004
 honey+0.004
idges+0.004
ad+0.004
Neg logit contributions
gy-0.008
 bank-0.007
lves-0.006
zag-0.006
 drown-0.006
Token asked
Token ID1965
Feature activation-9.14e-01

Pos logit contributions
gy+0.355
zag+0.283
 bank+0.277
lves+0.271
 drown+0.267
Neg logit contributions
 ey-0.244
 yogurt-0.235
ad-0.231
 honey-0.216
 sweet-0.212
Token their
Token ID511
Feature activation-5.51e+00

Pos logit contributions
gy+0.082
 bank+0.066
lves+0.056
zag+0.055
 station+0.053
Neg logit contributions
 ey-0.071
 yogurt-0.059
idges-0.058
 honey-0.058
ad-0.058
TokenOne
Token ID3198
Feature activation-3.35e+00

Pos logit contributions
gy+0.005
 bank+0.004
lves+0.004
zag+0.004
 drown+0.004
Neg logit contributions
 ey-0.004
 yogurt-0.004
ad-0.003
idges-0.003
 honey-0.003
Token day
Token ID1110
Feature activation-2.91e+00

Pos logit contributions
gy+0.288
 bank+0.247
lves+0.212
 drown+0.197
zag+0.192
Neg logit contributions
 ey-0.242
 honey-0.229
 sweet-0.226
 yogurt-0.223
ad-0.214
Token,
Token ID11
Feature activation+2.41e-01

Pos logit contributions
gy+0.267
 bank+0.217
lves+0.189
zag+0.185
 station+0.177
Neg logit contributions
 ey-0.214
 yogurt-0.183
 honey-0.182
idges-0.178
ad-0.178
Token the
Token ID262
Feature activation-6.13e-02

Pos logit contributions
 ey+0.014
 yogurt+0.012
 honey+0.012
idges+0.011
ad+0.011
Neg logit contributions
gy-0.026
 bank-0.022
zag-0.019
lves-0.019
 drown-0.019
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
gy+0.005
 bank+0.004
zag+0.004
lves+0.003
 drown+0.003
Neg logit contributions
 honey-0.005
 sweet-0.005
 ey-0.004
 yogurt-0.004
ad-0.004
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.412
lves+0.380
 drown+0.380
 bank+0.377
 argue+0.364
Neg logit contributions
ad-0.281
 ey-0.273
 honey-0.254
 yogurt-0.252
 sweet-0.251
Token decided
Token ID3066
Feature activation-1.28e+00

Pos logit contributions
gy+1.489
 drown+1.272
zag+1.255
 argue+1.237
lves+1.230
Neg logit contributions
 sweet-0.684
 honey-0.677
ad-0.672
 yogurt-0.617
 me-0.602
Token to
Token ID284
Feature activation+4.91e-01

Pos logit contributions
gy+0.112
 bank+0.090
lves+0.078
zag+0.076
 station+0.072
Neg logit contributions
 ey-0.100
 yogurt-0.085
 honey-0.084
idges-0.084
ad-0.084
Token take
Token ID1011
Feature activation-4.96e-01

Pos logit contributions
 ey+0.035
ad+0.033
 honey+0.031
 yogurt+0.031
 sweet+0.029
Neg logit contributions
gy-0.043
lves-0.034
 bank-0.033
zag-0.030
 neither-0.028
Token a
Token ID257
Feature activation+1.51e-01

Pos logit contributions
gy+0.054
 bank+0.045
lves+0.041
zag+0.040
 station+0.039
Neg logit contributions
 ey-0.028
 honey-0.024
 yogurt-0.023
ad-0.023
idges-0.022
Token stroll
Token ID41360
Feature activation-9.39e-02

Pos logit contributions
 ey+0.012
 honey+0.011
 yogurt+0.011
 sweet+0.011
 pasta+0.010
Neg logit contributions
gy-0.013
 bank-0.009
lves-0.009
 neither-0.008
zag-0.008
Token the
Token ID262
Feature activation-6.71e-02

Pos logit contributions
gy+0.038
 bank+0.030
lves+0.026
zag+0.026
 drown+0.024
Neg logit contributions
 ey-0.033
 yogurt-0.030
 honey-0.029
ad-0.028
idges-0.028
Token raced
Token ID32897
Feature activation-2.35e+00

Pos logit contributions
gy+0.005
 bank+0.004
lves+0.003
zag+0.003
 station+0.003
Neg logit contributions
 ey-0.006
idges-0.005
ad-0.005
 yogurt-0.005
 honey-0.005
Token the
Token ID262
Feature activation-6.70e-02

Pos logit contributions
gy+0.200
 bank+0.158
lves+0.137
zag+0.134
 drown+0.127
Neg logit contributions
 ey-0.188
 yogurt-0.163
 honey-0.161
ad-0.160
idges-0.159
Token s
Token ID264
Feature activation-1.09e+00

Pos logit contributions
gy+0.005
 bank+0.004
lves+0.003
zag+0.003
 drown+0.003
Neg logit contributions
 ey-0.006
 yogurt-0.005
 honey-0.005
ad-0.005
idges-0.005
Tokenog
Token ID519
Feature activation-3.50e+00

Pos logit contributions
gy+0.096
 bank+0.079
zag+0.071
 station+0.069
house+0.065
Neg logit contributions
 ey-0.077
 honey-0.069
 sweet-0.065
 yogurt-0.063
idges-0.061
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.181
 bank+0.138
lves+0.134
 drown+0.121
 neither+0.099
Neg logit contributions
 ey-0.321
ad-0.320
 yogurt-0.306
 honey-0.301
idges-0.296
Token race
Token ID3234
Feature activation-5.55e+00

Pos logit contributions
gy+0.865
lves+0.573
 drown+0.491
 neither+0.488
zag+0.461
Neg logit contributions
 ey-1.550
 yogurt-1.486
 honey-1.472
 sweet-1.409
 cereal-1.400
Token car
Token ID1097
Feature activation-6.99e+00

Pos logit contributions
gy+0.544
 bank+0.439
lves+0.419
 drown+0.387
zag+0.385
Neg logit contributions
 ey-0.338
ad-0.304
 yogurt-0.296
 honey-0.281
idges-0.279
Token around
Token ID1088
Feature activation-2.49e+00

Pos logit contributions
gy+0.708
 bank+0.584
lves+0.583
 drown+0.548
 drowned+0.513
Neg logit contributions
 ey-0.338
ad-0.332
 yogurt-0.308
 honey-0.292
 himself-0.292
Token the
Token ID262
Feature activation-8.00e-02

Pos logit contributions
gy+0.239
 bank+0.195
lves+0.165
zag+0.165
 station+0.161
Neg logit contributions
 ey-0.178
idges-0.146
 yogurt-0.145
 honey-0.145
ad-0.139
Token bowl
Token ID9396
Feature activation+3.44e+00

Pos logit contributions
gy+0.007
 bank+0.005
lves+0.005
zag+0.005
 station+0.004
Neg logit contributions
 ey-0.006
 yogurt-0.006
 honey-0.005
idges-0.005
ad-0.005
Token and
Token ID290
Feature activation-4.34e-01

Pos logit contributions
 ey+0.033
 honey+0.031
 yogurt+0.030
 sweet+0.029
ad+0.028
Neg logit contributions
gy-0.055
 bank-0.045
lves-0.044
 drown-0.040
zag-0.039
Token get
Token ID651
Feature activation-3.51e+00

Pos logit contributions
gy+0.037
 bank+0.029
lves+0.025
zag+0.024
 drown+0.023
Neg logit contributions
 ey-0.035
 yogurt-0.030
idges-0.030
ad-0.030
 honey-0.030
Token warm
Token ID5814
Feature activation+2.84e+00

Pos logit contributions
gy+0.308
 bank+0.248
lves+0.210
 drown+0.208
 neither+0.198
Neg logit contributions
 ey-0.278
idges-0.228
ad-0.227
 yogurt-0.218
ango-0.215
Token."
Token ID526
Feature activation-1.98e+00

Pos logit contributions
 ey+0.257
idges+0.216
ad+0.215
 yogurt+0.207
 subtract+0.200
Neg logit contributions
gy-0.225
 bank-0.173
 station-0.136
zag-0.135
lves-0.133
Token Dog
Token ID8532
Feature activation-5.04e+00

Pos logit contributions
gy+0.169
 bank+0.144
lves+0.133
zag+0.127
 drown+0.125
Neg logit contributions
 ey-0.126
 honey-0.115
ad-0.112
 sweet-0.109
 yogurt-0.105
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.032
 bank-0.015
lves-0.063
 drown-0.066
 station-0.085
Neg logit contributions
 ey-0.731
ad-0.698
 honey-0.691
 sweet-0.679
idges-0.677
Token agreed
Token ID4987
Feature activation-1.83e-02

Pos logit contributions
gy+1.505
 bank+1.215
lves+1.127
zag+1.086
 drown+1.058
Neg logit contributions
 ey-1.042
 honey-0.936
 yogurt-0.933
ad-0.915
 sweet-0.877
Token,
Token ID11
Feature activation+2.46e-01

Pos logit contributions
gy+0.002
 bank+0.001
zag+0.001
lves+0.001
 station+0.001
Neg logit contributions
 ey-0.001
idges-0.001
 yogurt-0.001
 honey-0.001
ad-0.001
Token and
Token ID290
Feature activation-4.36e-01

Pos logit contributions
 ey+0.017
 yogurt+0.014
 honey+0.014
ad+0.014
idges+0.014
Neg logit contributions
gy-0.023
 bank-0.019
lves-0.017
zag-0.016
 drown-0.016
Token they
Token ID484
Feature activation-7.30e+00

Pos logit contributions
gy+0.034
 bank+0.028
zag+0.026
 argue+0.025
lves+0.024
Neg logit contributions
 honey-0.033
 sweet-0.031
 yogurt-0.028
 ey-0.028
ad-0.028
Token both
Token ID1111
Feature activation-2.40e+00

Pos logit contributions
gy+0.643
 bank+0.516
lves+0.466
zag+0.462
 drown+0.431
Neg logit contributions
 ey-0.504
 honey-0.478
 yogurt-0.469
ad-0.461
 sweet-0.449
Token.
Token ID13
Feature activation+8.37e-02

Pos logit contributions
gy+0.595
lves+0.536
 bank+0.525
zag+0.496
 harbor+0.492
Neg logit contributions
 sweet-0.142
 honey-0.134
 yogurt-0.112
 himself-0.103
 him-0.090
Token
Token ID198
Feature activation-4.71e-02

Pos logit contributions
 ey+0.005
idges+0.005
ad+0.005
 yogurt+0.004
 honey+0.004
Neg logit contributions
gy-0.008
 bank-0.007
lves-0.006
 neither-0.006
zag-0.006
Token
Token ID198
Feature activation-5.55e-02

