TOP ACTIVATIONS
MAX = 22.886

looked around and tried to think of something . Suddenly she
a surprise . But I think you will like it .
picture . What do you think ?" Anna and
kind and responsible . We think you are ready to have
cones and smile . They think it is the best ice
to tell someone if we think there 's a monster in
about that garden . I think you 'll love it ."
busy that he couldn 't think straight ! The
of it . Molly would think a lot about her team
to do . Do you think you will succeed ?"
and said , " I think there is some wool in
ice . Anna and Ben think they are funny . They
cat said , " I think we should cut the pepper
. " I think so , Lily ," Tom
away . She tried to think of a way to help
't want his friends to think he was bad at jumping
bed . They did not think they would sleep well .
and take some time to think before he did anything .
, so she couldn 't think of a good idea .
a diary . Do you think I should get one ?"

MIN ACTIVATIONS
MIN = -28.935

bed that he sn ugg led in . But one night
The cater pillar w igg led inside and felt safe .
she did , it spark led with the most beautiful light
, Bob 's eyes spark led with joy . His sister
so happy that she whist led all the way home .
around . She w igg led it and squ igg led
graceful car - it spark led in the sunshine . One
S ara gigg led . She picked up her
Mom smiled , t uss led his hair and replied ,
a shiny rock that spark led in the sun . She
As he padd led along , he saw an
bed , he sn ugg led under the covers and fell
. Tim my sn ugg led up to his mom and
hedge . He w igg led and squ irmed and soon
and spikes . They grow led and roared and his sed
Suddenly , his mom tick led him and he laughed and
. But it tw ink led in the sunlight and danced
many colors . It spark led in the sun , and
It bark ed and grow led at them , and they
looked at them and grow led again . Tom and Lily

INTERVAL 9.931 - 22.886
CONTAINS 4.333%

more clothes and toys , but they did not find the
learned that sometimes things can look scary , but it 's
. <|endoftext|> Once upon a time , there was a little
. No one would ever guess it was a lung .
She knew she had to tell her dad about the bug

INTERVAL -3.024 - 9.931
CONTAINS 63.314%

handed the ball to the dog . The dog
stop . He spun around and around until he was dizz
saw how happy and safe the area was . They knew
a boy and made him fall down . She felt very
the dinosaur . He couldn 't believe that a real ,

INTERVAL -15.980 - -3.024
CONTAINS 32.008%

nap under the big tree in the park . Her mom
was too big to fit in the suitcase , and that
look for her dolls again . She opened the case and
pony stopped in her tracks . She felt a bit scared
He showed her a soft bear . He said the bear

INTERVAL -28.935 - -15.980
CONTAINS 0.345%

eat . L ily was happy to learn about
loud . L ily is scared . She runs
snow man . <|endoftext|> L ily was a creative girl who
loudly . He pe ck ed at their shoes and legs
it ." L ily felt happy that she was
Token looked
Token ID3114
Feature activation-1.68e+00

Pos logit contributions
led+0.262
ed+0.220
ier+0.209
med+0.200
ked+0.199
Neg logit contributions
 great-0.174
 think-0.171
 pleasure-0.169
 plan-0.166
 learn-0.165
Token around
Token ID1088
Feature activation-9.00e+00

Pos logit contributions
led+0.102
ed+0.084
awed+0.069
ied+0.069
ked+0.068
Neg logit contributions
 pleasure-0.103
 welcome-0.091
 Deal-0.091
 great-0.091
 learn-0.088
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
led+0.595
ed+0.495
ied+0.420
y+0.402
ted+0.400
Neg logit contributions
 pleasure-0.516
 Deal-0.473
 welcome-0.435
 deal-0.421
 learn-0.419
Token tried
Token ID3088
Feature activation-1.34e+00

Pos logit contributions
 pleasure+0.201
 Deal+0.178
 welcome+0.175
 learn+0.172
 great+0.171
Neg logit contributions
led-0.239
ed-0.197
ied-0.168
ked-0.163
awed-0.163
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
led+0.080
ed+0.067
ied+0.057
y+0.053
ing+0.053
Neg logit contributions
 pleasure-0.084
 Deal-0.078
 welcome-0.073
 deal-0.068
 meantime-0.067
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.315
ed+0.262
ling+0.238
ly+0.236
ied+0.235
Neg logit contributions
 pleasure-0.209
 Deal-0.174
 Today-0.148
 Sometimes-0.144
 welcome-0.142
Token of
Token ID286
Feature activation-1.25e+01

Pos logit contributions
 pleasure+1.256
 Deal+1.101
 welcome+1.097
 great+1.081
 learn+1.066
Neg logit contributions
led-1.550
ed-1.279
awed-1.094
ked-1.089
ied-1.052
Token something
Token ID1223
Feature activation+1.18e+01

Pos logit contributions
led+0.823
ed+0.699
ied+0.629
med+0.605
ted+0.602
Neg logit contributions
 Deal-0.564
 pleasure-0.530
 welcome-0.468
 Today-0.460
 deal-0.447
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.533
 great+0.458
 welcome+0.456
 think+0.424
 fun+0.421
Neg logit contributions
led-0.940
ed-0.799
ked-0.706
awed-0.690
ied-0.689
Token Suddenly
Token ID24975
Feature activation+4.62e+00

Pos logit contributions
led+0.369
ed+0.365
ted+0.288
y+0.278
awed+0.277
Neg logit contributions
 pleasure-0.294
 Deal-0.275
 welcome-0.256
 deal-0.255
 great-0.253
Token she
Token ID673
Feature activation-4.53e+00

Pos logit contributions
 pleasure+0.158
 welcome+0.127
 Deal+0.125
 great+0.124
 learn+0.120
Neg logit contributions
led-0.407
ed-0.349
ied-0.316
awed-0.312
ked-0.310
Token a
Token ID257
Feature activation+3.36e+00

Pos logit contributions
 pleasure+0.188
 Deal+0.165
 learn+0.155
 know+0.146
 think+0.145
Neg logit contributions
led-0.368
ed-0.314
ied-0.276
y-0.270
med-0.265
Token surprise
Token ID5975
Feature activation+1.31e+01

Pos logit contributions
 pleasure+0.138
 Deal+0.137
 learn+0.124
 know+0.123
 think+0.113
Neg logit contributions
led-0.207
ed-0.178
y-0.172
ling-0.161
lers-0.159
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.626
 welcome+0.574
 Deal+0.525
 great+0.512
 deal+0.507
Neg logit contributions
led-1.011
ed-0.829
awed-0.751
ked-0.737
ied-0.727
Token But
Token ID887
Feature activation+1.14e+01

Pos logit contributions
led+0.424
ed+0.397
ted+0.338
ked+0.328
med+0.326
Neg logit contributions
 pleasure-0.226
 plan-0.221
 great-0.215
 deal-0.204
 learn-0.203
Token I
Token ID314
Feature activation+3.13e+00

Pos logit contributions
 pleasure+0.438
 Deal+0.412
 learn+0.353
 meantime+0.345
 know+0.342
Neg logit contributions
led-0.887
ed-0.771
ied-0.689
ing-0.664
we-0.660
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.109
 Deal+0.098
 welcome+0.079
 meantime+0.074
 great+0.071
Neg logit contributions
led-0.260
ed-0.230
y-0.203
ling-0.190
ave-0.190
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.905
 Deal+0.790
 welcome+0.731
 learn+0.705
 think+0.681
Neg logit contributions
led-1.909
ed-1.649
ied-1.458
med-1.404
ked-1.403
Token will
Token ID481
Feature activation+4.69e+00

Pos logit contributions
 pleasure+0.355
 Deal+0.318
 welcome+0.274
 great+0.248
 meantime+0.241
Neg logit contributions
led-0.862
ed-0.748
ied-0.647
y-0.640
ked-0.640
Token like
Token ID588
Feature activation+4.80e+00

Pos logit contributions
 pleasure+0.195
 Deal+0.178
 meantime+0.135
 Promise+0.131
 Sometimes+0.129
Neg logit contributions
led-0.284
ed-0.258
y-0.247
ier-0.239
red-0.220
Token it
Token ID340
Feature activation+5.59e+00

Pos logit contributions
 pleasure+0.216
 Deal+0.195
 welcome+0.178
 learn+0.167
 think+0.163
Neg logit contributions
led-0.373
ed-0.319
ied-0.280
ted-0.272
med-0.272
Token.
Token ID13
Feature activation-5.87e+00

Pos logit contributions
 pleasure+0.294
 Deal+0.260
 welcome+0.259
 great+0.249
 learn+0.248
Neg logit contributions
led-0.394
ed-0.327
ied-0.284
awed-0.279
ked-0.277
Token picture
Token ID4286
Feature activation+4.91e+00

Pos logit contributions
 pleasure+0.170
 Deal+0.156
 welcome+0.134
 think+0.132
 know+0.130
Neg logit contributions
led-0.213
ed-0.179
ling-0.159
y-0.158
lers-0.155
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.243
 welcome+0.224
 Deal+0.214
 learn+0.212
 great+0.210
Neg logit contributions
led-0.352
ed-0.289
ked-0.257
awed-0.255
ied-0.254
Token What
Token ID1867
Feature activation+5.27e+00

Pos logit contributions
ed+0.294
led+0.289
med+0.254
als+0.252
es+0.250
Neg logit contributions
 plan-0.266
 great-0.231
 pleasure-0.229
 deal-0.227
 chores-0.223
Token do
Token ID466
Feature activation+7.66e+00

Pos logit contributions
 pleasure+0.222
 Deal+0.205
 welcome+0.171
 meantime+0.164
 think+0.158
Neg logit contributions
led-0.415
ed-0.354
ied-0.313
y-0.307
es-0.305
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.306
 Deal+0.259
 welcome+0.222
 meantime+0.210
 know+0.209
Neg logit contributions
led-0.637
ed-0.534
we-0.487
ied-0.479
es-0.467
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.439
 Deal+0.372
 Sometimes+0.311
 meantime+0.299
 welcome+0.296
Neg logit contributions
led-0.719
ed-0.622
y-0.556
ave-0.525
ier-0.521
Token?"
Token ID1701
Feature activation+7.09e+00

Pos logit contributions
 pleasure+1.088
 Deal+0.964
 welcome+0.888
 learn+0.855
 think+0.838
Neg logit contributions
led-1.753
ed-1.487
ied-1.306
med-1.250
ted-1.235
Token
Token ID198
Feature activation+9.27e+00

Pos logit contributions
 pleasure+0.288
 Deal+0.240
 great+0.229
 deal+0.227
 plan+0.218
Neg logit contributions
led-0.533
ed-0.493
ted-0.428
awed-0.427
es-0.420
Token
Token ID198
Feature activation+9.25e+00

Pos logit contributions
 pleasure+0.357
 Deal+0.284
 deal+0.255
 great+0.247
 welcome+0.242
Neg logit contributions
led-0.768
ed-0.681
awed-0.608
ied-0.602
med-0.597
TokenAnna
Token ID31160
Feature activation-7.19e+00

Pos logit contributions
 pleasure+0.491
 Deal+0.425
 welcome+0.401
 great+0.389
 learn+0.381
Neg logit contributions
led-0.653
ed-0.553
ied-0.474
awed-0.468
med-0.462
Token and
Token ID290
Feature activation+3.59e+00

Pos logit contributions
led+0.481
ed+0.397
ied+0.342
ked+0.328
awed+0.326
Neg logit contributions
 pleasure-0.400
 Deal-0.361
 welcome-0.348
 learn-0.340
 think-0.337
Token kind
Token ID1611
Feature activation-1.53e+00

Pos logit contributions
 pleasure+0.181
 Deal+0.153
 welcome+0.139
 learn+0.132
 great+0.129
Neg logit contributions
led-0.466
ed-0.405
ied-0.360
ked-0.351
awed-0.350
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
led+0.117
ed+0.093
awed+0.087
ied+0.086
ked+0.084
Neg logit contributions
 pleasure-0.073
 welcome-0.066
 learn-0.061
 Deal-0.061
 think-0.059
Token responsible
Token ID4497
Feature activation-4.72e-01

Pos logit contributions
 pleasure+0.145
 Deal+0.134
 meantime+0.116
 Today+0.109
 welcome+0.108
Neg logit contributions
led-0.287
ed-0.246
ked-0.215
ied-0.208
ted-0.207
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
led+0.033
ed+0.027
awed+0.025
ked+0.024
ied+0.024
Neg logit contributions
 pleasure-0.025
 welcome-0.022
 Deal-0.022
 learn-0.021
 great-0.021
Token We
Token ID775
Feature activation+3.98e+00

Pos logit contributions
led+0.380
ed+0.363
ted+0.317
ked+0.304
med+0.303
Neg logit contributions
 plan-0.240
 pleasure-0.227
 great-0.219
 deal-0.218
 learn-0.197
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.147
 Deal+0.137
 welcome+0.110
 meantime+0.105
 great+0.104
Neg logit contributions
led-0.321
ed-0.287
y-0.247
ked-0.244
ied-0.241
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.963
 Deal+0.854
 welcome+0.782
 learn+0.753
 think+0.736
Neg logit contributions
led-1.851
ed-1.589
ied-1.400
ked-1.348
ted-1.345
Token are
Token ID389
Feature activation+8.87e+00

Pos logit contributions
 pleasure+0.369
 Deal+0.348
 welcome+0.287
 meantime+0.268
 Today+0.258
Neg logit contributions
led-0.835
ed-0.729
y-0.623
ied-0.617
ked-0.615
Token ready
Token ID3492
Feature activation+3.47e+00

Pos logit contributions
 pleasure+0.340
 Deal+0.300
 welcome+0.260
 learn+0.258
 think+0.250
Neg logit contributions
led-0.743
ed-0.638
ied-0.561
ked-0.552
med-0.547
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
 pleasure+0.190
 Deal+0.174
 welcome+0.162
 learn+0.156
 great+0.155
Neg logit contributions
led-0.235
ed-0.197
ied-0.167
ked-0.159
y-0.159
Token have
Token ID423
Feature activation+1.00e+01

Pos logit contributions
led+0.281
ed+0.246
y+0.229
med+0.225
ted+0.224
Neg logit contributions
 pleasure-0.175
 Deal-0.165
 Today-0.122
 meantime-0.119
 Sometimes-0.118
Token cones
Token ID47314
Feature activation-4.74e+00

Pos logit contributions
 pleasure+0.013
 Deal+0.012
 welcome+0.011
 learn+0.011
 think+0.011
Neg logit contributions
led-0.019
ed-0.016
ied-0.013
ked-0.013
awed-0.013
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
led+0.324
ed+0.270
awed+0.235
ked+0.234
ied+0.231
Neg logit contributions
 pleasure-0.235
 learn-0.221
 welcome-0.216
 think-0.210
 have-0.204
Token smile
Token ID8212
Feature activation+1.00e+01

Pos logit contributions
 pleasure+0.152
 Deal+0.132
 welcome+0.122
 great+0.116
 learn+0.111
Neg logit contributions
led-0.289
ed-0.247
ked-0.211
ted-0.209
med-0.207
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.466
 great+0.426
 learn+0.423
 welcome+0.414
 OK+0.411
Neg logit contributions
led-0.713
ied-0.577
ed-0.554
awed-0.535
web-0.504
Token They
Token ID1119
Feature activation+1.25e+00

Pos logit contributions
led+0.436
ed+0.408
ted+0.337
awed+0.331
ked+0.331
Neg logit contributions
 pleasure-0.251
 Deal-0.226
 deal-0.215
 meantime-0.206
 great-0.205
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.041
 Deal+0.035
 welcome+0.028
 Today+0.027
 meantime+0.027
Neg logit contributions
led-0.109
ed-0.095
ked-0.084
ted-0.082
y-0.082
Token it
Token ID340
Feature activation+5.58e+00

Pos logit contributions
 pleasure+0.987
 Deal+0.835
 welcome+0.811
 great+0.783
 learn+0.774
Neg logit contributions
led-1.841
ed-1.586
ied-1.369
ked-1.365
awed-1.361
Token is
Token ID318
Feature activation+4.65e+00

Pos logit contributions
 pleasure+0.191
 Deal+0.158
 welcome+0.151
 great+0.148
 learn+0.146
Neg logit contributions
led-0.490
ed-0.426
ied-0.386
ked-0.379
awed-0.374
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
 pleasure+0.162
 Deal+0.143
 learn+0.124
 welcome+0.122
 think+0.114
Neg logit contributions
led-0.405
ed-0.346
ied-0.307
ked-0.299
y-0.299
Token best
Token ID1266
Feature activation+5.40e+00

Pos logit contributions
led+0.142
ed+0.124
ier+0.111
y+0.109
ling+0.108
Neg logit contributions
 pleasure-0.071
 Deal-0.068
 know-0.062
 learn-0.061
 Not-0.058
Token ice
Token ID4771
Feature activation+3.44e+00

Pos logit contributions
 pleasure+0.227
 Deal+0.207
 welcome+0.184
 learn+0.181
 great+0.175
Neg logit contributions
led-0.427
ed-0.372
ied-0.325
y-0.315
awed-0.314
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
led+0.037
ed+0.030
ied+0.025
ked+0.024
awed+0.024
Neg logit contributions
 pleasure-0.033
 Deal-0.030
 welcome-0.029
 learn-0.028
 great-0.028
Token tell
Token ID1560
Feature activation+1.08e+01

Pos logit contributions
led+0.304
ling+0.252
ed+0.250
y+0.244
ied+0.238
Neg logit contributions
 pleasure-0.166
 Deal-0.148
 Today-0.130
 meantime-0.119
 Anything-0.106
Token someone
Token ID2130
Feature activation+5.55e+00

Pos logit contributions
 pleasure+0.446
 Deal+0.406
 welcome+0.350
 meantime+0.331
 learn+0.331
Neg logit contributions
led-0.873
ed-0.754
ied-0.670
ted-0.641
ked-0.634
Token if
Token ID611
Feature activation+4.35e+00

Pos logit contributions
 pleasure+0.276
 welcome+0.238
 great+0.231
 learn+0.229
 Deal+0.226
Neg logit contributions
led-0.408
ed-0.344
awed-0.300
ked-0.299
ied-0.295
Token we
Token ID356
Feature activation+5.29e+00

Pos logit contributions
 pleasure+0.150
 Deal+0.131
 welcome+0.115
 learn+0.108
 great+0.106
Neg logit contributions
led-0.385
ed-0.336
ied-0.298
ked-0.289
ted-0.287
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.178
 Deal+0.152
 welcome+0.131
 great+0.124
 learn+0.118
Neg logit contributions
led-0.471
ed-0.413
ied-0.363
ked-0.358
ted-0.352
Token there
Token ID612
Feature activation-2.69e+00

Pos logit contributions
 pleasure+1.210
 Deal+1.072
 welcome+1.042
 learn+1.004
 great+0.998
Neg logit contributions
led-1.607
ed-1.347
ied-1.147
awed-1.124
ked-1.122
Token's
Token ID338
Feature activation-2.79e+00

Pos logit contributions
led+0.220
ed+0.191
ied+0.167
y+0.161
ling+0.160
Neg logit contributions
 pleasure-0.110
 Deal-0.100
 welcome-0.086
 learn-0.081
 great-0.080
Token a
Token ID257
Feature activation+3.35e+00

Pos logit contributions
led+0.215
ed+0.185
ied+0.158
ier+0.156
ling+0.156
Neg logit contributions
 pleasure-0.112
 Deal-0.103
 welcome-0.085
 learn-0.082
 deal-0.081
Token monster
Token ID9234
Feature activation-5.52e+00

Pos logit contributions
 Deal+0.121
 pleasure+0.116
 Today+0.092
 Not+0.088
 learn+0.087
Neg logit contributions
led-0.235
ed-0.204
ling-0.196
y-0.193
ier-0.187
Token in
Token ID287
Feature activation-1.19e+01

Pos logit contributions
led+0.391
ed+0.317
ied+0.288
awed+0.284
ked+0.273
Neg logit contributions
 pleasure-0.280
 welcome-0.256
 learn-0.248
 think-0.246
 great-0.243
Token about
Token ID546
Feature activation-1.96e+00

Pos logit contributions
 pleasure+0.213
 welcome+0.187
 Deal+0.182
 learn+0.177
 great+0.176
Neg logit contributions
led-0.281
ed-0.231
awed-0.201
ked-0.200
ied-0.198
Token that
Token ID326
Feature activation-9.92e-01

Pos logit contributions
led+0.148
ed+0.127
ied+0.112
y+0.108
med+0.106
Neg logit contributions
 pleasure-0.083
 Deal-0.082
 welcome-0.067
 learn-0.066
 deal-0.064
Token garden
Token ID11376
Feature activation+4.71e+00

Pos logit contributions
led+0.081
ed+0.070
ied+0.061
y+0.059
ling+0.059
Neg logit contributions
 pleasure-0.040
 Deal-0.037
 welcome-0.031
 learn-0.031
 great-0.029
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.224
 welcome+0.192
 Deal+0.190
 great+0.183
 learn+0.182
Neg logit contributions
led-0.355
ed-0.302
ied-0.261
ked-0.261
awed-0.260
Token I
Token ID314
Feature activation+3.13e+00

Pos logit contributions
led+0.345
ed+0.345
med+0.293
ted+0.293
als+0.284
Neg logit contributions
 great-0.246
 plan-0.244
 deal-0.236
 pleasure-0.235
 fun-0.224
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.101
 Deal+0.088
 welcome+0.074
 great+0.067
 deal+0.064
Neg logit contributions
led-0.280
ed-0.249
y-0.214
ied-0.213
ked-0.209
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.961
 Deal+0.885
 welcome+0.784
 learn+0.753
 great+0.733
Neg logit contributions
led-1.828
ed-1.577
ied-1.391
med-1.321
ked-1.315
Token'll
Token ID1183
Feature activation+6.61e+00

Pos logit contributions
 pleasure+0.405
 Deal+0.367
 welcome+0.327
 great+0.304
 learn+0.298
Neg logit contributions
led-0.808
ed-0.702
ied-0.603
ked-0.592
y-0.589
Token love
Token ID1842
Feature activation+1.49e+01

Pos logit contributions
 pleasure+0.237
 Deal+0.233
 Today+0.159
 meantime+0.158
 Sometimes+0.156
Neg logit contributions
led-0.457
ed-0.414
y-0.382
ier-0.380
ied-0.361
Token it
Token ID340
Feature activation+5.59e+00

Pos logit contributions
 pleasure+0.698
 Deal+0.655
 welcome+0.576
 learn+0.548
 deal+0.541
Neg logit contributions
led-1.127
ed-0.965
ied-0.840
med-0.820
y-0.819
Token."
Token ID526
Feature activation+2.37e+00

Pos logit contributions
 pleasure+0.261
 Deal+0.237
 welcome+0.215
 learn+0.210
 think+0.205
Neg logit contributions
led-0.425
ed-0.365
ied-0.311
y-0.303
ier-0.299
Token busy
Token ID8179
Feature activation+3.62e+00

Pos logit contributions
 pleasure+0.396
 Deal+0.338
 welcome+0.321
 learn+0.304
 great+0.301
Neg logit contributions
led-0.843
ed-0.729
ied-0.642
ked-0.628
awed-0.627
Token that
Token ID326
Feature activation-9.82e-01

Pos logit contributions
 pleasure+0.152
 welcome+0.129
 great+0.127
 learn+0.127
 think+0.126
Neg logit contributions
led-0.288
ed-0.243
ied-0.217
ked-0.214
awed-0.210
Token he
Token ID339
Feature activation-5.97e+00

Pos logit contributions
led+0.059
ed+0.048
ied+0.039
ling+0.037
ted+0.037
Neg logit contributions
 pleasure-0.062
 Deal-0.058
 welcome-0.053
 learn-0.051
 think-0.051
Token couldn
Token ID3521
Feature activation-3.25e+00

Pos logit contributions
led+0.415
ed+0.355
ied+0.317
awed+0.313
ier+0.311
Neg logit contributions
 pleasure-0.261
 great-0.258
 think-0.249
 learn-0.243
 have-0.240
Token't
Token ID470
Feature activation+3.06e+00

Pos logit contributions
led+0.285
ed+0.255
ied+0.223
med+0.219
ted+0.217
Neg logit contributions
 pleasure-0.116
 Deal-0.092
 welcome-0.084
 great-0.076
 think-0.075
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.089
 Deal+0.073
 welcome+0.061
 great+0.055
 meantime+0.049
Neg logit contributions
led-0.286
ed-0.254
ked-0.224
ied-0.223
y-0.220
Token straight
Token ID3892
Feature activation-8.09e+00

Pos logit contributions
 pleasure+1.247
 welcome+1.093
 Deal+1.091
 great+1.063
 learn+1.056
Neg logit contributions
led-1.577
ed-1.309
awed-1.109
ked-1.105
ied-1.089
Token!
Token ID0
Feature activation-2.03e+00

Pos logit contributions
led+0.562
ed+0.466
ied+0.404
awed+0.397
ked+0.391
Neg logit contributions
 pleasure-0.433
 welcome-0.376
 Deal-0.376
 great-0.366
 learn-0.362
Token
Token ID198
Feature activation+9.25e+00

Pos logit contributions
led+0.158
ed+0.151
awed+0.126
ted+0.124
ied+0.122
Neg logit contributions
 pleasure-0.078
 Deal-0.065
 deal-0.062
 learn-0.062
 welcome-0.061
Token
Token ID198
Feature activation+9.27e+00

Pos logit contributions
 pleasure+0.394
 Deal+0.333
 deal+0.285
 welcome+0.283
 learn+0.256
Neg logit contributions
led-0.743
ed-0.664
ied-0.587
y-0.581
awed-0.569
TokenThe
Token ID464
Feature activation-5.59e+00

Pos logit contributions
 pleasure+0.379
 Deal+0.316
 welcome+0.300
 learn+0.275
 great+0.273
Neg logit contributions
led-0.781
ed-0.675
ied-0.597
awed-0.580
ked-0.578
Token of
Token ID286
Feature activation-1.25e+01

Pos logit contributions
 pleasure+0.564
 great+0.508
 welcome+0.496
 learn+0.472
 have+0.466
Neg logit contributions
led-0.858
ed-0.688
awed-0.643
ked-0.642
ied-0.604
Token it
Token ID340
Feature activation+5.59e+00

Pos logit contributions
led+0.907
ed+0.770
ied+0.678
med+0.663
ted+0.653
Neg logit contributions
 pleasure-0.595
 Deal-0.548
 welcome-0.491
 learn-0.470
 deal-0.467
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.276
 great+0.254
 welcome+0.251
 learn+0.245
 think+0.244
Neg logit contributions
led-0.387
ed-0.322
ked-0.292
ied-0.290
awed-0.287
Token Molly
Token ID30236
Feature activation-2.70e+00

Pos logit contributions
led+0.424
ed+0.387
ied+0.323
y+0.323
ted+0.318
Neg logit contributions
 pleasure-0.240
 welcome-0.208
 Deal-0.205
 deal-0.204
 great-0.203
Token would
Token ID561
Feature activation-5.10e+00

Pos logit contributions
led+0.185
ed+0.153
ied+0.134
ked+0.130
awed+0.130
Neg logit contributions
 pleasure-0.141
 learn-0.124
 think-0.123
 great-0.122
 welcome-0.121
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.405
ed+0.354
ied+0.318
y+0.317
med+0.310
Neg logit contributions
 pleasure-0.180
 Deal-0.168
 welcome-0.133
 great-0.126
 OK-0.126
Token a
Token ID257
Feature activation+3.35e+00

Pos logit contributions
 pleasure+1.138
 Deal+0.976
 welcome+0.964
 great+0.950
 learn+0.939
Neg logit contributions
led-1.683
ed-1.423
ked-1.216
awed-1.210
ied-1.204
Token lot
Token ID1256
Feature activation+1.17e+01

Pos logit contributions
 Deal+0.100
 pleasure+0.094
 welcome+0.071
 OK+0.068
 learn+0.066
Neg logit contributions
led-0.269
ed-0.236
y-0.227
ling-0.220
mer-0.214
Token about
Token ID546
Feature activation-1.98e+00

Pos logit contributions
 pleasure+0.584
 welcome+0.525
 great+0.506
 learn+0.498
 think+0.480
Neg logit contributions
led-0.844
ed-0.705
awed-0.630
ked-0.628
ied-0.588
Token her
Token ID607
Feature activation-2.32e+00

Pos logit contributions
led+0.151
ed+0.131
ied+0.113
med+0.110
y+0.110
Neg logit contributions
 pleasure-0.087
 Deal-0.082
 welcome-0.072
 learn-0.067
 deal-0.066
Token team
Token ID1074
Feature activation+2.94e+00

Pos logit contributions
led+0.195
ed+0.171
ied+0.148
y+0.146
ling+0.145
Neg logit contributions
 pleasure-0.081
 Deal-0.076
 welcome-0.066
 learn-0.061
 know-0.061
Token to
Token ID284
Feature activation-4.44e+00

Pos logit contributions
 pleasure+0.692
 welcome+0.606
 Deal+0.583
 learn+0.569
 great+0.568
Neg logit contributions
led-1.046
ed-0.876
awed-0.761
ked-0.759
ied-0.755
Token do
Token ID466
Feature activation+7.67e+00

Pos logit contributions
led+0.310
ed+0.261
ied+0.235
ling+0.233
ier+0.232
Neg logit contributions
 pleasure-0.193
 Deal-0.175
 Today-0.143
 meantime-0.133
 Okay-0.126
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.375
 Deal+0.331
 welcome+0.318
 learn+0.305
 great+0.303
Neg logit contributions
led-0.570
ed-0.483
ied-0.417
ked-0.406
awed-0.405
Token Do
Token ID2141
Feature activation+4.69e+00

Pos logit contributions
led+0.372
ed+0.361
ted+0.309
med+0.303
ked+0.303
Neg logit contributions
 pleasure-0.237
 great-0.235
 plan-0.232
 deal-0.216
 meantime-0.209
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.214
 Deal+0.171
 welcome+0.157
 meantime+0.151
 Today+0.147
Neg logit contributions
led-0.348
ed-0.294
ied-0.277
es-0.267
ing-0.264
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.327
 Deal+0.280
 meantime+0.215
 great+0.210
 welcome+0.206
Neg logit contributions
led-0.832
ed-0.722
y-0.646
ling-0.640
ier-0.639
Token you
Token ID345
Feature activation+9.88e+00

Pos logit contributions
 pleasure+1.162
 Deal+1.056
 welcome+0.965
 learn+0.932
 great+0.917
Neg logit contributions
led-1.648
ed-1.390
ied-1.205
med-1.154
ted-1.146
Token will
Token ID481
Feature activation+4.68e+00

Pos logit contributions
 pleasure+0.435
 Deal+0.402
 welcome+0.342
 meantime+0.327
 great+0.320
Neg logit contributions
led-0.763
ed-0.662
y-0.562
ied-0.558
ked-0.552
Token succeed
Token ID6758
Feature activation+7.81e+00

Pos logit contributions
 pleasure+0.180
 Deal+0.166
 meantime+0.116
 Today+0.111
 Sometimes+0.110
Neg logit contributions
led-0.312
ed-0.287
ier-0.270
y-0.269
es-0.254
Token?"
Token ID1701
Feature activation+7.09e+00

Pos logit contributions
 pleasure+0.329
 Deal+0.287
 welcome+0.260
 learn+0.246
 great+0.242
Neg logit contributions
led-0.639
ed-0.547
ied-0.478
ling-0.468
y-0.467
Token
Token ID220
Feature activation+1.55e+01

Pos logit contributions
 pleasure+0.212
 Deal+0.173
 great+0.156
 welcome+0.149
 deal+0.149
Neg logit contributions
led-0.642
ed-0.577
ted-0.503
awed-0.499
med-0.499
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
led+0.484
ed+0.395
ied+0.392
awed+0.378
we+0.372
Neg logit contributions
 pleasure-0.245
 welcome-0.205
 great-0.204
 Deal-0.195
 OK-0.189
Token said
Token ID531
Feature activation-1.48e+00

Pos logit contributions
 pleasure+0.174
 welcome+0.150
 great+0.148
 think+0.148
 learn+0.143
Neg logit contributions
led-0.256
ed-0.215
ied-0.194
ier-0.188
awed-0.185
Token,
Token ID11
Feature activation+5.37e+00

Pos logit contributions
led+0.130
ed+0.111
awed+0.101
ied+0.101
ked+0.099
Neg logit contributions
 pleasure-0.050
 welcome-0.042
 great-0.041
 Deal-0.040
 learn-0.038
Token "
Token ID366
Feature activation+2.25e-01

Pos logit contributions
 pleasure+0.214
 Deal+0.183
 welcome+0.173
 learn+0.164
 great+0.162
Neg logit contributions
led-0.447
ed-0.388
ied-0.339
ked-0.334
awed-0.331
TokenI
Token ID40
Feature activation-7.58e+00