Pos logit contributions
gy+0.004
 bank+0.003
zag+0.003
lves+0.003
 drown+0.003
Neg logit contributions
 ey-0.003
 yogurt-0.003
 honey-0.003
idges-0.003
ad-0.003
Token"
Token ID1
Feature activation-1.35e+00

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
zag+0.004
 drown+0.004
Neg logit contributions
 ey-0.004
 yogurt-0.003
 honey-0.003
idges-0.003
ad-0.003
TokenDog
Token ID32942
Feature activation-8.17e+00

Pos logit contributions
gy+0.150
 bank+0.125
lves+0.112
zag+0.112
 station+0.107
Neg logit contributions
 ey-0.076
 yogurt-0.061
 honey-0.060
ad-0.059
idges-0.059
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.667
 bank+0.567
lves+0.502
zag+0.470
 drown+0.460
Neg logit contributions
 ey-0.607
ad-0.550
 honey-0.540
 yogurt-0.526
 sweet-0.515
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
gy+1.527
 bank+1.243
lves+1.139
zag+1.109
 drown+1.057
Neg logit contributions
 ey-1.041
 honey-0.905
ad-0.894
 yogurt-0.893
idges-0.853
Token you
Token ID345
Feature activation+2.54e+00

Pos logit contributions
 ey+0.016
 honey+0.014
 yogurt+0.013
ad+0.013
idges+0.013
Neg logit contributions
gy-0.024
 bank-0.020
lves-0.017
zag-0.017
 station-0.016
Token are
Token ID389
Feature activation+2.01e-01

Pos logit contributions
 ey+0.153
 honey+0.135
 yogurt+0.132
 sweet+0.131
ad+0.129
Neg logit contributions
gy-0.258
 bank-0.214
zag-0.193
lves-0.187
 station-0.183
Token a
Token ID257
Feature activation+1.78e-01

Pos logit contributions
 ey+0.014
 honey+0.012
 yogurt+0.012
ad+0.012
idges+0.012
Neg logit contributions
gy-0.019
 bank-0.016
zag-0.013
lves-0.013
 station-0.013
Token bad
Token ID2089
Feature activation-3.80e+00

Pos logit contributions
 sweet+0.010
 honey+0.009
 ey+0.008
 yogurt+0.008
 mirror+0.007
Neg logit contributions
gy-0.019
 bank-0.015
zag-0.014
 banks-0.014
lves-0.013
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
 ey+0.152
 yogurt+0.125
 honey+0.124
idges+0.123
ad+0.122
Neg logit contributions
gy-0.225
 bank-0.186
lves-0.164
zag-0.159
 station-0.153
Token penny
Token ID26369
Feature activation-2.84e+00

Pos logit contributions
 ey+0.084
 yogurt+0.072
 honey+0.072
idges+0.071
ad+0.071
Neg logit contributions
gy-0.084
 bank-0.066
lves-0.057
zag-0.055
 station-0.052
Token in
Token ID287
Feature activation+1.19e+00

Pos logit contributions
gy+0.241
 bank+0.191
lves+0.170
zag+0.163
 drown+0.162
Neg logit contributions
 ey-0.213
 yogurt-0.194
 honey-0.189
ad-0.186
idges-0.182
Token the
Token ID262
Feature activation-7.06e-02

Pos logit contributions
 ey+0.079
idges+0.066
 honey+0.061
 yogurt+0.061
ad+0.060
Neg logit contributions
gy-0.119
 bank-0.099
lves-0.084
zag-0.081
 station-0.080
Token pig
Token ID12967
Feature activation-5.39e+00

Pos logit contributions
gy+0.006
 bank+0.005
lves+0.004
zag+0.004
 station+0.004
Neg logit contributions
 ey-0.005
idges-0.005
 yogurt-0.005
 honey-0.004
ad-0.004
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.092
 bank+0.032
lves+0.029
 drown+0.027
 neither+0.002
Neg logit contributions
 ey-0.666
ad-0.653
 honey-0.634
 yogurt-0.633
 sweet-0.620
Token bank
Token ID3331
Feature activation-1.24e+01

Pos logit contributions
gy+0.448
lves+0.092
zag+0.066
 bank+0.055
 drown+0.037
Neg logit contributions
 ey-2.067
 yogurt-1.997
 honey-1.964
ad-1.896
 sweet-1.880
Token ever
Token ID1683
Feature activation-7.20e-01

Pos logit contributions
gy+1.098
 bank+0.914
lves+0.760
zag+0.757
 station+0.728
Neg logit contributions
 ey-0.955
idges-0.791
 honey-0.785
 yogurt-0.780
ad-0.774
Token again
Token ID757
Feature activation+5.27e-01

Pos logit contributions
gy+0.058
 bank+0.048
lves+0.038
zag+0.036
 argue+0.036
Neg logit contributions
 ey-0.062
idges-0.053
ad-0.051
 honey-0.050
 yogurt-0.050
Token.
Token ID13
Feature activation+9.44e-02

Pos logit contributions
 ey+0.034
 yogurt+0.029
 honey+0.029
ad+0.028
idges+0.028
Neg logit contributions
gy-0.052
 bank-0.042
lves-0.038
zag-0.037
 drown-0.036
Token She
Token ID1375
Feature activation+1.66e+00

Pos logit contributions
 ey+0.006
 honey+0.005
idges+0.005
 yogurt+0.005
ad+0.005
Neg logit contributions
gy-0.009
 bank-0.008
lves-0.007
zag-0.007
 station-0.006
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
gy+0.329
 bank+0.270
lves+0.236
zag+0.230
 drown+0.220
Neg logit contributions
 ey-0.262
 yogurt-0.224
 honey-0.224
ad-0.221
idges-0.219
Token a
Token ID257
Feature activation+1.67e-01

Pos logit contributions
 ey+0.014
 yogurt+0.012
 honey+0.012
ad+0.012
idges+0.011
Neg logit contributions
gy-0.025
 bank-0.021
lves-0.019
zag-0.019
 drown-0.018
Token dog
Token ID3290
Feature activation-5.02e+00

Pos logit contributions
 ey+0.010
 honey+0.009
 yogurt+0.009
 sweet+0.009
ad+0.008
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.012
zag-0.012
 drown-0.012
Token named
Token ID3706
Feature activation-6.49e+00

Pos logit contributions
gy+0.332
 bank+0.270
lves+0.223
zag+0.208
 drown+0.197
Neg logit contributions
 ey-0.454
ad-0.424
 honey-0.420
 yogurt-0.416
idges-0.406
Token Dog
Token ID8532
Feature activation-5.05e+00

Pos logit contributions
gy+0.598
 bank+0.487
lves+0.424
zag+0.417
 drown+0.397
Neg logit contributions
 ey-0.470
 yogurt-0.396
 honey-0.394
ad-0.389
idges-0.389
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.205
 bank+0.189
lves+0.147
 drown+0.134
zag+0.119
Neg logit contributions
ad-0.502
 ey-0.499
 honey-0.485
 sweet-0.472
idges-0.458
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
gy+1.544
lves+1.273
 bank+1.265
zag+1.205
 drown+1.171
Neg logit contributions
 ey-0.895
ad-0.818
 yogurt-0.779
 honey-0.778
 sweet-0.731
Token came
Token ID1625
Feature activation+5.04e-02

Pos logit contributions
 ey+0.022
 yogurt+0.019
idges+0.019
ad+0.019
 honey+0.019
Neg logit contributions
gy-0.019
 bank-0.014
lves-0.012
zag-0.011
 station-0.011
Token to
Token ID284
Feature activation+4.87e-01

Pos logit contributions
 ey+0.003
 honey+0.003
ad+0.003
 sweet+0.002
idges+0.002
Neg logit contributions
gy-0.005
 bank-0.004
lves-0.004
 drown-0.004
 sank-0.004
Token play
Token ID711
Feature activation+9.92e-01

Pos logit contributions
 ey+0.036
 yogurt+0.030
 honey+0.030
ad+0.029
idges+0.029
Neg logit contributions
gy-0.045
 bank-0.036
lves-0.032
zag-0.031
 station-0.030
Token with
Token ID351
Feature activation-1.51e-01

Pos logit contributions
 ey+0.054
 yogurt+0.048
 honey+0.047
ad+0.047
 sweet+0.046
Neg logit contributions
gy-0.105
 bank-0.086
lves-0.080
zag-0.079
 drown-0.075
Token met
Token ID1138
Feature activation-4.95e+00

Pos logit contributions
gy+0.265
 bank+0.207
lves+0.180
zag+0.179
 drown+0.170
Neg logit contributions
 ey-0.269
 yogurt-0.236
 honey-0.235
ad-0.232
idges-0.227
Token a
Token ID257
Feature activation+1.64e-01

Pos logit contributions
gy+0.434
 bank+0.326
lves+0.279
zag+0.277
house+0.272
Neg logit contributions
 ey-0.424
idges-0.334
 yogurt-0.324
 layers-0.314
ad-0.314
Token dog
Token ID3290
Feature activation-5.02e+00

Pos logit contributions
 ey+0.010
 yogurt+0.008
ad+0.008
idges+0.008
 honey+0.008
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.012
zag-0.012
 station-0.012
Token named
Token ID3706
Feature activation-6.49e+00

Pos logit contributions
gy+0.399
 bank+0.321
lves+0.283
zag+0.272
 drown+0.266
Neg logit contributions
 ey-0.379
 honey-0.356
ad-0.355
 yogurt-0.353
idges-0.334
Token Dog
Token ID8532
Feature activation-5.04e+00

Pos logit contributions
gy+0.581
 bank+0.457
lves+0.401
zag+0.387
 station+0.371
Neg logit contributions
 ey-0.505
 yogurt-0.420
idges-0.418
ad-0.412
 honey-0.411
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.338
 bank+0.304
 drown+0.264
lves+0.261
zag+0.248
Neg logit contributions
ad-0.368
 ey-0.367
 honey-0.358
 sweet-0.348
 himself-0.333
Token.
Token ID13
Feature activation+8.26e-02

Pos logit contributions
gy+1.490
 bank+1.190
lves+1.122
zag+1.089
 drown+1.062
Neg logit contributions
 ey-1.053
 honey-0.921
 yogurt-0.920
ad-0.904
idges-0.856
Token Dog
Token ID8532
Feature activation-5.05e+00

Pos logit contributions
 ey+0.007
 honey+0.006
ad+0.006
 yogurt+0.006
idges+0.006
Neg logit contributions
gy-0.006
 bank-0.005
lves-0.004
zag-0.004
 drown-0.004
Tokengy
Token ID1360
Feature activation-1.60e+01