Pos logit contributions
 pleasure+0.010
 Deal+0.009
 welcome+0.009
 great+0.008
 learn+0.008
Neg logit contributions
led-0.017
ed-0.015
ied-0.013
ked-0.013
awed-0.013
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.615
ed+0.569
y+0.495
ave+0.464
ier+0.461
Neg logit contributions
 Deal-0.245
 pleasure-0.240
 meantime-0.171
 welcome-0.169
 compromise-0.158
Token there
Token ID612
Feature activation-2.70e+00

Pos logit contributions
 pleasure+0.869
 Deal+0.737
 welcome+0.697
 learn+0.659
 great+0.653
Neg logit contributions
led-1.952
ed-1.691
ied-1.492
ked-1.461
awed-1.459
Token is
Token ID318
Feature activation+4.65e+00

Pos logit contributions
led+0.215
ed+0.185
ied+0.161
y+0.156
awed+0.154
Neg logit contributions
 pleasure-0.116
 Deal-0.105
 welcome-0.094
 learn-0.089
 great-0.088
Token some
Token ID617
Feature activation+4.19e+00

Pos logit contributions
 pleasure+0.168
 Deal+0.139
 welcome+0.134
 great+0.126
 learn+0.125
Neg logit contributions
led-0.406
ed-0.351
ied-0.312
awed-0.307
ked-0.306
Token wool
Token ID25749
Feature activation-2.06e+00

Pos logit contributions
 pleasure+0.197
 welcome+0.171
 great+0.165
 Deal+0.164
 learn+0.158
Neg logit contributions
led-0.322
ed-0.277
ked-0.240
awed-0.239
ied-0.237
Token in
Token ID287
Feature activation-1.19e+01

Pos logit contributions
led+0.138
ed+0.112
awed+0.105
ied+0.099
ked+0.097
Neg logit contributions
 pleasure-0.108
 welcome-0.100
 learn-0.095
 great-0.094
 think-0.093
Token ice
Token ID4771
Feature activation+3.43e+00

Pos logit contributions
led+0.147
ed+0.125
ied+0.108
awed+0.105
ked+0.105
Neg logit contributions
 pleasure-0.093
 Deal-0.082
 welcome-0.079
 learn-0.076
 great-0.075
Token.
Token ID13
Feature activation-5.87e+00

Pos logit contributions
 pleasure+0.153
 welcome+0.149
 learn+0.148
 deal+0.145
 think+0.141
Neg logit contributions
led-0.234
ed-0.198
ked-0.179
med-0.177
awed-0.177
Token Anna
Token ID11735
Feature activation-3.27e+00

Pos logit contributions
led+0.397
ed+0.365
ked+0.308
ted+0.307
med+0.295
Neg logit contributions
 pleasure-0.270
 Deal-0.246
 plan-0.237
 deal-0.235
 promise-0.231
Token and
Token ID290
Feature activation+3.59e+00

Pos logit contributions
led+0.243
ed+0.203
ied+0.182
ked+0.174
awed+0.173
Neg logit contributions
 pleasure-0.157
 Deal-0.138
 welcome-0.136
 learn-0.133
 think-0.131
Token Ben
Token ID3932
Feature activation-2.14e+00

Pos logit contributions
 pleasure+0.129
 Deal+0.108
 welcome+0.101
 learn+0.095
 great+0.094
Neg logit contributions
led-0.317
ed-0.276
ied-0.244
ked-0.240
awed-0.239
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.190
ed+0.166
ked+0.146
ling+0.144
ted+0.142
Neg logit contributions
 pleasure-0.072
 Deal-0.061
 welcome-0.050
 great-0.048
 meantime-0.046
Token they
Token ID484
Feature activation-2.04e+00

Pos logit contributions
 pleasure+0.898
 welcome+0.748
 great+0.728
 learn+0.707
 Deal+0.680
Neg logit contributions
led-1.921
ed-1.667
ked-1.481
awed-1.475
ied-1.436
Token are
Token ID389
Feature activation+8.86e+00

Pos logit contributions
led+0.184
ed+0.160
ling+0.139
y+0.138
lers+0.138
Neg logit contributions
 pleasure-0.067
 Deal-0.058
 welcome-0.048
 meantime-0.041
 great-0.040
Token funny
Token ID8258
Feature activation+4.90e+00

Pos logit contributions
 pleasure+0.328
 welcome+0.282
 Deal+0.273
 great+0.264
 learn+0.253
Neg logit contributions
led-0.769
ed-0.671
ied-0.598
awed-0.585
ked-0.578
Token.
Token ID13
Feature activation-5.87e+00

Pos logit contributions
 pleasure+0.212
 welcome+0.199
 fun+0.191
 love+0.184
 OK+0.184
Neg logit contributions
led-0.369
ed-0.292
ied-0.282
ked-0.272
awed-0.269
Token They
Token ID1119
Feature activation+1.26e+00

Pos logit contributions
led+0.410
ed+0.374
ted+0.307
y+0.304
ked+0.298
Neg logit contributions
 pleasure-0.285
 Deal-0.243
 deal-0.238
 plan-0.233
 learn-0.230
Token cat
Token ID3797
Feature activation-4.92e+00

Pos logit contributions
led+0.357
ed+0.298
ked+0.247
awed+0.245
ted+0.245
Neg logit contributions
 pleasure-0.327
 Deal-0.290
 welcome-0.258
 think-0.252
 know-0.252
Token said
Token ID531
Feature activation-1.48e+00

Pos logit contributions
led+0.359
ed+0.296
ied+0.280
ier+0.273
ked+0.263
Neg logit contributions
 pleasure-0.205
 think-0.201
 learn-0.198
 great-0.190
 know-0.189
Token,
Token ID11
Feature activation+5.37e+00

Pos logit contributions
led+0.129
ed+0.111
ied+0.099
awed+0.098
ked+0.097
Neg logit contributions
 pleasure-0.052
 welcome-0.044
 Deal-0.043
 great-0.041
 learn-0.040
Token "
Token ID366
Feature activation+2.25e-01

Pos logit contributions
 pleasure+0.219
 Deal+0.188
 welcome+0.176
 learn+0.168
 great+0.166
Neg logit contributions
led-0.443
ed-0.385
ied-0.336
ked-0.332
awed-0.327
TokenI
Token ID40
Feature activation-7.58e+00

Pos logit contributions
 pleasure+0.011
 Deal+0.010
 welcome+0.009
 learn+0.009
 great+0.009
Neg logit contributions
led-0.017
ed-0.014
ied-0.012
ked-0.012
awed-0.012
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.639
ed+0.576
y+0.506
ked+0.479
ied+0.477
Neg logit contributions
 pleasure-0.262
 Deal-0.243
 welcome-0.183
 meantime-0.179
 great-0.169
Token we
Token ID356
Feature activation+5.28e+00

Pos logit contributions
 pleasure+0.964
 Deal+0.867
 welcome+0.774
 learn+0.753
 think+0.730
Neg logit contributions
led-1.844
ed-1.587
ied-1.389
ked-1.347
med-1.344
Token should
Token ID815
Feature activation-5.81e+00

Pos logit contributions
 pleasure+0.201
 Deal+0.176
 welcome+0.156
 great+0.144
 learn+0.143
Neg logit contributions
led-0.447
ed-0.391
ied-0.338
ked-0.336
y-0.332
Token cut
Token ID2005
Feature activation-3.98e+00

Pos logit contributions
led+0.418
ed+0.365
y+0.340
ly+0.331
ling+0.324
Neg logit contributions
 pleasure-0.219
 Deal-0.194
 meantime-0.140
 Today-0.140
 great-0.136
Token the
Token ID262
Feature activation-1.96e+00

Pos logit contributions
led+0.305
ed+0.262
ing+0.222
ied+0.221
ted+0.217
Neg logit contributions
 pleasure-0.191
 Deal-0.172
 welcome-0.150
 meantime-0.144
 learn-0.143
Token pepper
Token ID13385
Feature activation-4.34e+00

Pos logit contributions
led+0.117
ed+0.096
ling+0.076
ked+0.075
ied+0.075
Neg logit contributions
 pleasure-0.125
 Deal-0.117
 welcome-0.106
 learn-0.104
 think-0.102
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
led+0.163
ed+0.129
ied+0.117
awed+0.115
attered+0.114
Neg logit contributions
 pleasure-0.099
 Deal-0.095
 welcome-0.094
 learn-0.089
 OK-0.089
Token
Token ID198
Feature activation+9.27e+00

Pos logit contributions
led+0.452
ed+0.412
ked+0.350
ted+0.345
awed+0.344
Neg logit contributions
 pleasure-0.261
 Deal-0.211
 welcome-0.198
 great-0.198
 deal-0.197
Token
Token ID198
Feature activation+9.25e+00

Pos logit contributions
 pleasure+0.396
 Deal+0.294
 deal+0.278
 welcome+0.263
 great+0.261
Neg logit contributions
led-0.734
ed-0.673
awed-0.586
ied-0.583
med-0.577
Token"
Token ID1
Feature activation-3.34e-01

Pos logit contributions
 pleasure+0.474
 Deal+0.391
 welcome+0.372
 great+0.357
 deal+0.347
Neg logit contributions
led-0.682
ed-0.591
ied-0.501
awed-0.497
med-0.493
TokenI
Token ID40
Feature activation-7.58e+00

Pos logit contributions
led+0.028
ed+0.025
ied+0.022
ked+0.021
awed+0.021
Neg logit contributions
 pleasure-0.013
 Deal-0.011
 welcome-0.010
 learn-0.010
 great-0.010
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.653
ed+0.587
y+0.505
ied+0.484
ked+0.484
Neg logit contributions
 pleasure-0.268
 Deal-0.243
 welcome-0.199
 meantime-0.182
 learn-0.171
Token so
Token ID523
Feature activation+9.96e+00

Pos logit contributions
 pleasure+0.860
 Deal+0.739
 welcome+0.680
 learn+0.646
 great+0.628
Neg logit contributions
led-1.960
ed-1.702
ied-1.505
ked-1.460
awed-1.454
Token,
Token ID11
Feature activation+5.38e+00

Pos logit contributions
 pleasure+0.576
 Deal+0.512
 meantime+0.428
 discuss+0.426
 learn+0.422
Neg logit contributions
led-0.618
ed-0.504
y-0.470
es-0.436
ing-0.436
Token Lily
Token ID20037
Feature activation-6.01e-02

Pos logit contributions
 pleasure+0.256
 Deal+0.213
 learn+0.202
 welcome+0.195
 meantime+0.195
Neg logit contributions
led-0.349
ed-0.296
ly-0.269
ier-0.257
ted-0.255
Token,"
Token ID553
Feature activation+3.90e+00

Pos logit contributions
led+0.005
ed+0.004
ked+0.004
ied+0.004
awed+0.003
Neg logit contributions
 pleasure-0.003
 welcome-0.003
 think-0.002
 have-0.002
 great-0.002
Token Tom
Token ID4186
Feature activation+1.37e+00

Pos logit contributions
 pleasure+0.209
 Deal+0.174
 welcome+0.162
 great+0.160
 compromise+0.153
Neg logit contributions
led-0.231
ed-0.199
ted-0.182
y-0.169
ked-0.168
Token away
Token ID1497
Feature activation-1.07e+00

Pos logit contributions
led+0.288
ed+0.245
awed+0.222
ied+0.219
med+0.218
Neg logit contributions
 pleasure-0.207
 welcome-0.193
 great-0.187
 think-0.184
 try-0.176
Token.
Token ID13
Feature activation-5.87e+00

Pos logit contributions
led+0.075
ed+0.061
awed+0.056
ked+0.056
med+0.056
Neg logit contributions
 pleasure-0.053
 welcome-0.049
 great-0.047
 think-0.045
 learn-0.045
Token She
Token ID1375
Feature activation-3.82e+00

Pos logit contributions
led+0.437
ed+0.398
ied+0.334
awed+0.332
ted+0.328
Neg logit contributions
 pleasure-0.259
 Deal-0.230
 welcome-0.217
 deal-0.213
 great-0.212
Token tried
Token ID3088
Feature activation-1.33e+00

Pos logit contributions
led+0.245
ed+0.203
ied+0.177
awed+0.173
ier+0.173
Neg logit contributions
 pleasure-0.208
 think-0.191
 learn-0.186
 great-0.185
 know-0.183
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
led+0.074
ed+0.063
ied+0.051
ing+0.049
y+0.048
Neg logit contributions
 pleasure-0.087
 Deal-0.081
 welcome-0.075
 deal-0.072
 great-0.071
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.316
ed+0.265
ling+0.247
ked+0.240
ried+0.231
Neg logit contributions
 pleasure-0.198
 Deal-0.177
 Today-0.158
 meantime-0.153
 Not-0.148
Token of
Token ID286
Feature activation-1.25e+01

Pos logit contributions
 pleasure+1.216
 Deal+1.062
 welcome+1.053
 great+1.026
 learn+1.017
Neg logit contributions
led-1.589
ed-1.320
awed-1.121
ked-1.119
ied-1.104
Token a
Token ID257
Feature activation+3.36e+00

Pos logit contributions
led+0.844
ed+0.718
ied+0.639
ted+0.630
ing+0.607
Neg logit contributions
 Deal-0.554
 pleasure-0.514
 Today-0.459
 welcome-0.452
 deal-0.442
Token way
Token ID835
Feature activation+1.07e+01

Pos logit contributions
 Deal+0.129
 pleasure+0.125
 learn+0.105
 welcome+0.099
 Not+0.098
Neg logit contributions
led-0.254
ed-0.219
ling-0.201
y-0.200
ied-0.192
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
 pleasure+0.548
 welcome+0.483
 Deal+0.463
 learn+0.455
 great+0.450
Neg logit contributions
led-0.790
ed-0.645
awed-0.564
ked-0.554
ied-0.547
Token help
Token ID1037
Feature activation+7.33e+00

Pos logit contributions
led+0.344
ed+0.291
ling+0.262
ked+0.260
ied+0.260
Neg logit contributions
 pleasure-0.174
 Deal-0.168
 Today-0.136
 meantime-0.126
 welcome-0.124
Token't
Token ID470
Feature activation+3.06e+00

Pos logit contributions
 pleasure+0.186
 Deal+0.136
 welcome+0.135
 deal+0.125
 compromise+0.119
Neg logit contributions
led-0.343
ed-0.305
ied-0.270
med-0.267
ier-0.259
Token want
Token ID765
Feature activation+1.08e+01

Pos logit contributions
 pleasure+0.097
 Deal+0.080
 welcome+0.065
 great+0.062
 learn+0.058
Neg logit contributions
led-0.281
ed-0.247
ied-0.218
y-0.216
ked-0.216
Token his
Token ID465
Feature activation-3.15e+00

Pos logit contributions
 pleasure+0.632
 Deal+0.572
 welcome+0.549
 learn+0.532
 great+0.528
Neg logit contributions
led-0.701
ed-0.579
ied-0.486
ked-0.469
awed-0.467
Token friends
Token ID2460
Feature activation+3.55e+00

Pos logit contributions
led+0.248
ed+0.217
ied+0.188
ked+0.181
y+0.181
Neg logit contributions
 pleasure-0.132
 Deal-0.123
 welcome-0.105
 meantime-0.099
 learn-0.099
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
 pleasure+0.199
 welcome+0.176
 Deal+0.176
 learn+0.170
 great+0.168
Neg logit contributions
led-0.242
ed-0.199
ied-0.168
awed-0.165
ked-0.164
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.340
ed+0.298
y+0.280
ling+0.278
ier+0.270
Neg logit contributions
 pleasure-0.177
 Deal-0.158
 meantime-0.112
 great-0.108
 Not-0.108
Token he
Token ID339
Feature activation-5.97e+00

Pos logit contributions
 pleasure+1.186
 welcome+1.047
 Deal+1.025
 great+1.023
 learn+1.008
Neg logit contributions
led-1.607
ed-1.355
ked-1.165
awed-1.154
ied-1.120
Token was
Token ID373
Feature activation-1.54e+00

Pos logit contributions
led+0.442
ed+0.362
ied+0.335
med+0.330
ked+0.325
Neg logit contributions
 pleasure-0.267
 great-0.242
 think-0.238
 know-0.233
 have-0.230
Token bad
Token ID2089
Feature activation+2.33e+00

Pos logit contributions
led+0.120
ed+0.102
ied+0.089
ked+0.087
awed+0.087
Neg logit contributions
 pleasure-0.070
 Deal-0.061
 welcome-0.058
 learn-0.056
 great-0.056
Token at
Token ID379
Feature activation-7.67e+00

Pos logit contributions
 pleasure+0.119
 welcome+0.107
 think+0.102
 great+0.101
 learn+0.101
Neg logit contributions
led-0.165
ed-0.133
awed-0.122
ied-0.120
med-0.120
Token jumping
Token ID14284
Feature activation-1.02e+00

Pos logit contributions
led+0.553
ed+0.465
ied+0.421
ked+0.393
ling+0.390
Neg logit contributions
 pleasure-0.376
 Deal-0.345
 welcome-0.299
 learn-0.293
 meantime-0.292
Token bed
Token ID3996
Feature activation+8.42e+00

Pos logit contributions
led+0.153
ed+0.131
ied+0.114
ling+0.111
ted+0.109
Neg logit contributions
 pleasure-0.086
 Deal-0.074
 welcome-0.068
 know-0.067
 learn-0.067
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.422
 welcome+0.375
 great+0.364
 learn+0.363
 Deal+0.356
Neg logit contributions
led-0.592
ed-0.487
awed-0.437
ied-0.433
ked-0.432
Token They
Token ID1119
Feature activation+1.25e+00

Pos logit contributions
led+0.371
ed+0.357
ked+0.285
ted+0.283
es+0.279
Neg logit contributions
 pleasure-0.265
 plan-0.244
 deal-0.240
 learn-0.231
 promise-0.229
Token did
Token ID750
Feature activation-1.57e+00

Pos logit contributions
 pleasure+0.057
 think+0.053
 learn+0.052
 know+0.050
 Deal+0.050
Neg logit contributions
led-0.094
ed-0.080
ied-0.071
ing-0.070
med-0.070
Token not
Token ID407
Feature activation+1.01e+01

Pos logit contributions
led+0.135
ed+0.115
ied+0.104
ling+0.100
ked+0.100
Neg logit contributions
 pleasure-0.059
 Deal-0.049
 welcome-0.044
 meantime-0.037
 Today-0.035
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.305
 Deal+0.250
 welcome+0.199
 great+0.185
 meantime+0.175
Neg logit contributions
led-0.926
ed-0.815
y-0.722
ied-0.715
ling-0.711
Token they
Token ID484
Feature activation-2.03e+00

Pos logit contributions
 pleasure+0.972
 Deal+0.828
 welcome+0.804
 great+0.774
 learn+0.768
Neg logit contributions
led-1.851
ed-1.597
ied-1.381
ked-1.377
awed-1.374
Token would
Token ID561
Feature activation-5.10e+00

Pos logit contributions
led+0.155
ed+0.132
med+0.119
ied+0.118
awed+0.118
Neg logit contributions
 pleasure-0.083
 think-0.082
 learn-0.081
 have-0.081
 know-0.079
Token sleep
Token ID3993
Feature activation+8.13e+00

Pos logit contributions
led+0.387
ed+0.331
y+0.314
ling+0.299
ier+0.298
Neg logit contributions
 pleasure-0.189
 Deal-0.163
 welcome-0.124
 meantime-0.118
 Today-0.118
Token well
Token ID880
Feature activation-5.06e+00

Pos logit contributions
 pleasure+0.443
 great+0.410
 welcome+0.407
 Deal+0.397
 learn+0.395
Neg logit contributions
led-0.513
ed-0.430
awed-0.379
ied-0.379
ked-0.368
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
led+0.347
ed+0.293
ied+0.265
awed+0.264
ked+0.258
Neg logit contributions
 pleasure-0.246
 great-0.224
 welcome-0.221
 think-0.217
 learn-0.215
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
 pleasure+0.244
 welcome+0.209
 Deal+0.202
 great+0.199
 think+0.197
Neg logit contributions
led-0.366
ed-0.302
ied-0.274
awed-0.272
ked-0.267
Token take
Token ID1011
Feature activation+2.72e+00

Pos logit contributions
 pleasure+0.121
 Deal+0.110
 welcome+0.087
 meantime+0.084
 great+0.081
Neg logit contributions
led-0.308
ed-0.267
ied-0.234
ling-0.228
ked-0.227
Token some
Token ID617
Feature activation+4.21e+00

Pos logit contributions
 pleasure+0.108
 Deal+0.097
 welcome+0.086
 learn+0.082
 think+0.080
Neg logit contributions
led-0.228
ed-0.200
ied-0.173
med-0.169
ted-0.167
Token time
Token ID640
Feature activation+1.06e+01

Pos logit contributions
 pleasure+0.157
 Deal+0.132
 welcome+0.125
 learn+0.118
 great+0.117
Neg logit contributions
led-0.364
ed-0.316
ied-0.279
ked-0.274
awed-0.273
Token to
Token ID284
Feature activation-4.44e+00

Pos logit contributions
 pleasure+0.568
 welcome+0.498
 learn+0.488
 great+0.480
 think+0.473
Neg logit contributions
led-0.727
ed-0.591
awed-0.521
ked-0.513
ied-0.504
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
led+0.319
ed+0.275
med+0.252
ied+0.252
ling+0.250
Neg logit contributions
 pleasure-0.166
 Deal-0.156
 Today-0.123
 Not-0.118
 meantime-0.111
Token before
Token ID878
Feature activation-2.93e+00

Pos logit contributions
 pleasure+1.273
 welcome+1.116
 Deal+1.103
 great+1.101
 learn+1.083
Neg logit contributions
led-1.526
ed-1.264
awed-1.090
ked-1.081
ied-1.033
Token he
Token ID339
Feature activation-5.95e+00

Pos logit contributions
led+0.206
ed+0.174
ied+0.149
med+0.146
ted+0.146
Neg logit contributions
 pleasure-0.148
 Deal-0.135
 welcome-0.124
 learn-0.116
 deal-0.114
Token did
Token ID750
Feature activation-1.59e+00

Pos logit contributions
led+0.385
ed+0.312
ied+0.276
awed+0.267
ked+0.264
Neg logit contributions
 pleasure-0.341
 Deal-0.299
 learn-0.299
 welcome-0.299
 think-0.299
Token anything
Token ID1997
Feature activation+6.16e+00

Pos logit contributions
led+0.127
ed+0.109
ied+0.095
ked+0.092
awed+0.091
Neg logit contributions
 pleasure-0.069
 Deal-0.062
 welcome-0.057
 learn-0.053
 great-0.052
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.320
 great+0.279
 welcome+0.278
 Deal+0.271
 think+0.267
Neg logit contributions
led-0.435
ed-0.370
ked-0.318
ied-0.317
awed-0.317
Token,
Token ID11
Feature activation+5.38e+00

Pos logit contributions
led+0.359
ed+0.298
ied+0.285
med+0.268
ked+0.266
Neg logit contributions
 pleasure-0.158
 welcome-0.131
 great-0.127
 learn-0.122
 Deal-0.120
Token so
Token ID523
Feature activation+9.97e+00

Pos logit contributions
 pleasure+0.222
 Deal+0.202
 welcome+0.180
 learn+0.171
 great+0.167
Neg logit contributions
led-0.435
ed-0.376
ied-0.331
awed-0.322
ked-0.321
Token she
Token ID673
Feature activation-4.53e+00

Pos logit contributions
 pleasure+0.582
 Deal+0.535
 welcome+0.504
 learn+0.490
 think+0.479
Neg logit contributions
led-0.649
ed-0.538
ied-0.450
awed-0.427
ked-0.426
Token couldn
Token ID3521
Feature activation-3.23e+00

Pos logit contributions
led+0.299
ed+0.245
ier+0.229
ked+0.227
awed+0.224
Neg logit contributions
 pleasure-0.211
 great-0.210
 think-0.203
 have-0.201
 know-0.195
Token't
Token ID470
Feature activation+3.06e+00

Pos logit contributions
led+0.278
ed+0.252
ied+0.220
med+0.216
y+0.214
Neg logit contributions
 pleasure-0.119
 Deal-0.096
 welcome-0.086
 deal-0.079
 great-0.077
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.107
 Deal+0.090
 welcome+0.081
 great+0.071
 deal+0.067
Neg logit contributions
led-0.266
ed-0.235
ied-0.207
ked-0.204
y-0.203
Token of
Token ID286
Feature activation-1.25e+01

Pos logit contributions
 pleasure+1.247
 welcome+1.092
 Deal+1.090
 great+1.077
 learn+1.073
Neg logit contributions
led-1.569
ed-1.297
ked-1.109
awed-1.104
ied-1.057
Token a
Token ID257
Feature activation+3.36e+00

Pos logit contributions
led+0.823
ed+0.714
ied+0.627
we+0.607
med+0.606
Neg logit contributions
 Deal-0.574
 pleasure-0.554
 welcome-0.470
 Today-0.463
 deal-0.462
Token good
Token ID922
Feature activation+5.67e+00

Pos logit contributions
 pleasure+0.151
 Deal+0.146
 welcome+0.123
 learn+0.122
 know+0.118
Neg logit contributions
led-0.241
ed-0.208
y-0.181
ied-0.180
ling-0.176
Token idea
Token ID2126
Feature activation+1.31e+01

Pos logit contributions
 pleasure+0.160
 Deal+0.147
 welcome+0.114
 learn+0.108
 great+0.101
Neg logit contributions
led-0.524
ed-0.467
ied-0.416
y-0.408
ling-0.402
Token.
Token ID13
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.580
 welcome+0.565
 learn+0.534
 think+0.520
 have+0.516
Neg logit contributions
led-1.014
ed-0.792
awed-0.756
ked-0.741
ling-0.709
Token a
Token ID257
Feature activation+3.36e+00

Pos logit contributions
 pleasure+0.454
 Deal+0.407
 welcome+0.380
 learn+0.360
 great+0.351
Neg logit contributions
led-0.780
ed-0.669
ied-0.579
ked-0.563
awed-0.560
Token diary
Token ID26339
Feature activation-2.25e+00

Pos logit contributions
 Deal+0.170
 pleasure+0.168
 welcome+0.144
 learn+0.137
 meantime+0.136
Neg logit contributions
led-0.201
ed-0.174
y-0.149
ly-0.148
lers-0.141
Token.
Token ID13
Feature activation-5.87e+00

Pos logit contributions
led+0.172
ed+0.140
ied+0.126
awed+0.125
ked+0.121
Neg logit contributions
 pleasure-0.109
 welcome-0.095
 Deal-0.092
 learn-0.092
 great-0.090
Token Do
Token ID2141
Feature activation+4.70e+00

Pos logit contributions
led+0.398
ed+0.378
ked+0.315
ted+0.313
med+0.308
Neg logit contributions
 pleasure-0.240
 plan-0.225
 great-0.220
 deal-0.206
 meantime-0.203
Token you
Token ID345
Feature activation+9.89e+00

Pos logit contributions
 pleasure+0.200
 Deal+0.154
 welcome+0.150
 meantime+0.131
 deal+0.129
Neg logit contributions
led-0.385
ed-0.330
ied-0.301
ted-0.291
we-0.291
Token think
Token ID892
Feature activation+2.29e+01

Pos logit contributions
 pleasure+0.389
 Deal+0.342
 welcome+0.275
 great+0.269
 meantime+0.267
Neg logit contributions
led-0.775
ed-0.668
y-0.607
ier-0.597
ly-0.581
Token I
Token ID314
Feature activation+3.11e+00

Pos logit contributions
 pleasure+1.033
 Deal+0.919
 welcome+0.838
 learn+0.798
 think+0.789
Neg logit contributions
led-1.774
ed-1.524
ied-1.341
med-1.292
ted-1.272
Token should
Token ID815
Feature activation-5.81e+00

Pos logit contributions
 pleasure+0.132
 Deal+0.118
 welcome+0.106
 great+0.100
 learn+0.098
Neg logit contributions
led-0.249
ed-0.216
ied-0.186
ked-0.182
y-0.181
Token get
Token ID651
Feature activation+1.09e+01

Pos logit contributions
led+0.402
ed+0.345
ly+0.321
y+0.306
ied+0.305
Neg logit contributions
 pleasure-0.246
 Deal-0.218
 welcome-0.174
 meantime-0.174
 Today-0.168
Token one
Token ID530
Feature activation+8.71e+00

Pos logit contributions
 pleasure+0.426
 Deal+0.369
 welcome+0.340
 learn+0.318
 great+0.315
Neg logit contributions
led-0.923
ed-0.802
ied-0.702
ked-0.684
med-0.680
Token?"
Token ID1701
Feature activation+7.08e+00

Pos logit contributions
 pleasure+0.375
 Deal+0.331
 welcome+0.287
 learn+0.283
 great+0.281
Neg logit contributions
led-0.683
ed-0.593
ied-0.515
y-0.509
ier-0.496
Token bed
Token ID3996
Feature activation+3.76e+00

Pos logit contributions
led+0.126
ed+0.107
ied+0.092
ted+0.087
med+0.087
Neg logit contributions
 pleasure-0.095
 Deal-0.090
 welcome-0.080
 learn-0.076
 great-0.074
Token that
Token ID326
Feature activation-4.64e+00

Pos logit contributions
 pleasure+0.172
 learn+0.155
 welcome+0.154
 great+0.149
 think+0.149
Neg logit contributions
led-0.257
ed-0.214
ked-0.200
awed-0.193
ied-0.191
Token he
Token ID339
Feature activation-8.94e+00

Pos logit contributions
led+0.350
ed+0.297
ied+0.257
ked+0.247
awed+0.247
Neg logit contributions
 pleasure-0.222
 Deal-0.197
 welcome-0.186
 learn-0.178
 great-0.176
Token sn
Token ID3013
Feature activation-7.90e+00

Pos logit contributions
led+0.595
ed+0.499
ied+0.429
ked+0.425
awed+0.419
Neg logit contributions
 pleasure-0.491
 Deal-0.438
 learn-0.427
 welcome-0.426
 think-0.424
Tokenugg
Token ID6837
Feature activation-1.51e+01

Pos logit contributions
led+0.447
ed+0.346
ked+0.291
ied+0.286
med+0.278
Neg logit contributions
 pleasure-0.501
 Deal-0.462
 welcome-0.453
 learn-0.434
 great-0.423
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.042
ked-0.047
ed-0.057
awed-0.102
ied-0.110
Neg logit contributions
 pleasure-1.487
 welcome-1.431
 great-1.419
 Deal-1.418
 learn-1.388
Token in
Token ID287
Feature activation-1.36e+01

Pos logit contributions
led+1.667
ed+1.372
ied+1.165
awed+1.146
ked+1.142
Neg logit contributions
 pleasure-1.546
 Deal-1.371
 welcome-1.355
 great-1.320
 learn-1.306
Token.
Token ID13
Feature activation-7.40e+00

Pos logit contributions
led+0.990
ed+0.852
ied+0.726
ted+0.725
med+0.725
Neg logit contributions
 pleasure-0.606
 Deal-0.558
 learn-0.487
 welcome-0.484
 compromise-0.482
Token But
Token ID887
Feature activation+1.00e+01

Pos logit contributions
led+0.501
ed+0.463
ted+0.396
med+0.381
awed+0.378
Neg logit contributions
 pleasure-0.304
 deal-0.280
 great-0.279
 plan-0.278
 learn-0.272
Token one
Token ID530
Feature activation+7.44e+00

Pos logit contributions
 pleasure+0.517
 Deal+0.470
 welcome+0.440
 learn+0.425
 great+0.419
Neg logit contributions
led-0.719
ed-0.608
ied-0.517
ked-0.500
ted-0.498
Token night
Token ID1755
Feature activation+2.54e+00

Pos logit contributions
 pleasure+0.232
 welcome+0.181
 Deal+0.172
 great+0.166
 learn+0.160
Neg logit contributions
led-0.694
ed-0.609
ked-0.550
awed-0.543
ied-0.540
Token The
Token ID383
Feature activation-7.93e+00

Pos logit contributions
led+0.174
ed+0.149
awed+0.127
ied+0.126
ked+0.126
Neg logit contributions
 pleasure-0.121
 welcome-0.108
 great-0.103
 Deal-0.101
 OK-0.098
Token cater
Token ID20825
Feature activation-1.16e+01

Pos logit contributions
led+0.575
ed+0.485
ied+0.417
ling+0.412
y+0.408
Neg logit contributions
 pleasure-0.377
 Deal-0.337
 welcome-0.307
 learn-0.300
 know-0.296
Tokenpillar
Token ID41643
Feature activation-1.54e+01

Pos logit contributions
led+0.620
ed+0.481
ied+0.415
ked+0.414
awed+0.371
Neg logit contributions
 pleasure-0.764
 welcome-0.707
 Deal-0.703
 learn-0.681
 think-0.681
Token w
Token ID266
Feature activation-2.89e+00