Pos logit contributions
gy+0.025
 bank-0.024
 drown-0.075
lves-0.077
zag-0.089
Neg logit contributions
 ey-0.738
ad-0.705
 honey-0.697
 sweet-0.689
idges-0.688
Token was
Token ID373
Feature activation+1.09e+00

Pos logit contributions
gy+1.528
 bank+1.241
lves+1.147
zag+1.117
 drown+1.111
Neg logit contributions
 ey-0.999
ad-0.879
 honey-0.870
 yogurt-0.868
idges-0.837
Token very
Token ID845
Feature activation-8.44e-01

Pos logit contributions
 ey+0.068
 honey+0.057
 yogurt+0.057
ad+0.056
idges+0.055
Neg logit contributions
gy-0.110
 bank-0.093
lves-0.082
zag-0.080
 drown-0.077
Token She
Token ID1375
Feature activation+1.73e+00

Pos logit contributions
 ey+0.013
idges+0.012
ad+0.012
 honey+0.011
ement+0.011
Neg logit contributions
gy-0.012
 bank-0.009
 neither-0.008
zag-0.008
lves-0.007
Token says
Token ID1139
Feature activation+8.19e-01

Pos logit contributions
 ey+0.126
idges+0.107
 yogurt+0.106
ad+0.106
 honey+0.105
Neg logit contributions
gy-0.155
 bank-0.129
lves-0.109
zag-0.107
 station-0.105
Token to
Token ID284
Feature activation+5.78e-01

Pos logit contributions
 ey+0.076
idges+0.064
ad+0.063
 layers+0.063
ango+0.061
Neg logit contributions
gy-0.052
 bank-0.042
 neither-0.038
zag-0.034
 argue-0.032
Token the
Token ID262
Feature activation+2.10e-02

Pos logit contributions
 ey+0.046
 importantly+0.041
idges+0.040
 layers+0.040
ement+0.039
Neg logit contributions
gy-0.045
 bank-0.035
 neither-0.030
 fight-0.029
 drown-0.029
Token ice
Token ID4771
Feature activation+4.70e+00

Pos logit contributions
 ey+0.002
idges+0.002
ad+0.001
 honey+0.001
ango+0.001
Neg logit contributions
gy-0.002
 bank-0.001
 station-0.001
zag-0.001
 drown-0.001
Token cream
Token ID8566
Feature activation+7.49e+00

Pos logit contributions
 ey+0.195
idges+0.137
 honey+0.135
ad+0.133
 yogurt+0.133
Neg logit contributions
gy-0.583
 bank-0.504
zag-0.453
lves-0.451
 station-0.438
Token man
Token ID582
Feature activation-1.57e+00

Pos logit contributions
 ey+0.605
idges+0.518
 honey+0.497
ad+0.492
 yogurt+0.488
Neg logit contributions
gy-0.630
 bank-0.527
zag-0.429
 station-0.427
lves-0.416
Token,
Token ID11
Feature activation+3.46e-01

Pos logit contributions
gy+0.142
 bank+0.113
zag+0.097
lves+0.097
 station+0.093
Neg logit contributions
 ey-0.120
idges-0.099
 yogurt-0.099
 honey-0.098
ad-0.098
Token "
Token ID366
Feature activation+2.06e+00

Pos logit contributions
 ey+0.024
idges+0.020
ad+0.020
 yogurt+0.019
 honey+0.018
Neg logit contributions
gy-0.033
 bank-0.027
lves-0.023
 station-0.023
zag-0.023
TokenCan
Token ID6090
Feature activation+5.87e+00

Pos logit contributions
 ey+0.134
 honey+0.110
idges+0.108
 yogurt+0.104
ad+0.100
Neg logit contributions
gy-0.204
 bank-0.176
lves-0.155
zag-0.147
 station-0.145
Token I
Token ID314
Feature activation+3.51e+00

Pos logit contributions
 ey+0.338
 yogurt+0.263
 honey+0.262
idges+0.261
ad+0.260
Neg logit contributions
gy-0.633
 bank-0.531
lves-0.471
zag-0.468
 drown-0.450
Token little
Token ID1310
Feature activation+1.13e+00

Pos logit contributions
gy+0.243
 bank+0.203
lves+0.170
 station+0.169
zag+0.165
Neg logit contributions
 ey-0.199
idges-0.168
ad-0.165
 yogurt-0.158
 honey-0.155
Token girl
Token ID2576
Feature activation-1.06e+00

Pos logit contributions
 ey+0.081
 honey+0.071
 yogurt+0.071
ad+0.068
 sweet+0.066
Neg logit contributions
gy-0.104
 bank-0.085
lves-0.076
zag-0.075
 drown-0.072
Token said
Token ID531
Feature activation-3.06e-01

Pos logit contributions
gy+0.104
 bank+0.086
lves+0.075
zag+0.074
 station+0.071
Neg logit contributions
 ey-0.071
 yogurt-0.058
 honey-0.058
idges-0.058
ad-0.057
Token,
Token ID11
Feature activation+3.18e-01

Pos logit contributions
gy+0.025
 bank+0.020
zag+0.016
 neither+0.016
lves+0.016
Neg logit contributions
 ey-0.027
ad-0.022
idges-0.022
 yogurt-0.022
 honey-0.021
Token "
Token ID366
Feature activation+2.02e+00

Pos logit contributions
 ey+0.020
 yogurt+0.016
idges+0.016
ad+0.016
 honey+0.015
Neg logit contributions
gy-0.033
 bank-0.027
zag-0.024
lves-0.024
 station-0.023
TokenOk
Token ID18690
Feature activation+5.26e+00

Pos logit contributions
 ey+0.143
 honey+0.118
 yogurt+0.114
idges+0.113
ad+0.108
Neg logit contributions
gy-0.191
 bank-0.158
lves-0.143
zag-0.138
 station-0.133
Token!
Token ID0
Feature activation+2.24e+00

Pos logit contributions
 ey+0.430
 yogurt+0.352
idges+0.350
ad+0.348
 honey+0.340
Neg logit contributions
gy-0.461
 bank-0.358
zag-0.306
lves-0.301
 station-0.295
Token I
Token ID314
Feature activation+3.45e+00

Pos logit contributions
 ey+0.150
 yogurt+0.124
 honey+0.122
idges+0.121
ad+0.121
Neg logit contributions
gy-0.221
 bank-0.179
lves-0.158
zag-0.157
 station-0.152
Token'll
Token ID1183
Feature activation-8.53e-01

Pos logit contributions
 ey+0.238
 yogurt+0.216
 honey+0.216
 sweet+0.215
ad+0.215
Neg logit contributions
gy-0.299
 bank-0.236
lves-0.222
zag-0.204
 jet-0.193
Token put
Token ID1234
Feature activation+6.56e-01

Pos logit contributions
gy+0.073
 bank+0.059
lves+0.050
zag+0.049
 drown+0.047
Neg logit contributions
 ey-0.068
 yogurt-0.058
 honey-0.057
idges-0.057
ad-0.056
Token the
Token ID262
Feature activation-3.35e-02

Pos logit contributions
 ey+0.048
ad+0.039
idges+0.039
 yogurt+0.038
 honey+0.038
Neg logit contributions
gy-0.061
 bank-0.050
lves-0.043
zag-0.041
 station-0.040
Token smiled
Token ID13541
Feature activation+6.06e+00

Pos logit contributions
gy+0.373
 bank+0.308
zag+0.264
lves+0.262
 station+0.252
Neg logit contributions
 ey-0.255
idges-0.202
 yogurt-0.194
ad-0.193
 honey-0.191
Token and
Token ID290
Feature activation-3.58e-01

Pos logit contributions
 ey+0.555
idges+0.498
 yogurt+0.468
ad+0.466
mmmm+0.452
Neg logit contributions
gy-0.467
 bank-0.330
 neither-0.271
zag-0.262
lves-0.261
Token said
Token ID531
Feature activation-3.11e-01

Pos logit contributions
gy+0.032
 bank+0.026
lves+0.023
zag+0.022
 station+0.021
Neg logit contributions
 ey-0.027
idges-0.023
ad-0.022
 yogurt-0.022
 honey-0.022
Token,
Token ID11
Feature activation+3.05e-01

Pos logit contributions
gy+0.021
 bank+0.015
 neither+0.013
zag+0.012
 argue+0.011
Neg logit contributions
 ey-0.032
idges-0.026
ad-0.026
ango-0.026
 layers-0.025
Token "
Token ID366
Feature activation+2.03e+00

Pos logit contributions
 ey+0.021
ad+0.017
idges+0.017
 yogurt+0.017
 honey+0.016
Neg logit contributions
gy-0.030
 bank-0.024
zag-0.021
lves-0.021
 station-0.020
TokenWould
Token ID17353
Feature activation+5.35e+00

Pos logit contributions
 ey+0.153
 honey+0.127
idges+0.124
 yogurt+0.118
ad+0.115
Neg logit contributions
gy-0.180
 bank-0.146
lves-0.134
zag-0.125
 neither-0.121
Token you
Token ID345
Feature activation+2.61e+00

Pos logit contributions
 ey+0.422
 layers+0.303
idges+0.289
 amaz+0.287
 honey+0.286
Neg logit contributions
gy-0.452
 bank-0.379
lves-0.344
 neither-0.333
zag-0.315
Token like
Token ID588
Feature activation+1.49e+00

Pos logit contributions
 ey+0.249
idges+0.209
ement+0.205
ango+0.196
ad+0.195
Neg logit contributions
gy-0.179
 bank-0.141
 argue-0.112
 neither-0.106
 fight-0.103
Token to
Token ID284
Feature activation+5.65e-01

Pos logit contributions
 ey+0.162
ement+0.145
ango+0.133
idges+0.132
Jamie+0.131
Neg logit contributions
gy-0.067
 bank-0.056
 station-0.038
 neither-0.037
 fight-0.035
Token share
Token ID2648
Feature activation+3.56e+00

Pos logit contributions
 ey+0.053
ement+0.046
idges+0.045
 importantly+0.044
ango+0.043
Neg logit contributions
gy-0.041
 bank-0.033
 argue-0.025
 fight-0.025
 drown-0.024
Token some
Token ID617
Feature activation-3.38e+00

Pos logit contributions
 ey+0.281
idges+0.220
ad+0.219
 importantly+0.218
ement+0.216
Neg logit contributions
gy-0.302
 bank-0.251
lves-0.202
 station-0.200
house-0.196
Token that
Token ID326
Feature activation-7.64e-01

Pos logit contributions
gy+0.023
 bank+0.019
lves+0.016
zag+0.016
 neither+0.015
Neg logit contributions
 ey-0.018
 yogurt-0.014
ad-0.014
idges-0.014
 honey-0.014
Token her
Token ID607
Feature activation+1.12e+00

Pos logit contributions
gy+0.075
 bank+0.062
lves+0.054
zag+0.054
 drown+0.051
Neg logit contributions
 ey-0.051
 yogurt-0.043
 honey-0.042
idges-0.042
ad-0.042
Token mom
Token ID1995
Feature activation-5.94e-01

Pos logit contributions
 ey+0.072
 yogurt+0.063
 sweet+0.062
 honey+0.060
idges+0.055
Neg logit contributions
gy-0.109
 bank-0.089
lves-0.084
zag-0.077
 drown-0.074
Token always
Token ID1464
Feature activation-3.31e-01

Pos logit contributions
gy+0.055
 bank+0.046
lves+0.040
zag+0.039
 drown+0.039
Neg logit contributions
 ey-0.041
 yogurt-0.034
ad-0.034
 honey-0.034
idges-0.034
Token knew
Token ID2993
Feature activation-8.67e-01

Pos logit contributions
gy+0.028
 bank+0.022
lves+0.019
zag+0.019
 station+0.018
Neg logit contributions
 ey-0.027
 yogurt-0.023
idges-0.023
 honey-0.023
ad-0.022
Token what
Token ID644
Feature activation+5.25e+00

Pos logit contributions
gy+0.082
 bank+0.066
lves+0.059
zag+0.059
 neither+0.059
Neg logit contributions
 ey-0.060
ad-0.047
 yogurt-0.045
idges-0.044
 layers-0.044
Token was
Token ID373
Feature activation+1.22e+00

Pos logit contributions
 ey+0.416
ad+0.343
idges+0.341
 yogurt+0.339
 honey+0.337
Neg logit contributions
gy-0.455
 bank-0.363
zag-0.309
lves-0.309
 station-0.297
Token best
Token ID1266
Feature activation-9.22e-01

Pos logit contributions
 ey+0.084
 honey+0.073
 yogurt+0.072
idges+0.070
ad+0.070
Neg logit contributions
gy-0.116
 bank-0.095
lves-0.083
zag-0.082
 drown-0.078
Token for
Token ID329
Feature activation-1.72e+00

Pos logit contributions
gy+0.078
 bank+0.060
zag+0.053
lves+0.050
 station+0.049
Neg logit contributions
 ey-0.076
 yogurt-0.064
ad-0.063
idges-0.063
 honey-0.061
Token her
Token ID607
Feature activation+1.14e+00

Pos logit contributions
gy+0.179
 bank+0.145
lves+0.130
zag+0.128
 station+0.126
Neg logit contributions
 ey-0.107
ad-0.081
 yogurt-0.081
idges-0.078
 honey-0.077
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
 ey+0.074
 honey+0.065
 yogurt+0.065
 sweet+0.063
ad+0.061
Neg logit contributions
gy-0.110
 bank-0.090
lves-0.083
zag-0.078
 drown-0.075
Token nap
Token ID25422
Feature activation+1.22e+00

Pos logit contributions
 ey+0.013
 honey+0.011
 yogurt+0.011
ad+0.011
idges+0.011
Neg logit contributions
gy-0.015
 bank-0.012
lves-0.010
zag-0.010
 station-0.009
Token now
Token ID783
Feature activation+2.54e+00

Pos logit contributions
 ey+0.085
 yogurt+0.072
 honey+0.072
ad+0.071
idges+0.071
Neg logit contributions
gy-0.114
 bank-0.093
lves-0.083
zag-0.080
 drown-0.077
Token."
Token ID526
Feature activation-1.97e+00

Pos logit contributions
 ey+0.169
 honey+0.147
 yogurt+0.144
ad+0.142
idges+0.140
Neg logit contributions
gy-0.242
 bank-0.197
lves-0.178
zag-0.170
 drown-0.163
Token
Token ID198
Feature activation-4.26e-02

Pos logit contributions
gy+0.180
 bank+0.146
zag+0.120
 station+0.118
lves+0.114
Neg logit contributions
 ey-0.150
idges-0.129
 honey-0.129
 yogurt-0.122
ad-0.119
Token
Token ID198
Feature activation-4.56e-02

Pos logit contributions
gy+0.004
 bank+0.003
zag+0.003
lves+0.002
 drown+0.002
Neg logit contributions
 ey-0.004
 honey-0.003
 yogurt-0.003
idges-0.003
 pasta-0.003
TokenJohn
Token ID7554
Feature activation+5.76e+00

Pos logit contributions
gy+0.005
 bank+0.004
zag+0.003
lves+0.003
 station+0.003
Neg logit contributions
 ey-0.003
 honey-0.003
 yogurt-0.002
idges-0.002
ad-0.002
Token and
Token ID290
Feature activation-4.22e-01

Pos logit contributions
 ey+0.438
 yogurt+0.372
 honey+0.369
ad+0.366
idges+0.366
Neg logit contributions
gy-0.511
 bank-0.410
lves-0.356
zag-0.349
 drown-0.331
Token the
Token ID262
Feature activation-5.80e-02

Pos logit contributions
gy+0.050
 bank+0.042
lves+0.037
zag+0.037
 station+0.036
Neg logit contributions
 ey-0.021
idges-0.016
 yogurt-0.016
 honey-0.016
ad-0.015
Token little
Token ID1310
Feature activation+1.07e+00

Pos logit contributions
gy+0.005
 bank+0.004
lves+0.003
zag+0.003
 jet+0.003
Neg logit contributions
 ey-0.005
idges-0.004
 yogurt-0.004
ad-0.004
 honey-0.004
Token squirrel
Token ID33039
Feature activation-5.18e-02

Pos logit contributions
 ey+0.091
idges+0.078
 yogurt+0.077
 honey+0.076
ad+0.075
Neg logit contributions
gy-0.086
 bank-0.068
lves-0.057
zag-0.054
 station-0.053
Token stayed
Token ID9658
Feature activation-1.23e+00

Pos logit contributions
gy+0.004
 bank+0.003
lves+0.003
 drown+0.003
zag+0.003
Neg logit contributions
ad-0.003
 honey-0.003
 ey-0.003
 yogurt-0.003
 sweet-0.003
Token,
Token ID11
Feature activation+4.81e-01

Pos logit contributions
 ey+0.282
 yogurt+0.240
 honey+0.239
idges+0.235
ad+0.235
Neg logit contributions
gy-0.346
 bank-0.280
lves-0.244
zag-0.239
 station-0.227
Token it
Token ID340
Feature activation+1.47e-01

Pos logit contributions
 ey+0.036
idges+0.029
ad+0.029
ement+0.027
 yogurt+0.026
Neg logit contributions
gy-0.043
 bank-0.036
lves-0.030
 neither-0.030
 drown-0.029
Token's
Token ID338
Feature activation-6.21e+00

Pos logit contributions
 ey+0.012
 yogurt+0.010
 honey+0.010
ad+0.010
idges+0.010
Neg logit contributions
gy-0.012
 bank-0.010
lves-0.008
zag-0.008
 drown-0.008
Token so
Token ID523
Feature activation+7.72e-01

Pos logit contributions
gy+0.547
 bank+0.421
lves+0.350
 station+0.346
zag+0.337
Neg logit contributions
 ey-0.503
idges-0.434
 yogurt-0.411
ement-0.391
ad-0.391
Token big
Token ID1263
Feature activation+1.27e+00

Pos logit contributions
 ey+0.047
 yogurt+0.037
idges+0.037
 honey+0.036
ad+0.036
Neg logit contributions
gy-0.082
 bank-0.068
lves-0.061
zag-0.060
 drown-0.057
Token and
Token ID290
Feature activation-1.85e-01

Pos logit contributions
 ey+0.093
 yogurt+0.077
idges+0.077
ad+0.075
 honey+0.075
Neg logit contributions
gy-0.119
 bank-0.096
lves-0.082
zag-0.082
 station-0.079
Token strong
Token ID1913
Feature activation-2.58e-01

Pos logit contributions
gy+0.018
 bank+0.015
lves+0.013
zag+0.012
 station+0.012
Neg logit contributions
 ey-0.013
idges-0.011
ad-0.011
 yogurt-0.010
 honey-0.010
Token!"
Token ID2474
Feature activation+6.00e-01

Pos logit contributions
gy+0.024
 bank+0.019
zag+0.016
lves+0.016
 station+0.016
Neg logit contributions
 ey-0.019
 yogurt-0.016
idges-0.016
ad-0.016
 honey-0.015
Token Ben
Token ID3932
Feature activation+2.23e+00

Pos logit contributions
 ey+0.036
 yogurt+0.029
idges+0.029
 honey+0.029
ad+0.028
Neg logit contributions
gy-0.063
 bank-0.053
lves-0.047
zag-0.046
 drown-0.044
Token said
Token ID531
Feature activation-1.09e-01

Pos logit contributions
 ey+0.136
 yogurt+0.115
ad+0.114
 honey+0.114
idges+0.108
Neg logit contributions
gy-0.227
 bank-0.187
lves-0.171
zag-0.165
 drown-0.162
Token,
Token ID11
Feature activation+5.10e-01

Pos logit contributions
gy+0.011
 bank+0.009
lves+0.008
zag+0.008
 station+0.008
Neg logit contributions
 ey-0.007
 yogurt-0.006
 honey-0.006
ad-0.006
 sweet-0.006
Token and
Token ID290
Feature activation-4.37e-01

Pos logit contributions
 ey+0.589
idges+0.538
mmmm+0.506
 yogurt+0.505
 subtract+0.496
Neg logit contributions
gy-0.405
 bank-0.272
 neither-0.220
zag-0.215
 station-0.214
Token hugged
Token ID41130
Feature activation+2.46e+00

Pos logit contributions
gy+0.034
 bank+0.027
lves+0.024
 station+0.023
 neither+0.023
Neg logit contributions
 ey-0.037
idges-0.030
ad-0.030
 yogurt-0.029
ummy-0.029
Token them
Token ID606
Feature activation-9.45e-01

Pos logit contributions
 ey+0.194
 importantly+0.166
odic+0.163
idges+0.162
mmmm+0.158
Neg logit contributions
gy-0.207
 bank-0.154
 neither-0.141
 argue-0.128
lves-0.126
Token.
Token ID13
Feature activation+8.37e-02

Pos logit contributions
gy+0.089
 bank+0.073
lves+0.064
zag+0.063
 drown+0.060
Neg logit contributions
 ey-0.067
 yogurt-0.056
 honey-0.056
ad-0.055
idges-0.055
Token "
Token ID366
Feature activation+1.97e+00

Pos logit contributions
 ey+0.007
ad+0.006
idges+0.006
odic+0.006
 yogurt+0.006
Neg logit contributions
gy-0.006
 bank-0.004
 neither-0.004
 station-0.004
zag-0.004
TokenWe
Token ID1135
Feature activation-9.06e-01