Pos logit contributions
led+1.034
ed+0.866
ied+0.756
ked+0.742
ier+0.715
Neg logit contributions
 pleasure-0.817
 Deal-0.722
 welcome-0.721
 learn-0.716
 think-0.715
Tokenigg
Token ID6950
Feature activation-1.02e+01

Pos logit contributions
led+0.184
ed+0.151
ied+0.127
ked+0.126
med+0.124
Neg logit contributions
 pleasure-0.170
 Deal-0.152
 welcome-0.149
 great-0.142
 learn-0.141
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.077
med+0.023
we+0.020
ed+0.005
awed+0.002
Neg logit contributions
 pleasure-0.918
 think-0.896
 great-0.894
 welcome-0.889
 know-0.877
Token inside
Token ID2641
Feature activation-1.10e+01

Pos logit contributions
led+1.962
ed+1.661
ied+1.439
awed+1.402
ked+1.401
Neg logit contributions
 pleasure-1.273
 Deal-1.115
 welcome-1.081
 learn-1.031
 great-1.030
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
led+0.826
ed+0.699
ied+0.601
ked+0.595
awed+0.590
Neg logit contributions
 pleasure-0.534
 Deal-0.465
 welcome-0.458
 learn-0.437
 great-0.433
Token felt
Token ID2936
Feature activation-3.25e+00

Pos logit contributions
 pleasure+0.111
 think+0.099
 welcome+0.098
 learn+0.098
 great+0.096
Neg logit contributions
led-0.132
ed-0.108
ied-0.097
ier-0.095
awed-0.094
Token safe
Token ID3338
Feature activation+2.52e+00

Pos logit contributions
led+0.282
ed+0.244
ied+0.213
ling+0.207
ked+0.207
Neg logit contributions
 pleasure-0.117
 Deal-0.104
 welcome-0.090
 learn-0.088
 deal-0.085
Token.
Token ID13
Feature activation-7.05e+00

Pos logit contributions
 pleasure+0.117
 welcome+0.105
 think+0.094
 great+0.094
 be+0.093
Neg logit contributions
led-0.179
ed-0.143
ied-0.138
awed-0.137
ked-0.134
Token she
Token ID673
Feature activation-9.20e+00

Pos logit contributions
led+0.805
ed+0.685
awed+0.629
ked+0.612
ied+0.611
Neg logit contributions
 pleasure-0.392
 welcome-0.337
 great-0.336
 learn-0.313
 Deal-0.309
Token did
Token ID750
Feature activation-5.24e+00

Pos logit contributions
led+0.587
ed+0.480
ied+0.412
ked+0.409
awed+0.404
Neg logit contributions
 pleasure-0.534
 welcome-0.473
 Deal-0.471
 learn-0.461
 think-0.458
Token,
Token ID11
Feature activation+2.40e+00

Pos logit contributions
led+0.413
ed+0.358
ied+0.314
med+0.303
y+0.298
Neg logit contributions
 pleasure-0.226
 Deal-0.201
 welcome-0.179
 deal-0.160
 great-0.159
Token it
Token ID340
Feature activation+3.01e+00

Pos logit contributions
 pleasure+0.116
 Deal+0.104
 welcome+0.097
 great+0.093
 learn+0.093
Neg logit contributions
led-0.177
ed-0.151
ied-0.129
ked-0.127
awed-0.125
Token spark
Token ID9009
Feature activation-6.70e+00

Pos logit contributions
 pleasure+0.143
 think+0.133
 great+0.132
 learn+0.131
 welcome+0.128
Neg logit contributions
led-0.207
ed-0.174
ied-0.158
ked-0.158
awed-0.154
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.050
year+0.017
ied+0.011
awed-0.000
ed-0.001
Neg logit contributions
 great-0.606
 pleasure-0.602
 fun-0.573
 think-0.572
 be-0.572
Token with
Token ID351
Feature activation-3.57e+00

Pos logit contributions
led+1.883
ed+1.579
ied+1.394
awed+1.380
ked+1.364
Neg logit contributions
 pleasure-1.352
 welcome-1.182
 great-1.150
 Deal-1.120
 think-1.079
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+0.309
ed+0.270
ied+0.237
ked+0.232
awed+0.231
Neg logit contributions
 pleasure-0.127
 Deal-0.112
 welcome-0.101
 learn-0.097
 think-0.093
Token most
Token ID749
Feature activation+6.71e+00

Pos logit contributions
led+0.260
ed+0.220
ied+0.190
ked+0.184
awed+0.183
Neg logit contributions
 pleasure-0.166
 Deal-0.150
 welcome-0.140
 learn-0.136
 great-0.132
Token beautiful
Token ID4950
Feature activation+1.64e+00

Pos logit contributions
 pleasure+0.259
 welcome+0.203
 Deal+0.202
 great+0.199
 learn+0.188
Neg logit contributions
led-0.574
ed-0.501
ied-0.443
ked-0.440
awed-0.433
Token light
Token ID1657
Feature activation+5.06e-01

Pos logit contributions
 pleasure+0.079
 welcome+0.066
 great+0.064
 Deal+0.064
 learn+0.062
Neg logit contributions
led-0.124
ed-0.105
ied-0.092
ked-0.092
awed-0.090
Token,
Token ID11
Feature activation+7.14e-01

Pos logit contributions
 pleasure+0.199
 great+0.184
 learn+0.168
 think+0.167
 have+0.167
Neg logit contributions
led-0.349
awed-0.282
ed-0.281
ked-0.274
ied-0.263
Token Bob
Token ID5811
Feature activation-2.97e+00

Pos logit contributions
 pleasure+0.033
 Deal+0.029
 welcome+0.026
 learn+0.026
 great+0.025
Neg logit contributions
led-0.054
ed-0.046
ied-0.040
ked-0.039
y-0.039
Token's
Token ID338
Feature activation-5.78e+00

Pos logit contributions
led+0.197
ed+0.161
ied+0.143
ked+0.136
awed+0.135
Neg logit contributions
 pleasure-0.164
 welcome-0.149
 Deal-0.143
 think-0.142
 learn-0.142
Token eyes
Token ID2951
Feature activation+7.82e-01

Pos logit contributions
led+0.457
ed+0.398
ied+0.352
ked+0.341
y+0.339
Neg logit contributions
 pleasure-0.215
 Deal-0.198
 learn-0.177
 welcome-0.174
 think-0.169
Token spark
Token ID9009
Feature activation-6.70e+00

Pos logit contributions
 pleasure+0.040
 Deal+0.035
 welcome+0.035
 great+0.035
 learn+0.034
Neg logit contributions
led-0.055
ed-0.046
ied-0.040
awed-0.039
ked-0.039
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.165
year+0.154
ied+0.149
awed+0.144
ase+0.134
Neg logit contributions
 great-0.465
 pleasure-0.455
 fun-0.426
 look-0.419
 love-0.417
Token with
Token ID351
Feature activation-3.57e+00

Pos logit contributions
led+1.722
ed+1.430
awed+1.276
ied+1.269
ked+1.216
Neg logit contributions
 pleasure-1.480
 welcome-1.326
 great-1.300
 Deal-1.194
 fun-1.193
Token joy
Token ID8716
Feature activation+1.25e+01

Pos logit contributions
led+0.314
ed+0.274
ied+0.241
ked+0.237
ted+0.236
Neg logit contributions
 pleasure-0.119
 Deal-0.109
 learn-0.093
 welcome-0.093
 think-0.088
Token.
Token ID13
Feature activation-7.26e+00

Pos logit contributions
 pleasure+0.559
 welcome+0.469
 love+0.463
 great+0.461
 be+0.444
Neg logit contributions
led-0.838
ed-0.696
awed-0.663
ied-0.639
attered-0.626
Token His
Token ID2399
Feature activation-5.21e+00

Pos logit contributions
led+0.487
ed+0.446
ted+0.383
awed+0.375
y+0.370
Neg logit contributions
 pleasure-0.304
 learn-0.286
 great-0.284
 deal-0.276
 Deal-0.274
Token sister
Token ID6621
Feature activation-7.08e-01

Pos logit contributions
led+0.429
ed+0.372
ied+0.328
ked+0.317
lers+0.315
Neg logit contributions
 pleasure-0.184
 Deal-0.180
 welcome-0.159
 learn-0.153
 meantime-0.146
Token so
Token ID523
Feature activation+5.31e+00

Pos logit contributions
 pleasure+0.104
 Deal+0.082
 welcome+0.075
 learn+0.067
 great+0.066
Neg logit contributions
led-0.318
ed-0.281
ied-0.252
ked-0.244
awed-0.244
Token happy
Token ID3772
Feature activation+7.43e+00

Pos logit contributions
 pleasure+0.218
 Deal+0.198
 welcome+0.172
 learn+0.169
 deal+0.164
Neg logit contributions
led-0.437
ed-0.373
ied-0.329
ling-0.315
awed-0.312
Token that
Token ID326
Feature activation-3.97e+00

Pos logit contributions
 pleasure+0.367
 welcome+0.322
 think+0.303
 learn+0.303
 great+0.299
Neg logit contributions
led-0.534
ed-0.440
ked-0.397
ied-0.393
awed-0.384
Token she
Token ID673
Feature activation-7.11e+00

Pos logit contributions
led+0.274
ed+0.229
ied+0.195
awed+0.185
ked+0.185
Neg logit contributions
 pleasure-0.212
 Deal-0.194
 welcome-0.180
 learn-0.176
 great-0.173
Token whist
Token ID32262
Feature activation-5.54e+00

Pos logit contributions
led+0.448
ed+0.365
ied+0.323
ked+0.321
awed+0.320
Neg logit contributions
 pleasure-0.410
 welcome-0.367
 great-0.360
 learn-0.358
 think-0.358
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.029
ed-0.015
ked-0.035
awed-0.039
ied-0.043
Neg logit contributions
 pleasure-0.561
 great-0.550
 welcome-0.537
 learn-0.529
 Deal-0.528
Token all
Token ID477
Feature activation-5.63e-01

Pos logit contributions
led+1.897
ed+1.600
ied+1.370
ked+1.333
awed+1.328
Neg logit contributions
 pleasure-1.333
 Deal-1.187
 welcome-1.135
 learn-1.093
 great-1.083
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+0.046
ed+0.040
ked+0.036
awed+0.036
ied+0.035
Neg logit contributions
 pleasure-0.022
 welcome-0.020
 great-0.018
 Deal-0.018
 learn-0.017
Token way
Token ID835
Feature activation+9.36e+00

Pos logit contributions
led+0.311
ed+0.268
ied+0.239
ling+0.235
ked+0.230
Neg logit contributions
 pleasure-0.118
 Deal-0.104
 welcome-0.090
 learn-0.087
 know-0.083
Token home
Token ID1363
Feature activation+6.58e+00

Pos logit contributions
 pleasure+0.521
 welcome+0.461
 great+0.438
 learn+0.438
 Deal+0.419
Neg logit contributions
led-0.628
ed-0.501
awed-0.446
ked-0.435
ied-0.417
Token.
Token ID13
Feature activation-7.05e+00

Pos logit contributions
 pleasure+0.346
 welcome+0.305
 learn+0.302
 great+0.296
 think+0.284
Neg logit contributions
led-0.456
ed-0.364
awed-0.336
ked-0.327
ied-0.323
Token around
Token ID1088
Feature activation-1.37e+01

Pos logit contributions
led+0.324
ed+0.262
awed+0.240
ked+0.237
ied+0.230
Neg logit contributions
 pleasure-0.191
 welcome-0.182
 great-0.165
 OK-0.162
 think-0.162
Token.
Token ID13
Feature activation-9.52e+00

Pos logit contributions
led+1.012
ed+0.857
ied+0.737
awed+0.714
ked+0.712
Neg logit contributions
 pleasure-0.672
 Deal-0.602
 welcome-0.564
 learn-0.540
 great-0.537
Token She
Token ID1375
Feature activation-6.79e+00

Pos logit contributions
led+0.767
ed+0.694
ted+0.592
ied+0.590
med+0.589
Neg logit contributions
 pleasure-0.355
 Deal-0.301
 welcome-0.282
 great-0.280
 deal-0.279
Token w
Token ID266
Feature activation-2.89e+00

Pos logit contributions
led+0.438
ed+0.360
ied+0.308
ked+0.301
awed+0.297
Neg logit contributions
 pleasure-0.388
 Deal-0.346
 welcome-0.340
 learn-0.339
 think-0.337
Tokenigg
Token ID6950
Feature activation-1.02e+01

Pos logit contributions
led+0.160
ed+0.131
ked+0.104
ied+0.102
ted+0.101
Neg logit contributions
 pleasure-0.191
 Deal-0.176
 welcome-0.169
 great-0.164
 learn-0.163
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.083
ed+0.038
ked+0.036
we+0.029
awed+0.024
Neg logit contributions
 think-0.863
 great-0.861
 pleasure-0.856
 learn-0.849
 know-0.846
Token it
Token ID340
Feature activation+3.89e+00

Pos logit contributions
led+2.015
ed+1.707
ied+1.497
awed+1.469
ked+1.458
Neg logit contributions
 pleasure-1.220
 Deal-1.046
 welcome-1.025
 great-0.986
 learn-0.975
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
 pleasure+0.181
 great+0.163
 think+0.161
 welcome+0.158
 learn+0.157
Neg logit contributions
led-0.264
ed-0.216
ied-0.202
awed-0.199
ked-0.191
Token squ
Token ID2809
Feature activation-1.92e+00

Pos logit contributions
 pleasure+0.111
 think+0.099
 learn+0.098
 great+0.097
 welcome+0.097
Neg logit contributions
led-0.133
ed-0.110
ied-0.099
ier-0.095
awed-0.094
Tokenigg
Token ID6950
Feature activation-9.25e+00

Pos logit contributions
led+0.088
ed+0.067
ied+0.059
we+0.055
web+0.054
Neg logit contributions
 pleasure-0.138
 Deal-0.126
 welcome-0.123
 great-0.120
 think-0.120
Tokenled
Token ID992
Feature activation-2.54e+01

Pos logit contributions
led+0.052
year+0.030
web+0.026
ked+0.019
awed+0.015
Neg logit contributions
 great-0.776
 pleasure-0.756
 good-0.743
 think-0.743
 know-0.724
Token graceful
Token ID44363
Feature activation-5.87e+00

Pos logit contributions
led+0.253
ed+0.210
ied+0.169
ling+0.168
y+0.163
Neg logit contributions
 pleasure-0.246
 Deal-0.232
 welcome-0.212
 learn-0.210
 know-0.206
Token car
Token ID1097
Feature activation-4.86e+00

Pos logit contributions
led+0.426
ed+0.357
ied+0.311
awed+0.305
ked+0.305
Neg logit contributions
 pleasure-0.297
 welcome-0.254
 Deal-0.251
 learn-0.241
 great-0.241
Token -
Token ID532
Feature activation-4.65e+00

Pos logit contributions
led+0.335
ed+0.267
ied+0.246
awed+0.246
ked+0.235
Neg logit contributions
 pleasure-0.243
 welcome-0.214
 learn-0.209
 think-0.204
 great-0.204
Token it
Token ID340
Feature activation+3.01e+00

Pos logit contributions
led+0.355
ed+0.310
ied+0.266
ked+0.262
y+0.261
Neg logit contributions
 pleasure-0.195
 Deal-0.183
 welcome-0.158
 learn-0.151
 meantime-0.148
Token spark
Token ID9009
Feature activation-6.70e+00

Pos logit contributions
 pleasure+0.153
 welcome+0.133
 great+0.130
 Deal+0.129
 think+0.129
Neg logit contributions
led-0.213
ed-0.179
ied-0.156
ked-0.155
awed-0.154
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.091
ed+0.040
ied+0.028
awed+0.027
ked+0.023
Neg logit contributions
 pleasure-0.617
 great-0.594
 think-0.562
 welcome-0.561
 fun-0.552
Token in
Token ID287
Feature activation-1.36e+01

Pos logit contributions
led+1.785
ed+1.487
awed+1.284
ied+1.284
ked+1.256
Neg logit contributions
 pleasure-1.462
 welcome-1.276
 great-1.240
 Deal-1.194
 think-1.164
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+0.938
ed+0.800
med+0.700
ied+0.696
y+0.683
Neg logit contributions
 pleasure-0.643
 Deal-0.616
 learn-0.540
 deal-0.533
 welcome-0.521
Token sunshine
Token ID34488
Feature activation+7.20e+00

Pos logit contributions
led+0.268
ed+0.228
ied+0.197
ling+0.191
ked+0.191
Neg logit contributions
 pleasure-0.159
 Deal-0.143
 welcome-0.131
 learn-0.128
 think-0.125
Token.
Token ID13
Feature activation-7.13e+00