Pos logit contributions
 ey+0.120
 yogurt+0.096
 honey+0.096
idges+0.095
ad+0.094
Neg logit contributions
gy-0.202
 bank-0.170
lves-0.154
zag-0.149
 station-0.144
Token can
Token ID460
Feature activation+3.25e+00

Pos logit contributions
gy+0.093
 bank+0.075
zag+0.070
lves+0.069
 drown+0.065
Neg logit contributions
 ey-0.053
ad-0.047
 yogurt-0.047
 honey-0.046
idges-0.044
Token learn
Token ID2193
Feature activation-1.59e+00

Pos logit contributions
 ey+0.261
 yogurt+0.221
 honey+0.220
idges+0.217
ad+0.214
Neg logit contributions
gy-0.279
 bank-0.223
zag-0.188
lves-0.187
 station-0.178
Token to
Token ID284
Feature activation+4.89e-01

Pos logit contributions
gy+0.144
 bank+0.122
zag+0.104
 station+0.102
lves+0.102
Neg logit contributions
 ey-0.114
ad-0.093
 yogurt-0.090
idges-0.090
ango-0.084
Token be
Token ID307
Feature activation+1.38e-01

Pos logit contributions
 ey+0.037
 yogurt+0.032
 honey+0.031
idges+0.031
ad+0.031
Neg logit contributions
gy-0.044
 bank-0.035
lves-0.030
zag-0.030
 station-0.028
Token modest
Token ID12949
Feature activation+7.11e-02

Pos logit contributions
 ey+0.008
 honey+0.007
 yogurt+0.006
 sweet+0.006
ad+0.006
Neg logit contributions
gy-0.015
 bank-0.012
lves-0.011
zag-0.011
 drown-0.011
Token the
Token ID262
Feature activation+2.21e-01

Pos logit contributions
gy+0.077
 bank+0.064
lves+0.056
zag+0.055
 station+0.053
Neg logit contributions
 ey-0.050
 yogurt-0.041
idges-0.041
 honey-0.040
ad-0.040
Token ground
Token ID2323
Feature activation+1.13e+00

Pos logit contributions
 ey+0.016
idges+0.013
 yogurt+0.013
ad+0.013
 honey+0.013
Neg logit contributions
gy-0.021
 bank-0.017
lves-0.015
zag-0.014
 station-0.014
Token.
Token ID13
Feature activation+3.12e-01

Pos logit contributions
 ey+0.079
 yogurt+0.067
 honey+0.066
ad+0.065
idges+0.065
Neg logit contributions
gy-0.106
 bank-0.087
lves-0.076
zag-0.075
 drown-0.071
Token He
Token ID679
Feature activation+2.97e+00

Pos logit contributions
 ey+0.022
idges+0.018
 honey+0.018
ad+0.018
 yogurt+0.017
Neg logit contributions
gy-0.029
 bank-0.024
lves-0.021
 station-0.020
zag-0.020
Token saw
Token ID2497
Feature activation-9.81e-01

Pos logit contributions
 ey+0.252
idges+0.220
 honey+0.217
 yogurt+0.216
ad+0.214
Neg logit contributions
gy-0.232
 bank-0.188
lves-0.152
zag-0.149
 station-0.143
Token the
Token ID262
Feature activation+1.11e-01

Pos logit contributions
gy+0.090
 bank+0.076
lves+0.064
 station+0.062
 neither+0.061
Neg logit contributions
 ey-0.072
idges-0.059
ad-0.056
 yogurt-0.054
ement-0.054
Token scissors
Token ID41786
Feature activation+3.33e+00

Pos logit contributions
 ey+0.008
idges+0.007
ad+0.007
 yogurt+0.006
 honey+0.006
Neg logit contributions
gy-0.010
 bank-0.009
lves-0.007
zag-0.007
 station-0.007
Token and
Token ID290
Feature activation-2.93e-01

Pos logit contributions
 ey+0.228
 yogurt+0.195
ad+0.193
 honey+0.192
idges+0.187
Neg logit contributions
gy-0.315
 bank-0.255
lves-0.235
zag-0.219
 drown-0.213
Token the
Token ID262
Feature activation+7.13e-02

Pos logit contributions
gy+0.026
 bank+0.022
lves+0.018
 station+0.017
 neither+0.017
Neg logit contributions
 ey-0.022
idges-0.019
ement-0.018
ad-0.018
ummy-0.018
Token hat
Token ID6877
Feature activation+3.22e-01

Pos logit contributions
 ey+0.005
idges+0.004
ad+0.004
 yogurt+0.004
ement+0.004
Neg logit contributions
gy-0.007
 bank-0.006
lves-0.005
 station-0.005
zag-0.005
Token.
Token ID13
Feature activation+1.87e-01

Pos logit contributions
 ey+0.022
 yogurt+0.019
 honey+0.019
ad+0.019
idges+0.018
Neg logit contributions
gy-0.030
 bank-0.025
lves-0.022
zag-0.021
 drown-0.020
Token can
Token ID460
Feature activation+3.48e+00

Pos logit contributions
 ey+0.218
ad+0.189
 yogurt+0.189
 honey+0.187
idges+0.185
Neg logit contributions
gy-0.234
 bank-0.188
zag-0.166
lves-0.162
 station-0.151
Token make
Token ID787
Feature activation+9.73e-01

Pos logit contributions
 ey+0.245
ad+0.232
idges+0.214
 yogurt+0.212
 sweet+0.205
Neg logit contributions
gy-0.300
 bank-0.247
lves-0.233
zag-0.197
 drown-0.196
Token another
Token ID1194
Feature activation-2.38e+00

Pos logit contributions
 ey+0.061
 yogurt+0.049
 honey+0.049
ad+0.048
idges+0.048
Neg logit contributions
gy-0.101
 bank-0.083
lves-0.074
zag-0.073
 station-0.070
Token car
Token ID1097
Feature activation-6.75e+00

Pos logit contributions
gy+0.223
lves+0.173
 bank+0.167
zag+0.149
nes+0.148
Neg logit contributions
 ey-0.161
 yogurt-0.149
 honey-0.149
 sweet-0.149
 pasta-0.138
Token with
Token ID351
Feature activation+7.78e-02

Pos logit contributions
gy+0.657
 bank+0.543
lves+0.520
 drown+0.460
zag+0.459
Neg logit contributions
 ey-0.389
ad-0.362
 honey-0.358
 yogurt-0.355
 sweet-0.346
Token another
Token ID1194
Feature activation-2.38e+00

Pos logit contributions
 ey+0.005
 yogurt+0.004
 honey+0.004
idges+0.004
ad+0.004
Neg logit contributions
gy-0.008
 bank-0.006
lves-0.006
zag-0.006
 station-0.005
Token box
Token ID3091
Feature activation-3.53e-01

Pos logit contributions
gy+0.205
lves+0.153
 bank+0.148
zag+0.132
 drown+0.129
Neg logit contributions
 ey-0.171
 honey-0.161
 yogurt-0.159
 sweet-0.157
 surprises-0.148
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
gy+0.035
 bank+0.029
lves+0.027
zag+0.025
 drown+0.025
Neg logit contributions
 ey-0.021
 honey-0.019
 yogurt-0.019
ad-0.018
 sweet-0.018
Token And
Token ID843
Feature activation-4.05e-01

Pos logit contributions
 ey+0.024
 honey+0.020
idges+0.020
 yogurt+0.020
ad+0.019
Neg logit contributions
gy-0.032
 bank-0.025
lves-0.022
 station-0.022
 drown-0.022
Token you
Token ID345
Feature activation+2.80e+00

Pos logit contributions
gy+0.040
 bank+0.033
lves+0.029
zag+0.029
 drown+0.027
Neg logit contributions
 ey-0.027
 yogurt-0.022
 honey-0.022
idges-0.022
ad-0.022
Token can
Token ID460
Feature activation+3.52e+00

Pos logit contributions
 ey+0.161
ad+0.149
 honey+0.144
 yogurt+0.142
 sweet+0.141
Neg logit contributions
gy-0.266
 bank-0.216
lves-0.202
zag-0.201
ene-0.187
Token is
Token ID318
Feature activation+1.76e+00

Pos logit contributions
 ey+0.122
idges+0.107
 yogurt+0.104
ad+0.102
ummy+0.100
Neg logit contributions
gy-0.157
 bank-0.133
lves-0.115
zag-0.110
 station-0.108
Token happy
Token ID3772
Feature activation+8.89e-01

Pos logit contributions
 ey+0.141
idges+0.119
 yogurt+0.116
ad+0.115
 honey+0.113
Neg logit contributions
gy-0.152
 bank-0.117
lves-0.103
zag-0.102
 drown-0.098
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
 ey+0.091
idges+0.079
mmmm+0.076
 layers+0.074
ango+0.074
Neg logit contributions
gy-0.052
 bank-0.034
 neither-0.033
 they-0.029
 drown-0.028
Token She
Token ID1375
Feature activation+1.76e+00

Pos logit contributions
 ey+0.014
idges+0.013
 yogurt+0.012
 pasta+0.012
 layers+0.012
Neg logit contributions
gy-0.016
 bank-0.011
 neither-0.010
zag-0.010
lves-0.010
Token thinks
Token ID6834
Feature activation+4.81e-01

Pos logit contributions
 ey+0.122
idges+0.105
 yogurt+0.103
ad+0.101
ummy+0.098
Neg logit contributions
gy-0.161
 bank-0.137
lves-0.119
zag-0.114
 station-0.112
Token the
Token ID262
Feature activation+3.70e-02

Pos logit contributions
 ey+0.038
idges+0.031
 layers+0.030
 yogurt+0.030
ad+0.030
Neg logit contributions
gy-0.038
 bank-0.030
 neither-0.028
 drown-0.027
zag-0.027
Token lizard
Token ID42406
Feature activation+3.18e-02

Pos logit contributions
 ey+0.003
idges+0.003
 subtract+0.003
ad+0.003
mmmm+0.002
Neg logit contributions
gy-0.003
 bank-0.002
zag-0.002
lves-0.002
 drown-0.002
Token is
Token ID318
Feature activation+1.77e+00

Pos logit contributions
 ey+0.002
 yogurt+0.002
 honey+0.002
idges+0.002
ad+0.002
Neg logit contributions
gy-0.003
 bank-0.003
lves-0.002
zag-0.002
 station-0.002
Token fine
Token ID3734
Feature activation+1.61e+00

Pos logit contributions
 ey+0.140
idges+0.114
ement+0.111
ad+0.111
ummy+0.110
Neg logit contributions
gy-0.156
 bank-0.117
lves-0.109
 neither-0.102
 drown-0.100
Token.
Token ID13
Feature activation+2.00e-01

Pos logit contributions
 ey+0.139
idges+0.117
ad+0.113
 yogurt+0.111
 honey+0.107
Neg logit contributions
gy-0.131
 bank-0.102
zag-0.085
 neither-0.083
 station-0.081
Token She
Token ID1375
Feature activation+1.77e+00

Pos logit contributions
 ey+0.015
idges+0.014
 yogurt+0.013
 pasta+0.013
ad+0.013
Neg logit contributions
gy-0.017
 bank-0.012
 neither-0.011
lves-0.011
zag-0.011
Token was
Token ID373
Feature activation+1.15e+00

Pos logit contributions
gy+0.034
 bank+0.027
lves+0.024
zag+0.023
 drown+0.022
Neg logit contributions
 ey-0.029
 yogurt-0.025
 honey-0.025
ad-0.025
idges-0.024
Token always
Token ID1464
Feature activation-3.96e-01

Pos logit contributions
 ey+0.077
 honey+0.071
 yogurt+0.070
 sweet+0.069
ad+0.067
Neg logit contributions
gy-0.104
 bank-0.085
lves-0.076
zag-0.074
 drown-0.069
Token playing
Token ID2712
Feature activation+3.02e+00

Pos logit contributions
gy+0.034
 bank+0.027
lves+0.023
zag+0.023
 drown+0.022
Neg logit contributions
 ey-0.032
 yogurt-0.027
idges-0.026
ad-0.026
 honey-0.026
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
 ey+0.239
 yogurt+0.199
idges+0.199
ad+0.197
 honey+0.197
Neg logit contributions
gy-0.264
 bank-0.214
lves-0.180
zag-0.177
 station-0.172
Token One
Token ID1881
Feature activation-5.48e+00

Pos logit contributions
 ey+0.012
idges+0.011
 honey+0.010
 yogurt+0.010
ad+0.010
Neg logit contributions
gy-0.011
 bank-0.008
 station-0.007
zag-0.007
lves-0.007
Token day
Token ID1110
Feature activation-2.86e+00

Pos logit contributions
gy+0.435
 bank+0.348
lves+0.301
zag+0.280
 drown+0.274
Neg logit contributions
 ey-0.460
 yogurt-0.421
 honey-0.413
ad-0.399
 sweet-0.397
Token he
Token ID339
Feature activation+8.52e-01

Pos logit contributions
gy+0.233
 bank+0.181
lves+0.149
zag+0.148
 neither+0.142
Neg logit contributions
 ey-0.247
idges-0.209
ad-0.206
 honey-0.203
 yogurt-0.201
Token was
Token ID373
Feature activation+1.16e+00

Pos logit contributions
 ey+0.055
 yogurt+0.050
ad+0.048
 honey+0.046
 pasta+0.045
Neg logit contributions
gy-0.079
 bank-0.064
lves-0.061
zag-0.060
 drown-0.055
Token playing
Token ID2712
Feature activation+3.03e+00

Pos logit contributions
 ey+0.058
 yogurt+0.054
 honey+0.053
 sweet+0.051
ad+0.048
Neg logit contributions
gy-0.121
 bank-0.101
lves-0.095
zag-0.090
mer-0.085
Token outside
Token ID2354
Feature activation+2.52e+00

Pos logit contributions
 ey+0.241
idges+0.200
 yogurt+0.199
ad+0.199
 honey+0.197
Neg logit contributions
gy-0.264
 bank-0.213
lves-0.179
zag-0.178
 station-0.171
Token when
Token ID618
Feature activation-9.13e-01

Pos logit contributions
 ey+0.206
 yogurt+0.175
 honey+0.174
idges+0.174
ad+0.172
Neg logit contributions
gy-0.213
 bank-0.168
lves-0.142
zag-0.140
 station-0.134
Token kind
Token ID1611
Feature activation+4.31e+00

Pos logit contributions
 ey+0.021
 yogurt+0.017
idges+0.017
ad+0.016
 honey+0.016
Neg logit contributions
gy-0.033
 bank-0.027
lves-0.024
zag-0.023
 station-0.023
Token and
Token ID290
Feature activation-2.42e-01

Pos logit contributions
 ey+0.303
 yogurt+0.254
 honey+0.253
ad+0.250
idges+0.249
Neg logit contributions
gy-0.406
 bank-0.331
lves-0.292
zag-0.286
 drown-0.273
Token helpful
Token ID7613
Feature activation+4.27e+00

Pos logit contributions
gy+0.025
 bank+0.021
lves+0.019
zag+0.019
 drown+0.018
Neg logit contributions
 ey-0.015
 yogurt-0.012
 honey-0.012
idges-0.011
ad-0.011
Token and
Token ID290
Feature activation-2.33e-01

Pos logit contributions
 ey+0.315
 yogurt+0.266
 honey+0.264
ad+0.261
idges+0.261
Neg logit contributions
gy-0.391
 bank-0.316
lves-0.276
zag-0.271
 drown-0.257
Token not
Token ID407
Feature activation-3.07e+00

Pos logit contributions
gy+0.024
 bank+0.020
lves+0.018
zag+0.018
 station+0.017
Neg logit contributions
 ey-0.014
 honey-0.012
 yogurt-0.012
ad-0.011
idges-0.011
Token gr
Token ID1036
Feature activation-3.91e+00

Pos logit contributions
gy+0.251
 bank+0.195
lves+0.172
zag+0.169
 station+0.158
Neg logit contributions
 ey-0.248
 yogurt-0.220
 honey-0.218
ad-0.213
idges-0.209
Tokenumpy
Token ID32152
Feature activation-6.06e+00

Pos logit contributions
gy+0.354
 bank+0.303
 station+0.255
lves+0.250
zag+0.249
Neg logit contributions
 ey-0.267
ad-0.242
idges-0.235
ummy-0.215
ement-0.211
Token.
Token ID13
Feature activation+2.82e-01

Pos logit contributions
gy+0.509
 bank+0.399
lves+0.356
zag+0.343
 drown+0.319
Neg logit contributions
 ey-0.468
 yogurt-0.424
 honey-0.421
ad-0.411
idges-0.406
Token<|endoftext|>
Token ID50256
Feature activation+1.22e+00

Pos logit contributions
 ey+0.023
 yogurt+0.019
ad+0.019
 honey+0.019
idges+0.019
Neg logit contributions
gy-0.023
 bank-0.019
zag-0.016
lves-0.016
 drown-0.015
TokenS
Token ID50
Feature activation-3.42e+00

Pos logit contributions
 ey+0.101
idges+0.089
 honey+0.089
 layers+0.084
 subtract+0.082
Neg logit contributions
gy-0.099
 bank-0.075
zag-0.066
 station-0.062
 drown-0.059
Tokenara
Token ID3301
Feature activation+9.48e-01

Pos logit contributions
gy+0.281
 bank+0.227
 station+0.190
zag+0.189
lves+0.188
Neg logit contributions
 ey-0.272
 honey-0.231
idges-0.227
 layers-0.222
 importantly-0.222
Token and
Token ID290
Feature activation-2.62e-01

Pos logit contributions
 ey+0.052
idges+0.044
 yogurt+0.044
ad+0.044
 honey+0.043
Neg logit contributions
gy-0.060
 bank-0.048
lves-0.041
zag-0.040
 station-0.039
Token a
Token ID257
Feature activation+3.40e-01

Pos logit contributions
gy+0.023
 bank+0.019
lves+0.016
zag+0.015
 drown+0.015
Neg logit contributions
 ey-0.020
 yogurt-0.017
ad-0.017
idges-0.017
 honey-0.016
Token bit
Token ID1643
Feature activation-6.07e+00

Pos logit contributions
 ey+0.025
 honey+0.021
 yogurt+0.021
ad+0.020
 sweet+0.020
Neg logit contributions
gy-0.031
 bank-0.025
lves-0.022
zag-0.021
 drown-0.020
Token scary
Token ID14343
Feature activation-2.18e+00

Pos logit contributions
gy+0.518
 bank+0.415
lves+0.357
zag+0.347
 drown+0.332
Neg logit contributions
 ey-0.482
 yogurt-0.411
idges-0.406
ad-0.405
 honey-0.404
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
gy+0.200
 bank+0.162
lves+0.141
zag+0.139
 station+0.132
Neg logit contributions
 ey-0.160
 yogurt-0.135
 honey-0.133
idges-0.133
ad-0.132
Token But
Token ID887
Feature activation-3.10e+00

Pos logit contributions
 ey+0.018
 yogurt+0.015
 honey+0.015
idges+0.014
ad+0.014
Neg logit contributions
gy-0.026
 bank-0.021
lves-0.019
zag-0.018
 station-0.018
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
gy+0.326
 bank+0.273
lves+0.247
zag+0.242
 drown+0.231
Neg logit contributions
 ey-0.179
 honey-0.154
ad-0.146
 yogurt-0.145
 sweet-0.142
Token kitten
Token ID42143
Feature activation-6.92e+00

Pos logit contributions
 ey+0.009
 honey+0.008
 yogurt+0.008
 sweet+0.008
ad+0.008
Neg logit contributions
gy-0.010
 bank-0.008
lves-0.007
zag-0.007
 drown-0.006
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
gy+0.625
 bank+0.496
lves+0.455
zag+0.435
 drown+0.427
Neg logit contributions
 ey-0.476
 honey-0.425
ad-0.419
 yogurt-0.412
 sweet-0.402
Token brave
Token ID14802
Feature activation+1.08e+00

Pos logit contributions
 ey+0.095
 honey+0.082
 yogurt+0.081
ad+0.081
idges+0.079
Neg logit contributions
gy-0.117
 bank-0.094
lves-0.082
zag-0.080
 station-0.076
Token,
Token ID11
Feature activation+4.41e-01

Pos logit contributions
 ey+0.088
 yogurt+0.075
idges+0.074
ad+0.073
 honey+0.072
Neg logit contributions
gy-0.091
 bank-0.072
lves-0.061
zag-0.059
 station-0.058
Token One
Token ID1881
Feature activation-5.50e+00

Pos logit contributions
 ey+0.010
idges+0.009
 honey+0.009
ad+0.009
 yogurt+0.008
Neg logit contributions
gy-0.011
 bank-0.009
 station-0.007
zag-0.007
lves-0.007
Token day
Token ID1110
Feature activation-2.88e+00

Pos logit contributions
gy+0.450
 bank+0.375
lves+0.332
 drown+0.306
zag+0.292
Neg logit contributions
 ey-0.434
 yogurt-0.403
 honey-0.384
 sweet-0.384
ad-0.381
Token,
Token ID11
Feature activation+2.87e-01