Pos logit contributions
 pleasure+0.380
 welcome+0.333
 learn+0.314
 great+0.313
 think+0.307
Neg logit contributions
led-0.499
ed-0.408
ied-0.359
awed-0.356
ked-0.356
Token One
Token ID1881
Feature activation+5.42e+00

Pos logit contributions
led+0.570
ed+0.521
ted+0.449
med+0.447
ied+0.442
Neg logit contributions
 pleasure-0.247
 Deal-0.214
 great-0.205
 deal-0.205
 learn-0.201
Token
Token ID198
Feature activation+4.60e+00

Pos logit contributions
 pleasure+0.203
 Deal+0.176
 welcome+0.170
 learn+0.162
 great+0.161
Neg logit contributions
led-0.357
ed-0.305
ied-0.266
awed-0.258
ked-0.258
Token
Token ID198
Feature activation+5.61e+00

Pos logit contributions
 pleasure+0.209
 deal+0.164
 Deal+0.160
 great+0.153
 welcome+0.151
Neg logit contributions
led-0.340
ed-0.298
ied-0.264
med-0.263
y-0.261
TokenS
Token ID50
Feature activation-6.61e+00

Pos logit contributions
 pleasure+0.312
 Deal+0.253
 welcome+0.245
 deal+0.244
 great+0.239
Neg logit contributions
led-0.359
ed-0.306
ied-0.269
med-0.267
y-0.265
Tokenara
Token ID3301
Feature activation-7.76e+00

Pos logit contributions
led+0.501
ed+0.427
ied+0.369
ked+0.360
med+0.356
Neg logit contributions
 pleasure-0.311
 Deal-0.280
 welcome-0.267
 learn-0.254
 great-0.250
Token gigg
Token ID30442
Feature activation-2.56e+00

Pos logit contributions
led+0.528
ed+0.435
ied+0.386
ked+0.369
ier+0.362
Neg logit contributions
 pleasure-0.411
 Deal-0.369
 welcome-0.361
 learn-0.357
 think-0.356
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.002
we-0.008
stones-0.011
ed-0.011
web-0.011
Neg logit contributions
 Deal-0.248
 pleasure-0.242
 great-0.233
 welcome-0.233
 OK-0.230
Token.
Token ID13
Feature activation-7.57e+00

Pos logit contributions
led+1.794
ed+1.499
ied+1.259
ked+1.229
awed+1.219
Neg logit contributions
 pleasure-1.442
 Deal-1.297
 welcome-1.238
 learn-1.201
 great-1.189
Token She
Token ID1375
Feature activation-5.34e+00

Pos logit contributions
led+0.501
ed+0.457
ked+0.372
ted+0.371
awed+0.368
Neg logit contributions
 pleasure-0.374
 Deal-0.339
 great-0.324
 learn-0.321
 deal-0.316
Token picked
Token ID6497
Feature activation-1.14e+01

Pos logit contributions
led+0.347
ed+0.287
ied+0.245
ked+0.235
awed+0.232
Neg logit contributions
 pleasure-0.308
 Deal-0.275
 welcome-0.269
 great-0.263
 learn-0.263
Token up
Token ID510
Feature activation-2.84e+00

Pos logit contributions
led+0.824
ed+0.698
ied+0.594
ked+0.578
awed+0.575
Neg logit contributions
 pleasure-0.588
 Deal-0.527
 welcome-0.500
 learn-0.482
 great-0.476
Token her
Token ID607
Feature activation-3.50e+00

Pos logit contributions
led+0.243
ed+0.209
ied+0.186
awed+0.181
ked+0.181
Neg logit contributions
 pleasure-0.107
 Deal-0.090
 welcome-0.087
 great-0.083
 learn-0.083
Token Mom
Token ID11254
Feature activation+2.60e+00

Pos logit contributions
led+0.403
ed+0.376
y+0.334
red+0.334
ged+0.333
Neg logit contributions
 pleasure-0.183
 Deal-0.143
 Sometimes-0.089
 deal-0.088
 Not-0.087
Token smiled
Token ID13541
Feature activation-9.67e+00

Pos logit contributions
 pleasure+0.136
 Deal+0.122
 welcome+0.118
 learn+0.114
 think+0.112
Neg logit contributions
led-0.182
ed-0.152
ied-0.131
ked-0.128
awed-0.127
Token,
Token ID11
Feature activation+2.40e+00

Pos logit contributions
led+0.736
ed+0.614
ied+0.565
awed+0.542
ted+0.531
Neg logit contributions
 pleasure-0.452
 welcome-0.389
 Deal-0.378
 great-0.360
 learn-0.352
Token t
Token ID256
Feature activation-2.73e+00

Pos logit contributions
 pleasure+0.111
 Deal+0.099
 welcome+0.092
 learn+0.089
 great+0.088
Neg logit contributions
led-0.182
ed-0.155
ied-0.133
ked-0.132
awed-0.131
Tokenuss
Token ID1046
Feature activation-4.38e+00

Pos logit contributions
led+0.122
lers+0.083
ed+0.079
ils+0.076
ked+0.073
Neg logit contributions
 pleasure-0.163
 Deal-0.157
 welcome-0.147
 love-0.146
 Mom-0.142
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.224
attered+0.185
ed+0.180
ted+0.168
ked+0.164
Neg logit contributions
 be-0.214
 -0.211
 think-0.210
 have-0.209
 pleasure-0.207
Token his
Token ID465
Feature activation-4.84e+00

Pos logit contributions
led+1.975
ed+1.655
ied+1.485
awed+1.468
ier+1.445
Neg logit contributions
 pleasure-1.254
 welcome-1.081
 great-1.024
 Deal-1.024
 think-0.987
Token hair
Token ID4190
Feature activation+4.16e+00

Pos logit contributions
led+0.368
ed+0.313
ied+0.269
ked+0.265
awed+0.262
Neg logit contributions
 pleasure-0.222
 Deal-0.199
 welcome-0.188
 learn-0.184
 great-0.177
Token and
Token ID290
Feature activation+2.20e+00

Pos logit contributions
 pleasure+0.174
 be+0.156
 learn+0.153
 great+0.151
 rest+0.149
Neg logit contributions
led-0.306
ed-0.255
ied-0.235
year-0.227
ted-0.220
Token replied
Token ID8712
Feature activation-2.75e-01

Pos logit contributions
 pleasure+0.120
 welcome+0.105
 Deal+0.103
 great+0.102
 think+0.101
Neg logit contributions
led-0.148
ed-0.121
ied-0.108
ked-0.103
awed-0.103
Token,
Token ID11
Feature activation+4.20e+00

Pos logit contributions
led+0.024
ed+0.020
ied+0.018
awed+0.018
ked+0.018
Neg logit contributions
 pleasure-0.010
 Deal-0.008
 welcome-0.008
 great-0.008
 learn-0.007
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
 be+0.121
 have+0.120
 great+0.119
 think+0.116
 try+0.114
Neg logit contributions
led-0.188
ier-0.169
ed-0.160
ing-0.157
ied-0.154
Token shiny
Token ID22441
Feature activation-5.93e+00

Pos logit contributions
led+0.095
ed+0.081
y+0.075
ling+0.073
ied+0.070
Neg logit contributions
 pleasure-0.053
 Deal-0.052
 learn-0.044
 know-0.042
 welcome-0.041
Token rock
Token ID3881
Feature activation-4.07e+00

Pos logit contributions
led+0.443
ed+0.376
ied+0.325
awed+0.318
ked+0.316
Neg logit contributions
 pleasure-0.289
 welcome-0.248
 Deal-0.243
 great-0.238
 learn-0.234
Token that
Token ID326
Feature activation-3.57e+00

Pos logit contributions
led+0.294
ed+0.236
ied+0.220
awed+0.219
med+0.213
Neg logit contributions
 pleasure-0.171
 have-0.160
 be-0.158
 welcome-0.158
 think-0.154
Token spark
Token ID9009
Feature activation-6.70e+00

Pos logit contributions
led+0.241
ed+0.199
ked+0.171
ied+0.170
awed+0.169
Neg logit contributions
 pleasure-0.197
 welcome-0.174
 Deal-0.168
 great-0.168
 learn-0.165
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.112
awed+0.084
ied+0.064
ainted+0.063
year+0.061
Neg logit contributions
 pleasure-0.543
 great-0.540
 have-0.516
 be-0.515
 fun-0.511
Token in
Token ID287
Feature activation-1.36e+01

Pos logit contributions
led+1.750
ed+1.438
awed+1.303
ied+1.258
ked+1.234
Neg logit contributions
 pleasure-1.479
 welcome-1.324
 great-1.316
 think-1.203
 fun-1.199
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+1.021
ed+0.877
ied+0.762
med+0.748
y+0.745
Neg logit contributions
 pleasure-0.614
 Deal-0.572
 welcome-0.497
 learn-0.491
 deal-0.476
Token sun
Token ID4252
Feature activation+3.23e+00

Pos logit contributions
led+0.279
ed+0.239
ied+0.209
ked+0.203
awed+0.203
Neg logit contributions
 pleasure-0.152
 Deal-0.132
 welcome-0.124
 learn-0.119
 great-0.118
Token.
Token ID13
Feature activation-7.13e+00

Pos logit contributions
 pleasure+0.169
 welcome+0.147
 be+0.140
 learn+0.140
 have+0.138
Neg logit contributions
led-0.220
ed-0.178
ied-0.159
awed-0.157
ked-0.151
Token She
Token ID1375
Feature activation-4.98e+00

Pos logit contributions
led+0.553
ed+0.501
ted+0.431
ied+0.426
med+0.426
Neg logit contributions
 pleasure-0.271
 Deal-0.238
 great-0.225
 learn-0.221
 welcome-0.221
Token
Token ID198
Feature activation+4.60e+00

Pos logit contributions
 pleasure+0.114
 Deal+0.106
 welcome+0.090
 meantime+0.089
 great+0.088
Neg logit contributions
led-0.215
ed-0.187
ked-0.160
ted-0.158
ied-0.157
Token
Token ID198
Feature activation+5.61e+00

Pos logit contributions
 pleasure+0.209
 deal+0.164
 Deal+0.160
 great+0.153
 welcome+0.151
Neg logit contributions
led-0.340
ed-0.298
ied-0.264
med-0.263
y-0.261
TokenAs
Token ID1722
Feature activation+3.87e+00

Pos logit contributions
 pleasure+0.312
 Deal+0.253
 welcome+0.245
 deal+0.244
 great+0.239
Neg logit contributions
led-0.359
ed-0.306
ied-0.269
med-0.267
y-0.265
Token he
Token ID339
Feature activation-8.53e+00

Pos logit contributions
 pleasure+0.200
 Deal+0.183
 welcome+0.169
 learn+0.164
 think+0.160
Neg logit contributions
led-0.274
ed-0.231
ied-0.198
ted-0.190
ked-0.190
Token padd
Token ID14098
Feature activation-7.07e+00

Pos logit contributions
led+0.562
ed+0.462
ied+0.401
ked+0.393
ier+0.384
Neg logit contributions
 pleasure-0.471
 welcome-0.413
 Deal-0.412
 great-0.412
 learn-0.412
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.014
we-0.004
ed-0.028
ked-0.054
awed-0.055
Neg logit contributions
 pleasure-0.683
 welcome-0.676
 great-0.660
 know-0.659
 think-0.659
Token along
Token ID1863
Feature activation-1.08e+01

Pos logit contributions
led+1.887
ed+1.589
ied+1.360
ked+1.323
awed+1.318
Neg logit contributions
 pleasure-1.346
 Deal-1.199
 welcome-1.147
 learn-1.104
 great-1.093
Token,
Token ID11
Feature activation+3.85e+00

Pos logit contributions
led+0.894
ed+0.767
ied+0.678
awed+0.667
ked+0.662
Neg logit contributions
 pleasure-0.438
 Deal-0.367
 welcome-0.362
 great-0.342
 learn-0.342
Token he
Token ID339
Feature activation-7.34e+00

Pos logit contributions
 pleasure+0.205
 Deal+0.183
 welcome+0.176
 learn+0.169
 great+0.168
Neg logit contributions
led-0.270
ed-0.226
ied-0.192
ked-0.187
awed-0.186
Token saw
Token ID2497
Feature activation-3.15e+00

Pos logit contributions
led+0.463
ed+0.377
ied+0.325
awed+0.314
ked+0.310
Neg logit contributions
 pleasure-0.427
 Deal-0.378
 learn-0.377
 welcome-0.374
 great-0.373
Token an
Token ID281
Feature activation+1.81e+00

Pos logit contributions
led+0.293
ed+0.253
ied+0.231
awed+0.227
ked+0.227
Neg logit contributions
 pleasure-0.094
 welcome-0.070
 great-0.070
 learn-0.066
 Deal-0.065
Token bed
Token ID3996
Feature activation+3.76e+00

Pos logit contributions
 pleasure+0.048
 Deal+0.043
 welcome+0.040
 great+0.038
 learn+0.037
Neg logit contributions
led-0.065
ed-0.055
ied-0.047
ked-0.046
ling-0.045
Token,
Token ID11
Feature activation+1.73e+00

Pos logit contributions
 pleasure+0.172
 learn+0.155
 welcome+0.154
 great+0.149
 think+0.149
Neg logit contributions
led-0.257
ed-0.214
ked-0.200
awed-0.193
ied-0.191
Token he
Token ID339
Feature activation-8.94e+00

Pos logit contributions
 pleasure+0.084
 Deal+0.074
 welcome+0.071
 learn+0.068
 great+0.067
Neg logit contributions
led-0.129
ed-0.109
ied-0.094
ked-0.092
awed-0.091
Token sn
Token ID3013
Feature activation-7.90e+00

Pos logit contributions
led+0.597
ed+0.496
ied+0.424
ked+0.414
awed+0.410
Neg logit contributions
 pleasure-0.497
 Deal-0.447
 welcome-0.435
 learn-0.426
 great-0.421
Tokenugg
Token ID6837
Feature activation-1.51e+01

Pos logit contributions
led+0.464
ed+0.365
ked+0.305
ied+0.301
med+0.291
Neg logit contributions
 pleasure-0.492
 Deal-0.457
 welcome-0.448
 learn-0.428
 great-0.417
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.024
ked-0.060
ed-0.066
ied-0.118
awed-0.123
Neg logit contributions
 pleasure-1.490
 welcome-1.446
 great-1.435
 Deal-1.434
 learn-1.389
Token under
Token ID739
Feature activation-1.76e+01

Pos logit contributions
led+1.602
ed+1.311
ied+1.098
ked+1.077
awed+1.077
Neg logit contributions
 pleasure-1.611
 Deal-1.438
 welcome-1.419
 great-1.382
 learn-1.367
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+1.401
ed+1.208
ted+1.041
ied+1.038
med+1.027
Neg logit contributions
 pleasure-0.740
 Deal-0.664
 welcome-0.605
 learn-0.579
 deal-0.560
Token covers
Token ID8698
Feature activation-8.55e+00

Pos logit contributions
led+0.316
ed+0.276
ied+0.246
ked+0.242
awed+0.241
Neg logit contributions
 pleasure-0.116
 Deal-0.095
 welcome-0.091
 learn-0.085
 great-0.084
Token and
Token ID290
Feature activation+2.33e+00

Pos logit contributions
led+0.591
ed+0.488
awed+0.456
ked+0.454
attered+0.418
Neg logit contributions
 pleasure-0.404
 welcome-0.372
 great-0.342
 learn-0.340
 rest-0.337
Token fell
Token ID3214
Feature activation-8.75e+00

Pos logit contributions
 pleasure+0.127
 Deal+0.113
 welcome+0.110
 learn+0.108
 great+0.107
Neg logit contributions
led-0.157
ed-0.131
ied-0.114
awed-0.110
ked-0.110
Token.
Token ID13
Feature activation-1.05e+01

Pos logit contributions
led+0.089
ed+0.073
ied+0.069
ked+0.069
awed+0.067
Neg logit contributions
 pleasure-0.033
 welcome-0.028
 fun-0.028
 great-0.028
 learn-0.026
Token Tim
Token ID5045
Feature activation-1.67e+00

Pos logit contributions
led+0.833
ed+0.751
ted+0.642
y+0.639
ied+0.637
Neg logit contributions
 pleasure-0.406
 Deal-0.342
 great-0.324
 deal-0.315
 welcome-0.314
Tokenmy
Token ID1820
Feature activation+1.83e+00

Pos logit contributions
led+0.120
ed+0.101
ied+0.088
ked+0.086
awed+0.085
Neg logit contributions
 pleasure-0.084
 Deal-0.074
 welcome-0.073
 learn-0.071
 think-0.070
Token sn
Token ID3013
Feature activation-7.90e+00