Pos logit contributions
gy+0.261
 bank+0.212
lves+0.185
zag+0.180
 station+0.172
Neg logit contributions
 ey-0.213
 yogurt-0.182
 honey-0.180
ad-0.177
idges-0.177
Token Tim
Token ID5045
Feature activation-3.74e-01

Pos logit contributions
 ey+0.020
idges+0.017
ad+0.017
 honey+0.017
 yogurt+0.016
Neg logit contributions
gy-0.027
 bank-0.022
lves-0.019
zag-0.019
 station-0.018
Tokenmy
Token ID1820
Feature activation+3.04e+00

Pos logit contributions
gy+0.042
 bank+0.036
lves+0.033
zag+0.032
 drown+0.032
Neg logit contributions
 ey-0.019
 yogurt-0.015
ad-0.015
 honey-0.014
idges-0.014
Token's
Token ID338
Feature activation-6.41e+00

Pos logit contributions
 ey+0.187
 yogurt+0.183
 pasta+0.176
 sweet+0.166
 honey+0.164
Neg logit contributions
gy-0.258
 bank-0.217
lves-0.212
zag-0.206
 drown-0.200
Token little
Token ID1310
Feature activation+1.10e+00

Pos logit contributions
gy+0.575
 bank+0.467
lves+0.426
 drown+0.393
zag+0.388
Neg logit contributions
 ey-0.464
 yogurt-0.415
 honey-0.396
 sweet-0.395
ad-0.383
Token sister
Token ID6621
Feature activation-4.04e+00

Pos logit contributions
 ey+0.083
 yogurt+0.077
 honey+0.075
 sweet+0.073
 eyes+0.071
Neg logit contributions
gy-0.089
 bank-0.071
lves-0.071
zag-0.069
 drown-0.062
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
gy+0.366
 bank+0.311
lves+0.281
zag+0.281
 drown+0.265
Neg logit contributions
 ey-0.261
 yogurt-0.249
 honey-0.240
ad-0.236
 sweet-0.233
Token Sally
Token ID25737
Feature activation-9.37e-01

Pos logit contributions
 ey+0.020
 yogurt+0.016
idges+0.016
 honey+0.016
ad+0.016
Neg logit contributions
gy-0.028
 bank-0.023
lves-0.020
zag-0.020
 station-0.019
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
gy+0.089
 bank+0.076
lves+0.068
zag+0.068
 drown+0.065
Neg logit contributions
 ey-0.058
 honey-0.051
 yogurt-0.051
ad-0.050
idges-0.048
Token play
Token ID711
Feature activation+1.01e+00

Pos logit contributions
gy+0.595
 bank+0.483
lves+0.440
zag+0.428
 drown+0.412
Neg logit contributions
 ey-0.425
 honey-0.360
 yogurt-0.358
ad-0.342
idges-0.339
Tokenroom
Token ID3823
Feature activation+2.49e+00

Pos logit contributions
 ey+0.057
 yogurt+0.052
ad+0.051
 honey+0.051
idges+0.048
Neg logit contributions
gy-0.101
 bank-0.084
lves-0.079
 drown-0.075
zag-0.073
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
 ey+0.142
 honey+0.132
 yogurt+0.130
ad+0.124
idges+0.123
Neg logit contributions
gy-0.252
 bank-0.203
lves-0.190
 drown-0.184
zag-0.180
Token So
Token ID1406
Feature activation+5.08e-01

Pos logit contributions
 ey+0.008
 yogurt+0.006
 honey+0.006
idges+0.006
ad+0.006
Neg logit contributions
gy-0.012
 bank-0.010
lves-0.009
zag-0.009
 drown-0.009
Token one
Token ID530
Feature activation-9.62e+00

Pos logit contributions
 ey+0.031
 honey+0.028
 yogurt+0.028
 sweet+0.027
ad+0.026
Neg logit contributions
gy-0.051
 bank-0.043
lves-0.040
 drown-0.038
zag-0.037
Token day
Token ID1110
Feature activation-2.88e+00

Pos logit contributions
gy+0.558
 bank+0.374
zag+0.309
 station+0.289
lves+0.286
Neg logit contributions
 ey-1.024
idges-0.911
ad-0.887
 yogurt-0.861
 honey-0.855
Token,
Token ID11
Feature activation+2.83e-01

Pos logit contributions
gy+0.291
 bank+0.247
lves+0.220
zag+0.218
 drown+0.209
Neg logit contributions
 ey-0.171
 yogurt-0.159
 honey-0.156
 sweet-0.147
ad-0.144
Token Lily
Token ID20037
Feature activation-1.84e+00

Pos logit contributions
 ey+0.018
 yogurt+0.016
 honey+0.016
 sweet+0.015
idges+0.015
Neg logit contributions
gy-0.029
 bank-0.024
lves-0.021
zag-0.021
 drown-0.020
Token asked
Token ID1965
Feature activation-8.79e-01

Pos logit contributions
gy+0.166
 bank+0.135
lves+0.124
 drown+0.122
zag+0.121
Neg logit contributions
 ey-0.126
 yogurt-0.110
 honey-0.107
ad-0.106
 sweet-0.102
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
gy+0.094
 bank+0.077
lves+0.069
 station+0.068
zag+0.067
Neg logit contributions
 ey-0.054
 yogurt-0.041
idges-0.041
ad-0.040
 honey-0.039
Token grand
Token ID4490
Feature activation-1.45e+00

Pos logit contributions
 ey+0.075
 honey+0.065
 yogurt+0.064
idges+0.062
ad+0.062
Neg logit contributions
gy-0.099
 bank-0.081
lves-0.071
zag-0.070
 drown-0.067
Token fastest
Token ID14162
Feature activation-3.42e+00

Pos logit contributions
gy+0.255
 bank+0.200
zag+0.187
lves+0.184
 drown+0.174
Neg logit contributions
 ey-0.159
 honey-0.144
 yogurt-0.136
 sweet-0.133
ad-0.131
Token pig
Token ID12967
Feature activation-5.15e+00

Pos logit contributions
gy+0.311
 bank+0.244
lves+0.222
zag+0.221
 argue+0.216
Neg logit contributions
 ey-0.226
 honey-0.211
ad-0.205
 yogurt-0.204
idges-0.199
Token,
Token ID11
Feature activation+4.94e-01

Pos logit contributions
gy+0.473
 bank+0.382
lves+0.365
 drown+0.345
 argue+0.327
Neg logit contributions
 ey-0.314
ad-0.296
 honey-0.271
 yogurt-0.270
idges-0.268
Token the
Token ID262
Feature activation+1.82e-01

Pos logit contributions
 ey+0.032
 honey+0.028
 yogurt+0.027
ad+0.027
idges+0.026
Neg logit contributions
gy-0.049
 bank-0.039
zag-0.035
lves-0.035
 drown-0.033
Token smallest
Token ID18197
Feature activation-3.23e-01

Pos logit contributions
 ey+0.013
 honey+0.011
 yogurt+0.011
ad+0.010
 sweet+0.010
Neg logit contributions
gy-0.017
 bank-0.014
lves-0.012
zag-0.012
 drown-0.012
Token one
Token ID530
Feature activation-9.41e+00

Pos logit contributions
gy+0.030
 bank+0.024
lves+0.022
zag+0.021
 drown+0.020
Neg logit contributions
 ey-0.023
 honey-0.019
 yogurt-0.019
ad-0.019
idges-0.019
Token,
Token ID11
Feature activation+5.02e-01

Pos logit contributions
gy+0.844
 bank+0.682
zag+0.592
lves+0.585
 station+0.559
Neg logit contributions
 ey-0.720
 yogurt-0.594
idges-0.590
 honey-0.588
ad-0.577
Token won
Token ID1839
Feature activation-3.11e+00

Pos logit contributions
 ey+0.038
 yogurt+0.032
 honey+0.031
idges+0.031
ad+0.031
Neg logit contributions
gy-0.045
 bank-0.036
lves-0.032
zag-0.031
 station-0.030
Token the
Token ID262
Feature activation+2.02e-01

Pos logit contributions
gy+0.325
 bank+0.273
lves+0.245
zag+0.238
 station+0.230
Neg logit contributions
 ey-0.180
ad-0.150
 honey-0.148
 yogurt-0.148
idges-0.147
Token race
Token ID3234
Feature activation-5.28e+00

Pos logit contributions
 ey+0.016
 honey+0.015
 yogurt+0.014
 sweet+0.014
ad+0.014
Neg logit contributions
gy-0.017
 bank-0.012
lves-0.011
zag-0.011
 drown-0.010
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
gy+0.543
 bank+0.439
lves+0.418
 drown+0.389
zag+0.388
Neg logit contributions
 ey-0.291
ad-0.268
 yogurt-0.252
idges-0.244
 honey-0.242
Token stay
Token ID2652
Feature activation-1.04e-01

Pos logit contributions
gy+0.022
 bank+0.018
lves+0.015
zag+0.015
 drown+0.014
Neg logit contributions
 ey-0.020
idges-0.017
ad-0.016
 yogurt-0.016
 honey-0.016
Token with
Token ID351
Feature activation+2.92e-02

Pos logit contributions
gy+0.010
 bank+0.008
zag+0.007
lves+0.007
 drown+0.007
Neg logit contributions
 ey-0.007
 sweet-0.006
 honey-0.006
 yogurt-0.006
ad-0.006
Token me
Token ID502
Feature activation+5.99e+00

Pos logit contributions
 ey+0.002
ad+0.001
 yogurt+0.001
idges+0.001
ement+0.001
Neg logit contributions
gy-0.003
 bank-0.003
lves-0.002
 neither-0.002
 station-0.002
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
 ey+0.329
 honey+0.329
 sweet+0.309
 yogurt+0.309
idges+0.287
Neg logit contributions
gy-0.591
 bank-0.492
lves-0.464
 drown-0.430
zag-0.422
Token The
Token ID383
Feature activation-2.58e+00

Pos logit contributions
 ey+0.018
idges+0.015
 yogurt+0.015
 honey+0.015
ad+0.015
Neg logit contributions
gy-0.028
 bank-0.022
lves-0.020
zag-0.019
 station-0.019
Token bank
Token ID3331
Feature activation-1.23e+01

Pos logit contributions
gy+0.214
 bank+0.173
lves+0.144
zag+0.141
 station+0.138
Neg logit contributions
 ey-0.213
idges-0.182
ad-0.179
 yogurt-0.179
 honey-0.178
Token is
Token ID318
Feature activation+1.85e+00

Pos logit contributions
gy+1.231
 bank+1.024
lves+0.896
zag+0.890
 station+0.855
Neg logit contributions
 ey-0.790
 yogurt-0.642
 honey-0.636
idges-0.633
ad-0.630
Token not
Token ID407
Feature activation-3.06e+00