Pos logit contributions
 pleasure+0.098
 Deal+0.087
 learn+0.086
 welcome+0.086
 think+0.085
Neg logit contributions
led-0.123
ed-0.103
ied-0.089
ked-0.087
awed-0.085
Tokenugg
Token ID6837
Feature activation-1.51e+01

Pos logit contributions
led+0.438
ed+0.338
ied+0.277
ked+0.273
med+0.266
Neg logit contributions
 pleasure-0.528
 Deal-0.482
 welcome-0.476
 learn-0.453
 great-0.444
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.034
ed-0.061
ked-0.069
ied-0.114
year-0.122
Neg logit contributions
 pleasure-1.474
 welcome-1.451
 great-1.436
 Deal-1.434
 learn-1.403
Token up
Token ID510
Feature activation-3.28e+00

Pos logit contributions
led+1.744
ed+1.447
ied+1.225
ked+1.187
awed+1.186
Neg logit contributions
 pleasure-1.489
 Deal-1.336
 welcome-1.292
 learn-1.248
 great-1.245
Token to
Token ID284
Feature activation-5.96e+00

Pos logit contributions
led+0.218
ed+0.181
ied+0.159
ked+0.155
awed+0.153
Neg logit contributions
 pleasure-0.174
 welcome-0.157
 Deal-0.152
 think-0.152
 great-0.151
Token his
Token ID465
Feature activation-4.52e+00

Pos logit contributions
led+0.397
ed+0.332
ted+0.303
med+0.285
ting+0.283
Neg logit contributions
 pleasure-0.285
 Deal-0.273
 compromise-0.225
 meantime-0.224
 deal-0.219
Token mom
Token ID1995
Feature activation+5.07e+00

Pos logit contributions
led+0.374
ed+0.321
ied+0.281
ling+0.276
ked+0.276
Neg logit contributions
 pleasure-0.172
 Deal-0.154
 welcome-0.142
 learn-0.134
 think-0.131
Token and
Token ID290
Feature activation+2.41e+00

Pos logit contributions
 pleasure+0.229
 welcome+0.202
 Deal+0.197
 learn+0.195
 think+0.190
Neg logit contributions
led-0.391
ed-0.328
ied-0.292
awed-0.290
ked-0.285
Token hedge
Token ID19859
Feature activation-7.20e+00

Pos logit contributions
 pleasure+0.556
 Deal+0.499
 welcome+0.485
 learn+0.469
 great+0.467
Neg logit contributions
led-0.646
ed-0.533
ied-0.448
ked-0.437
awed-0.435
Token.
Token ID13
Feature activation-9.52e+00

Pos logit contributions
led+0.482
ed+0.386
ked+0.355
med+0.353
ied+0.353
Neg logit contributions
 pleasure-0.339
 welcome-0.312
 learn-0.308
 think-0.308
 have-0.302
Token He
Token ID679
Feature activation-7.17e+00

Pos logit contributions
led+0.745
ed+0.675
ted+0.578
y+0.575
med+0.574
Neg logit contributions
 pleasure-0.368
 Deal-0.314
 great-0.295
 deal-0.290
 welcome-0.286
Token w
Token ID266
Feature activation-2.89e+00

Pos logit contributions
led+0.469
ed+0.387
ied+0.332
ked+0.324
awed+0.321
Neg logit contributions
 pleasure-0.402
 Deal-0.358
 welcome-0.353
 learn-0.352
 think-0.351
Tokenigg
Token ID6950
Feature activation-1.02e+01

Pos logit contributions
led+0.173
ed+0.143
ied+0.116
ked+0.115
med+0.113
Neg logit contributions
 pleasure-0.179
 Deal-0.163
 welcome-0.158
 great-0.152
 learn-0.151
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.066
ed+0.020
we+0.016
med+0.012
awed+0.006
Neg logit contributions
 think-0.894
 pleasure-0.893
 great-0.888
 know-0.880
 learn-0.873
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
led+1.965
ed+1.662
ied+1.454
awed+1.428
ked+1.414
Neg logit contributions
 pleasure-1.262
 Deal-1.082
 welcome-1.072
 great-1.031
 learn-1.016
Token squ
Token ID2809
Feature activation-2.07e+00

Pos logit contributions
 pleasure+0.102
 think+0.091
 welcome+0.090
 great+0.089
 learn+0.089
Neg logit contributions
led-0.123
ed-0.102
ied-0.092
ier-0.089
awed-0.086
Tokenirmed
Token ID15491
Feature activation-1.02e+01

Pos logit contributions
led+0.092
ed+0.069
ied+0.062
we+0.060
web+0.059
Neg logit contributions
 pleasure-0.147
 Deal-0.135
 welcome-0.133
 great-0.129
 think-0.129
Token and
Token ID290
Feature activation+2.33e+00

Pos logit contributions
led+0.780
ed+0.637
awed+0.616
ied+0.594
med+0.584
Neg logit contributions
 pleasure-0.412
 welcome-0.369
 great-0.364
 think-0.334
 Deal-0.327
Token soon
Token ID2582
Feature activation+3.41e+00

Pos logit contributions
 pleasure+0.127
 Deal+0.113
 welcome+0.111
 great+0.108
 learn+0.107
Neg logit contributions
led-0.158
ed-0.132
ied-0.115
awed-0.109
ked-0.108
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
led+0.094
ed+0.075
awed+0.067
ier+0.067
ked+0.067
Neg logit contributions
 pleasure-0.079
 great-0.076
 welcome-0.075
 learn-0.074
 think-0.072
Token spikes
Token ID27198
Feature activation-7.37e+00

Pos logit contributions
led+0.079
ed+0.067
ied+0.058
awed+0.056
ked+0.056
Neg logit contributions
 pleasure-0.054
 Deal-0.047
 welcome-0.046
 learn-0.044
 great-0.044
Token.
Token ID13
Feature activation-8.86e+00

Pos logit contributions
led+0.452
ed+0.367
awed+0.349
year+0.345
ied+0.342
Neg logit contributions
 pleasure-0.337
 have-0.334
 know-0.331
 think-0.329
 welcome-0.320
Token They
Token ID1119
Feature activation-1.32e+00

Pos logit contributions
led+0.654
ed+0.600
ted+0.508
ked+0.500
med+0.499
Neg logit contributions
 pleasure-0.363
 deal-0.295
 great-0.295
 Deal-0.294
 plan-0.289
Token grow
Token ID1663
Feature activation+1.54e-01

Pos logit contributions
led+0.112
ed+0.097
ied+0.086
awed+0.084
ked+0.083
Neg logit contributions
 pleasure-0.051
 Deal-0.043
 welcome-0.041
 learn-0.039
 great-0.039
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
 great+0.012
 pleasure+0.011
 welcome+0.011
 learn+0.011
 good+0.011
Neg logit contributions
led-0.005
ed-0.004
awed-0.003
ked-0.003
ied-0.003
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
led+1.863
ed+1.558
ied+1.357
awed+1.332
ked+1.309
Neg logit contributions
 pleasure-1.374
 welcome-1.186
 Deal-1.179
 great-1.145
 learn-1.122
Token roared
Token ID45615
Feature activation-1.23e+01

Pos logit contributions
 pleasure+0.093
 welcome+0.082
 think+0.081
 Deal+0.081
 learn+0.081
Neg logit contributions
led-0.134
ed-0.115
ied-0.103
awed-0.098
ier-0.098
Token and
Token ID290
Feature activation+2.20e+00

Pos logit contributions
led+0.879
ed+0.707
ied+0.674
awed+0.659
ted+0.627
Neg logit contributions
 pleasure-0.582
 welcome-0.528
 great-0.527
 OK-0.511
 Deal-0.505
Token his
Token ID465
Feature activation-4.39e+00

Pos logit contributions
 pleasure+0.115
 welcome+0.104
 think+0.104
 Deal+0.103
 learn+0.101
Neg logit contributions
led-0.148
ed-0.124
ied-0.113
awed-0.105
ier-0.105
Tokensed
Token ID36622
Feature activation-6.01e+00

Pos logit contributions
led+0.323
ed+0.273
ied+0.235
ked+0.229
awed+0.228
Neg logit contributions
 pleasure-0.218
 Deal-0.194
 welcome-0.185
 learn-0.178
 great-0.176
Token Suddenly
Token ID24975
Feature activation-5.18e-02

Pos logit contributions
 pleasure+0.134
 welcome+0.123
 think+0.123
 learn+0.122
 Deal+0.120
Neg logit contributions
led-0.188
ed-0.163
ier-0.141
med-0.139
awed-0.138
Token,
Token ID11
Feature activation+1.73e+00

Pos logit contributions
led+0.004
ed+0.004
ied+0.003
awed+0.003
ked+0.003
Neg logit contributions
 pleasure-0.002
 welcome-0.002
 Deal-0.002
 great-0.002
 learn-0.002
Token his
Token ID465
Feature activation-6.12e+00

Pos logit contributions
 pleasure+0.078
 Deal+0.068
 welcome+0.065
 learn+0.062
 great+0.062
Neg logit contributions
led-0.135
ed-0.115
ied-0.100
awed-0.098
ked-0.098
Token mom
Token ID1995
Feature activation+3.75e+00

Pos logit contributions
led+0.542
ed+0.473
ied+0.420
ked+0.411
awed+0.410
Neg logit contributions
 pleasure-0.210
 Deal-0.176
 welcome-0.164
 learn-0.154
 great-0.151
Token tick
Token ID4378
Feature activation-9.91e+00

Pos logit contributions
 pleasure+0.179
 Deal+0.166
 welcome+0.165
 learn+0.164
 know+0.162
Neg logit contributions
led-0.263
ed-0.212
ied-0.188
ked-0.182
awed-0.180
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.106
ed+0.039
ied+0.001
ier-0.013
awed-0.016
Neg logit contributions
 pleasure-0.899
 great-0.890
 Deal-0.888
 practice-0.866
 welcome-0.863
Token him
Token ID683
Feature activation+5.99e-02

Pos logit contributions
led+2.029
ed+1.725
ied+1.511
awed+1.487
ked+1.465
Neg logit contributions
 pleasure-1.204
 Deal-1.051
 welcome-1.025
 great-0.984
 learn-0.964
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
 pleasure+0.003
 welcome+0.003
 think+0.003
 Deal+0.003
 great+0.003
Neg logit contributions
led-0.004
ed-0.003
awed-0.003
ied-0.003
ted-0.003
Token he
Token ID339
Feature activation-7.34e+00

Pos logit contributions
 pleasure+0.104
 Deal+0.093
 think+0.092
 welcome+0.092
 great+0.090
Neg logit contributions
led-0.142
ed-0.116
ied-0.106
awed-0.102
ier-0.099
Token laughed
Token ID13818
Feature activation-8.04e+00

Pos logit contributions
led+0.462
ed+0.372
ied+0.333
awed+0.318
ier+0.313
Neg logit contributions
 pleasure-0.412
 think-0.371
 Deal-0.367
 great-0.365
 learn-0.364
Token and
Token ID290
Feature activation+2.41e+00

Pos logit contributions
led+0.586
ed+0.473
ied+0.449
awed+0.444
lers+0.415
Neg logit contributions
 pleasure-0.378
 great-0.340
 welcome-0.327
 OK-0.323
 Deal-0.316
Token.
Token ID13
Feature activation-1.05e+01

Pos logit contributions
led+0.214
ed+0.182
ling+0.164
y+0.159
ing+0.158
Neg logit contributions
 Deal-0.129
 pleasure-0.129
 learn-0.104
 OK-0.103
 know-0.101
Token But
Token ID887
Feature activation+7.78e+00

Pos logit contributions
led+0.833
ed+0.751
ted+0.642
y+0.639
ied+0.637
Neg logit contributions
 pleasure-0.406
 Deal-0.342
 great-0.324
 deal-0.315
 welcome-0.314
Token it
Token ID340
Feature activation+2.60e+00

Pos logit contributions
 pleasure+0.360
 Deal+0.322
 welcome+0.296
 learn+0.284
 great+0.282
Neg logit contributions
led-0.590
ed-0.505
ied-0.435
ked-0.425
ted-0.422
Token tw
Token ID665
Feature activation-7.54e+00

Pos logit contributions
 pleasure+0.119
 think+0.105
 great+0.104
 learn+0.102
 welcome+0.102
Neg logit contributions
led-0.190
ed-0.162
ied-0.144
ked-0.143
awed-0.139
Tokenink
Token ID676
Feature activation-1.28e+01

Pos logit contributions
led+0.510
ed+0.418
ied+0.353
awed+0.347
ked+0.338
Neg logit contributions
 pleasure-0.430
 Deal-0.389
 welcome-0.379
 learn-0.366
 great-0.357
Tokenled
Token ID992
Feature activation-2.62e+01

Pos logit contributions
led+0.407
ed+0.297
ked+0.238
ied+0.229
awed+0.217
Neg logit contributions
 pleasure-1.015
 great-0.969
 welcome-0.961
 think-0.947
 learn-0.943
Token in
Token ID287
Feature activation-1.36e+01

Pos logit contributions
led+1.871
ed+1.576
ied+1.357
awed+1.329
ked+1.320
Neg logit contributions
 pleasure-1.369
 Deal-1.194
 welcome-1.177
 great-1.139
 learn-1.109
Token the
Token ID262
Feature activation-3.49e+00

Pos logit contributions
led+0.926
ed+0.789
y+0.699
med+0.689
ied+0.684
Neg logit contributions
 pleasure-0.637
 Deal-0.598
 learn-0.533
 deal-0.513
 welcome-0.508
Token sunlight
Token ID19606
Feature activation-1.34e+00

Pos logit contributions
led+0.270
ed+0.230
ied+0.199
awed+0.193
ked+0.193
Neg logit contributions
 pleasure-0.159
 Deal-0.141
 welcome-0.130
 learn-0.126
 great-0.124
Token and
Token ID290
Feature activation+2.33e+00

Pos logit contributions
led+0.096
ed+0.079
ied+0.070
ked+0.070
awed+0.069
Neg logit contributions
 pleasure-0.067
 welcome-0.059
 learn-0.055
 great-0.055
 think-0.054
Token danced
Token ID39480
Feature activation-1.12e+01

Pos logit contributions
 pleasure+0.119
 welcome+0.102
 Deal+0.100
 think+0.100
 learn+0.099
Neg logit contributions
led-0.163
ed-0.136
ied-0.121
awed-0.117
ked-0.116
Token many
Token ID867
Feature activation-3.67e+00

Pos logit contributions
led+0.517
ed+0.442
ied+0.387
ted+0.373
ked+0.372
Neg logit contributions
 pleasure-0.279
 Deal-0.251
 welcome-0.226
 learn-0.223
 great-0.214
Token colors
Token ID7577
Feature activation-1.47e+00

Pos logit contributions
led+0.289
ed+0.250
ied+0.217
ked+0.216
awed+0.213
Neg logit contributions
 pleasure-0.162
 Deal-0.137
 welcome-0.137
 great-0.132
 learn-0.130
Token.
Token ID13
Feature activation-8.45e+00

Pos logit contributions
led+0.101
ed+0.084
ked+0.077
awed+0.077
ted+0.073
Neg logit contributions
 pleasure-0.069
 welcome-0.062
 have-0.060
 great-0.059
 learn-0.059
Token It
Token ID632
Feature activation+1.52e+00

Pos logit contributions
led+0.602
ed+0.556
y+0.476
ted+0.471
med+0.471
Neg logit contributions
 pleasure-0.344
 deal-0.288
 great-0.283
 Deal-0.277
 plan-0.277
Token spark
Token ID9009
Feature activation-6.44e+00

Pos logit contributions
 pleasure+0.062
 welcome+0.053
 Deal+0.053
 learn+0.053
 think+0.053
Neg logit contributions
led-0.122
ed-0.105
ied-0.094
ked-0.092
awed-0.092
Tokenled
Token ID992
Feature activation-2.60e+01

Pos logit contributions
led+0.118
ed+0.063
ied+0.049
awed+0.038
ked+0.036
Neg logit contributions
 pleasure-0.570
 great-0.563
 think-0.537
 welcome-0.531
 learn-0.530
Token in
Token ID287
Feature activation-1.35e+01

Pos logit contributions
led+1.745
ed+1.453
ied+1.250
awed+1.246
ked+1.218
Neg logit contributions
 pleasure-1.454
 welcome-1.288
 great-1.260
 Deal-1.218
 think-1.193
Token the
Token ID262
Feature activation-3.35e+00