Pos logit contributions
 ey+0.142
 yogurt+0.120
 honey+0.119
idges+0.118
ad+0.118
Neg logit contributions
gy-0.164
 bank-0.132
lves-0.114
zag-0.112
 station-0.106
Token a
Token ID257
Feature activation+3.66e-01

Pos logit contributions
gy+0.315
 bank+0.261
lves+0.233
zag+0.232
 drown+0.221
Neg logit contributions
 ey-0.180
 honey-0.161
 yogurt-0.157
 sweet-0.151
ad-0.147
Token safe
Token ID3338
Feature activation-7.70e-01

Pos logit contributions
 ey+0.025
 honey+0.022
 yogurt+0.022
 sweet+0.022
 mirror+0.020
Neg logit contributions
gy-0.035
 bank-0.027
zag-0.025
lves-0.024
 drown-0.023
Token place
Token ID1295
Feature activation-2.98e+00

Pos logit contributions
gy+0.065
lves+0.053
 bank+0.050
zag+0.048
 drown+0.047
Neg logit contributions
 ey-0.052
 honey-0.049
 yogurt-0.048
 sweet-0.047
ad-0.046
Token the
Token ID262
Feature activation-4.12e-02

Pos logit contributions
 ey+0.210
idges+0.175
mmmm+0.169
ement+0.169
odic+0.162
Neg logit contributions
gy-0.219
 bank-0.187
lves-0.161
 station-0.154
 jet-0.151
Token toes
Token ID23932
Feature activation+2.08e+00

Pos logit contributions
gy+0.004
 bank+0.003
 station+0.002
lves+0.002
zag+0.002
Neg logit contributions
 ey-0.003
idges-0.003
ad-0.003
 honey-0.003
 yogurt-0.003
Token were
Token ID547
Feature activation-3.54e-02

Pos logit contributions
 ey+0.155
 honey+0.130
 yogurt+0.129
idges+0.129
ad+0.128
Neg logit contributions
gy-0.188
 bank-0.151
zag-0.130
lves-0.129
 station-0.123
Token pink
Token ID11398
Feature activation+2.42e+00

Pos logit contributions
gy+0.003
 bank+0.002
zag+0.002
 station+0.002
 neither+0.002
Neg logit contributions
 ey-0.003
idges-0.002
mmmm-0.002
ad-0.002
ement-0.002
Token and
Token ID290
Feature activation-4.04e-01

Pos logit contributions
 ey+0.202
idges+0.178
ad+0.171
 honey+0.162
mmmm+0.161
Neg logit contributions
gy-0.202
 bank-0.161
zag-0.131
 station-0.124
house-0.119
Token one
Token ID530
Feature activation-9.64e+00

Pos logit contributions
gy+0.038
 bank+0.030
zag+0.026
 neither+0.026
lves+0.025
Neg logit contributions
 ey-0.030
idges-0.024
ad-0.023
ement-0.023
mmmm-0.021
Token of
Token ID286
Feature activation+2.79e+00

Pos logit contributions
gy+0.800
 bank+0.644
zag+0.558
 station+0.525
house+0.519
Neg logit contributions
 ey-0.777
idges-0.665
ad-0.637
mmmm-0.605
ango-0.604
Token them
Token ID606
Feature activation-9.08e-01

Pos logit contributions
 ey+0.224
idges+0.182
 yogurt+0.179
 honey+0.172
ement+0.167
Neg logit contributions
gy-0.228
 bank-0.187
lves-0.160
 neither-0.153
 station-0.151
Token was
Token ID373
Feature activation+1.14e+00

Pos logit contributions
gy+0.075
 bank+0.060
zag+0.049
lves+0.049
 station+0.046
Neg logit contributions
 ey-0.076
idges-0.064
 honey-0.064
 yogurt-0.063
ad-0.063
Token black
Token ID2042
Feature activation+2.85e-01

Pos logit contributions
 ey+0.088
idges+0.072
ad+0.069
 yogurt+0.068
 honey+0.066
Neg logit contributions
gy-0.105
 bank-0.083
zag-0.072
lves-0.069
 station-0.068
Token.
Token ID13
Feature activation+1.27e-01

Pos logit contributions
 ey+0.025
idges+0.022
ad+0.020
mmmm+0.020
Jamie+0.020
Neg logit contributions
gy-0.023
 bank-0.018
zag-0.014
 station-0.014
house-0.013
Token so
Token ID523
Feature activation+5.39e-01

Pos logit contributions
 ey+0.127
 yogurt+0.104
ad+0.102
idges+0.100
ango+0.098
Neg logit contributions
gy-0.144
 bank-0.120
zag-0.103
lves-0.098
 station-0.097
Token you
Token ID345
Feature activation+2.55e+00

Pos logit contributions
 ey+0.039
 yogurt+0.033
 honey+0.033
idges+0.033
ad+0.033
Neg logit contributions
gy-0.050
 bank-0.040
lves-0.035
zag-0.034
 station-0.033
Token can
Token ID460
Feature activation+3.27e+00

Pos logit contributions
 ey+0.171
ad+0.149
 yogurt+0.146
 honey+0.146
idges+0.144
Neg logit contributions
gy-0.240
 bank-0.193
lves-0.177
zag-0.165
 station-0.160
Token manage
Token ID6687
Feature activation+9.69e-02

Pos logit contributions
 ey+0.243
ad+0.214
 yogurt+0.210
 honey+0.207
idges+0.207
Neg logit contributions
gy-0.287
 bank-0.227
lves-0.205
zag-0.190
 station-0.187
Token it
Token ID340
Feature activation-8.68e-02

Pos logit contributions
 ey+0.007
 yogurt+0.006
ad+0.006
idges+0.006
 honey+0.006
Neg logit contributions
gy-0.009
 bank-0.007
zag-0.006
lves-0.006
 station-0.006
Token one
Token ID530
Feature activation-9.64e+00

Pos logit contributions
gy+0.008
 bank+0.006
lves+0.005
zag+0.005
 station+0.005
Neg logit contributions
 ey-0.006
 yogurt-0.005
 honey-0.005
idges-0.005
ad-0.005
Token day
Token ID1110
Feature activation-2.90e+00

Pos logit contributions
gy+0.806
 bank+0.657
zag+0.566
lves+0.542
 station+0.530
Neg logit contributions
 ey-0.777
idges-0.643
ad-0.640
 yogurt-0.632
 honey-0.625
Token."
Token ID526
Feature activation-1.96e+00

Pos logit contributions
gy+0.260
 bank+0.211
lves+0.180
zag+0.179
 station+0.171
Neg logit contributions
 ey-0.219
 yogurt-0.182
 honey-0.181
idges-0.180
ad-0.180
Token
Token ID198
Feature activation-3.70e-02

Pos logit contributions
gy+0.162
 bank+0.129
zag+0.110
 station+0.105
 neither+0.102
Neg logit contributions
 ey-0.159
idges-0.136
 honey-0.134
 yogurt-0.132
ad-0.126
Token
Token ID198
Feature activation-3.03e-02

Pos logit contributions
gy+0.003
 bank+0.002
zag+0.002
 station+0.002
lves+0.002
Neg logit contributions
 ey-0.003
 honey-0.003
 yogurt-0.003
idges-0.003
umm-0.003
TokenLisa
Token ID44203
Feature activation+2.59e+00

Pos logit contributions
gy+0.003
 bank+0.002
zag+0.002
 station+0.002
house+0.002
Neg logit contributions
 ey-0.002
 honey-0.002
 yogurt-0.002
ummy-0.002
idges-0.002
Token there
Token ID612
Feature activation-1.51e+00

Pos logit contributions
 ey+0.025
ad+0.022
idges+0.022
 yogurt+0.021
 honey+0.021
Neg logit contributions
gy-0.022
 bank-0.017
lves-0.014
zag-0.014
 station-0.013
Token were
Token ID547
Feature activation-1.03e-02

Pos logit contributions
gy+0.127
 bank+0.102
zag+0.084
 station+0.083
lves+0.082
Neg logit contributions
 ey-0.124
idges-0.104
 honey-0.101
 yogurt-0.101
ad-0.099
Token two
Token ID734
Feature activation-2.65e-01

Pos logit contributions
gy+0.001
 bank+0.001
lves+0.001
 station+0.001
zag+0.001
Neg logit contributions
 ey-0.001
idges-0.001
ad-0.001
ement-0.001
 yogurt-0.001
Token stickers
Token ID28568
Feature activation+4.15e+00

Pos logit contributions
gy+0.027
 bank+0.022
lves+0.020
 station+0.019
zag+0.019
Neg logit contributions
 ey-0.017
ad-0.014
 yogurt-0.013
idges-0.013
 honey-0.013
Token,
Token ID11
Feature activation+2.89e-01

Pos logit contributions
 ey+0.269
 yogurt+0.233
 honey+0.231
ad+0.230
idges+0.222
Neg logit contributions
gy-0.400
 bank-0.331
lves-0.305
 drown-0.289
zag-0.278
Token one
Token ID530
Feature activation-9.61e+00

Pos logit contributions
 ey+0.020
idges+0.017
ad+0.016
 yogurt+0.015
 honey+0.015
Neg logit contributions
gy-0.028
 bank-0.023
lves-0.020
zag-0.019
 station-0.019
Token for
Token ID329
Feature activation-1.79e+00

Pos logit contributions
gy+0.827
 bank+0.674
zag+0.574
 station+0.561
lves+0.548
Neg logit contributions
 ey-0.746
idges-0.638
ad-0.616
 yogurt-0.603
 honey-0.587
Token Ben
Token ID3932
Feature activation+2.02e+00

Pos logit contributions
gy+0.170
 bank+0.140
lves+0.122
zag+0.118
 station+0.117
Neg logit contributions
 ey-0.126
 yogurt-0.101
idges-0.100
ad-0.099
 honey-0.099
Token and
Token ID290
Feature activation-3.84e-01

Pos logit contributions
 ey+0.117
 honey+0.108
 yogurt+0.106
 sweet+0.100
ad+0.099
Neg logit contributions
gy-0.198
 bank-0.167
lves-0.155
zag-0.147
 drown-0.146
Token one
Token ID530
Feature activation-9.61e+00

Pos logit contributions
gy+0.039
 bank+0.032
lves+0.029
zag+0.028
 station+0.027
Neg logit contributions
 ey-0.024
 yogurt-0.020
idges-0.020
 honey-0.020
ad-0.019
Token for
Token ID329
Feature activation-1.79e+00

Pos logit contributions
gy+0.816
 bank+0.670
zag+0.563
 station+0.546
lves+0.530
Neg logit contributions
 ey-0.765
idges-0.652
ad-0.627
 yogurt-0.601
 honey-0.588