Pos logit contributions
led+0.919
ed+0.769
med+0.685
ied+0.683
y+0.679
Neg logit contributions
 pleasure-0.650
 Deal-0.633
 learn-0.534
 deal-0.532
 welcome-0.530
Token sun
Token ID4252
Feature activation+3.36e+00

Pos logit contributions
led+0.262
ed+0.224
ied+0.194
ked+0.189
awed+0.188
Neg logit contributions
 pleasure-0.149
 Deal-0.133
 welcome-0.122
 learn-0.118
 think-0.116
Token,
Token ID11
Feature activation+4.20e+00

Pos logit contributions
 pleasure+0.170
 welcome+0.147
 Deal+0.143
 learn+0.140
 great+0.137
Neg logit contributions
led-0.242
ed-0.201
ied-0.177
awed-0.173
ked-0.171
Token and
Token ID290
Feature activation+2.50e+00

Pos logit contributions
 pleasure+0.211
 Deal+0.187
 welcome+0.180
 learn+0.173
 great+0.171
Neg logit contributions
led-0.308
ed-0.260
ied-0.224
ked-0.218
awed-0.217
Token It
Token ID632
Feature activation+8.21e-02

Pos logit contributions
led+0.833
ed+0.751
ted+0.642
y+0.639
ied+0.637
Neg logit contributions
 pleasure-0.406
 Deal-0.342
 great-0.324
 deal-0.315
 welcome-0.314
Token bark
Token ID21405
Feature activation-6.02e+00

Pos logit contributions
 pleasure+0.004
 think+0.003
 learn+0.003
 great+0.003
 have+0.003
Neg logit contributions
led-0.006
ed-0.005
ied-0.005
ked-0.004
awed-0.004
Tokened
Token ID276
Feature activation-2.30e+01

Pos logit contributions
led+0.149
ied+0.069
ed+0.052
awed+0.046
we+0.038
Neg logit contributions
 pleasure-0.525
 great-0.510
 welcome-0.505
 OK-0.494
 Deal-0.491
Token and
Token ID290
Feature activation+1.38e+00

Pos logit contributions
led+1.652
ed+1.381
ied+1.204
awed+1.173
ked+1.156
Neg logit contributions
 pleasure-1.190
 Deal-1.044
 welcome-1.025
 great-0.988
 learn-0.975
Token grow
Token ID1663
Feature activation+4.16e-01

Pos logit contributions
 pleasure+0.074
 Deal+0.066
 welcome+0.064
 learn+0.062
 great+0.062
Neg logit contributions
led-0.095
ed-0.079
ied-0.069
awed-0.066
ked-0.065
Tokenled
Token ID992
Feature activation-2.60e+01

Pos logit contributions
 great+0.040
 welcome+0.039
 good+0.038
 fun+0.038
 pleasure+0.038
Neg logit contributions
led-0.000
ked+0.001
attered+0.001
ied+0.002
awed+0.002
Token at
Token ID379
Feature activation-9.20e+00

Pos logit contributions
led+1.756
ed+1.443
ied+1.271
awed+1.246
ked+1.209
Neg logit contributions
 pleasure-1.462
 welcome-1.287
 Deal-1.263
 great-1.242
 think-1.208
Token them
Token ID606
Feature activation+3.40e+00

Pos logit contributions
led+0.720
ed+0.621
ied+0.543
ted+0.525
ked+0.522
Neg logit contributions
 pleasure-0.402
 Deal-0.368
 welcome-0.325
 learn-0.321
 great-0.311
Token,
Token ID11
Feature activation+4.12e+00

Pos logit contributions
 pleasure+0.187
 welcome+0.168
 learn+0.168
 think+0.164
 Deal+0.162
Neg logit contributions
led-0.229
ed-0.186
ied-0.159
awed-0.158
ked-0.154
Token and
Token ID290
Feature activation+2.41e+00

Pos logit contributions
 pleasure+0.199
 Deal+0.176
 welcome+0.167
 learn+0.160
 great+0.159
Neg logit contributions
led-0.308
ed-0.262
ied-0.225
ked-0.221
awed-0.220
Token they
Token ID484
Feature activation-3.11e+00

Pos logit contributions
 pleasure+0.117
 welcome+0.101
 think+0.100
 Deal+0.100
 learn+0.099
Neg logit contributions
led-0.173
ed-0.146
ied-0.131
awed-0.125
ier-0.125
Token looked
Token ID3114
Feature activation-5.33e+00

Pos logit contributions
led+0.068
ed+0.057
ied+0.050
ked+0.048
awed+0.048
Neg logit contributions
 pleasure-0.046
 Deal-0.041
 welcome-0.040
 learn-0.038
 great-0.038
Token at
Token ID379
Feature activation-1.07e+01

Pos logit contributions
led+0.439
ed+0.373
ied+0.327
ling+0.320
ked+0.316
Neg logit contributions
 pleasure-0.216
 Deal-0.196
 welcome-0.173
 learn-0.172
 think-0.161
Token them
Token ID606
Feature activation+2.21e+00

Pos logit contributions
led+0.811
ed+0.701
ied+0.612
ted+0.599
awed+0.587
Neg logit contributions
 pleasure-0.486
 Deal-0.446
 welcome-0.391
 learn-0.376
 deal-0.371
Token and
Token ID290
Feature activation+1.38e+00

Pos logit contributions
 pleasure+0.127
 Deal+0.113
 welcome+0.111
 learn+0.108
 great+0.107
Neg logit contributions
led-0.145
ed-0.120
ied-0.101
awed-0.099
ked-0.098
Token grow
Token ID1663
Feature activation+4.16e-01

Pos logit contributions
 pleasure+0.074
 welcome+0.065
 think+0.065
 Deal+0.065
 learn+0.064
Neg logit contributions
led-0.092
ed-0.076
ied-0.068
awed-0.064
ier-0.063
Tokenled
Token ID992
Feature activation-2.60e+01

Pos logit contributions
 great+0.038
 welcome+0.036
 good+0.035
 pleasure+0.035
 okay+0.035
Neg logit contributions
led-0.004
ked-0.002
awed-0.002
ed-0.002
ted-0.001
Token again
Token ID757
Feature activation-2.16e+00

Pos logit contributions
led+1.742
ed+1.430
ied+1.253
awed+1.236
ked+1.199
Neg logit contributions
 pleasure-1.473
 welcome-1.309
 great-1.265
 Deal-1.250
 think-1.230
Token.
Token ID13
Feature activation-7.26e+00

Pos logit contributions
led+0.136
ed+0.111
ied+0.094
ked+0.091
awed+0.090
Neg logit contributions
 pleasure-0.130
 welcome-0.116
 Deal-0.116
 learn-0.112
 great-0.112
Token Tom
Token ID4186
Feature activation+1.15e-01

Pos logit contributions
led+0.540
ed+0.499
ted+0.419
ked+0.414
awed+0.413
Neg logit contributions
 pleasure-0.292
 Deal-0.245
 great-0.242
 deal-0.240
 plan-0.239
Token and
Token ID290
Feature activation+2.41e+00

Pos logit contributions
 pleasure+0.005
 think+0.005
 welcome+0.005
 learn+0.005
 Deal+0.004
Neg logit contributions
led-0.009
ed-0.007
ied-0.007
ier-0.006
ked-0.006
Token Lily
Token ID20037
Feature activation-1.13e+00

Pos logit contributions
 pleasure+0.081
 Deal+0.067
 welcome+0.067
 learn+0.062
 think+0.061
Neg logit contributions
led-0.217
ed-0.187
ied-0.169
awed-0.165
ked-0.163
Token more
Token ID517
Feature activation+3.50e+00

Pos logit contributions
led+0.744
ed+0.645
ied+0.562
ked+0.551
awed+0.542
Neg logit contributions
 pleasure-0.385
 Deal-0.339
 welcome-0.315
 learn-0.297
 great-0.293
Token clothes
Token ID8242
Feature activation+4.02e+00

Pos logit contributions
 pleasure+0.159
 welcome+0.142
 learn+0.141
 great+0.140
 think+0.140
Neg logit contributions
led-0.259
ed-0.222
ked-0.196
awed-0.196
ied-0.188
Token and
Token ID290
Feature activation+3.50e+00

Pos logit contributions
 pleasure+0.145
 learn+0.133
 welcome+0.127
 see+0.127
 think+0.126
Neg logit contributions
led-0.325
ed-0.266
awed-0.254
ied-0.240
ted-0.236
Token toys
Token ID14958
Feature activation+2.71e+00

Pos logit contributions
 pleasure+0.166
 learn+0.166
 think+0.159
 see+0.156
 have+0.153
Neg logit contributions
led-0.235
ed-0.198
awed-0.182
ied-0.180
y-0.174
Token,
Token ID11
Feature activation+5.31e+00

Pos logit contributions
 pleasure+0.109
 have+0.102
 learn+0.102
 think+0.101
 see+0.100
Neg logit contributions
led-0.204
ed-0.161
awed-0.156
attered-0.148
ling-0.148
Token but
Token ID475
Feature activation+1.08e+01

Pos logit contributions
 pleasure+0.223
 Deal+0.192
 welcome+0.186
 learn+0.182
 think+0.177
Neg logit contributions
led-0.429
ed-0.370
ied-0.324
awed-0.319
ked-0.314
Token they
Token ID484
Feature activation-2.09e+00

Pos logit contributions
 pleasure+0.503
 Deal+0.440
 welcome+0.421
 learn+0.404
 great+0.401
Neg logit contributions
led-0.830
ed-0.706
ied-0.612
awed-0.598
ked-0.597
Token did
Token ID750
Feature activation-1.64e+00

Pos logit contributions
led+0.152
ed+0.129
med+0.114
awed+0.112
ied+0.111
Neg logit contributions
 pleasure-0.091
 think-0.089
 learn-0.086
 know-0.086
 have-0.085
Token not
Token ID407
Feature activation+1.00e+01

Pos logit contributions
led+0.162
ed+0.143
ied+0.128
ked+0.126
awed+0.125
Neg logit contributions
 pleasure-0.042
 Deal-0.033
 welcome-0.029
 learn-0.024
 great-0.024
Token find
Token ID1064
Feature activation+1.13e+01

Pos logit contributions
 pleasure+0.241
 Deal+0.186
 welcome+0.144
 great+0.131
 learn+0.119
Neg logit contributions
led-0.990
ed-0.880
ied-0.786
ked-0.779
y-0.776
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
 pleasure+0.449
 welcome+0.365
 Deal+0.358
 great+0.349
 learn+0.335
Neg logit contributions
led-0.959
ed-0.822
ied-0.728
awed-0.723
ked-0.710
Token learned
Token ID4499
Feature activation+5.09e-02

Pos logit contributions
led+0.006
ed+0.005
ied+0.005
ked+0.005
awed+0.005
Neg logit contributions
 pleasure-0.004
 learn-0.003
 welcome-0.003
 great-0.003
 think-0.003
Token that
Token ID326
Feature activation-1.02e+00

Pos logit contributions
 pleasure+0.003
 Deal+0.002
 welcome+0.002
 learn+0.002
 great+0.002
Neg logit contributions
led-0.004
ed-0.003
ied-0.003
ked-0.003
awed-0.003
Token sometimes
Token ID3360
Feature activation+1.24e+00

Pos logit contributions
led+0.072
ed+0.061
ied+0.054
ted+0.051
ing+0.051
Neg logit contributions
 pleasure-0.050
 Deal-0.048
 welcome-0.042
 great-0.039
 deal-0.039
Token things
Token ID1243
Feature activation+7.98e+00

Pos logit contributions
 Deal+0.061
 pleasure+0.060
 welcome+0.048
 meantime+0.046
 learn+0.045
Neg logit contributions
led-0.090
ed-0.074
ling-0.064
ing-0.064
lers-0.063
Token can
Token ID460
Feature activation+4.65e+00

Pos logit contributions
 pleasure+0.301
 Deal+0.267
 welcome+0.234
 learn+0.218
 great+0.214
Neg logit contributions
led-0.683
ed-0.588
ied-0.523
ked-0.505
ted-0.501
Token look
Token ID804
Feature activation+1.53e+01

Pos logit contributions
 pleasure+0.180
 Deal+0.155
 welcome+0.127
 great+0.110
 meantime+0.110
Neg logit contributions
led-0.381
ed-0.326
ling-0.304
y-0.300
ier-0.292
Token scary
Token ID14343
Feature activation-7.08e-01

Pos logit contributions
 pleasure+0.607
 Deal+0.527
 welcome+0.489
 learn+0.465
 great+0.451
Neg logit contributions
led-1.277
ed-1.098
ied-0.966
ked-0.943
awed-0.936
Token,
Token ID11
Feature activation+5.35e+00

Pos logit contributions
led+0.054
ed+0.045
ied+0.040
awed+0.040
ked+0.039
Neg logit contributions
 pleasure-0.033
 welcome-0.028
 Deal-0.028
 great-0.027
 learn-0.026
Token but
Token ID475
Feature activation+1.08e+01

Pos logit contributions
 pleasure+0.247
 Deal+0.238
 welcome+0.208
 meantime+0.192
 learn+0.191
Neg logit contributions
led-0.400
ed-0.339
ied-0.294
y-0.285
we-0.284
Token it
Token ID340
Feature activation+5.52e+00

Pos logit contributions
 pleasure+0.520
 Deal+0.510
 welcome+0.430
 meantime+0.425
 learn+0.401
Neg logit contributions
led-0.755
ed-0.640
ied-0.572
ing-0.547
y-0.534
Token's
Token ID338
Feature activation-2.85e+00

Pos logit contributions
 pleasure+0.288
 Deal+0.257
 welcome+0.244
 learn+0.232
 great+0.231
Neg logit contributions
led-0.397
ed-0.332
ied-0.283
ked-0.273
ling-0.272
Token.
Token ID13
Feature activation-5.92e+00

Pos logit contributions
 pleasure+0.520
 great+0.469
 welcome+0.464
 Deal+0.462
 think+0.459
Neg logit contributions
led-0.673
ed-0.553
ked-0.493
ied-0.484
awed-0.471
Token<|endoftext|>
Token ID50256
Feature activation+2.11e+00

Pos logit contributions
led+0.373
ed+0.358
med+0.300
ted+0.298
es+0.295
Neg logit contributions
 deal-0.242
 pleasure-0.241
 plan-0.236
 great-0.212
 learn-0.211
TokenOnce
Token ID7454
Feature activation+7.19e+00

Pos logit contributions
 pleasure+0.060
 Deal+0.049
 welcome+0.042
 learn+0.041
 great+0.039
Neg logit contributions
led-0.200
ed-0.179
ied-0.157
awed-0.155
ted-0.154
Token upon
Token ID2402
Feature activation-1.61e+00

Pos logit contributions
 pleasure+0.378
 Deal+0.342
 welcome+0.319
 learn+0.313
 great+0.305
Neg logit contributions
led-0.509
ed-0.427
ied-0.372
y-0.352
awed-0.351
Token a
Token ID257
Feature activation+3.33e+00

Pos logit contributions
led+0.121
ed+0.104
y+0.086
med+0.086
awed+0.086
Neg logit contributions
 pleasure-0.075
 Deal-0.068
 welcome-0.059
 deal-0.056
 meantime-0.056
Token time
Token ID640
Feature activation+1.05e+01

Pos logit contributions
 pleasure+0.124
 Deal+0.104
 learn+0.102
 welcome+0.098
 Anything+0.092
Neg logit contributions
led-0.265
y-0.216
ed-0.215
ling-0.206
awed-0.203
Token,
Token ID11
Feature activation+5.36e+00

Pos logit contributions
 pleasure+0.556
 Deal+0.514
 learn+0.473
 deal+0.461
 compromise+0.445
Neg logit contributions
led-0.725
ed-0.646
y-0.539
ied-0.534
ing-0.521
Token there
Token ID612
Feature activation-2.71e+00

Pos logit contributions
 pleasure+0.307
 Deal+0.276
 welcome+0.265
 learn+0.257
 great+0.254
Neg logit contributions
led-0.357
ed-0.296
ied-0.249
ked-0.241
awed-0.241
Token was
Token ID373
Feature activation-1.55e+00

Pos logit contributions
led+0.154
ed+0.128
ied+0.102
y+0.100
awed+0.097
Neg logit contributions
 pleasure-0.181
 Deal-0.175
 learn-0.156
 welcome-0.155
 think-0.150
Token a
Token ID257
Feature activation+3.35e+00

Pos logit contributions
led+0.119
ed+0.104
med+0.088
ied+0.087
awed+0.086
Neg logit contributions
 pleasure-0.067
 Deal-0.064
 deal-0.057
 learn-0.055
 welcome-0.055
Token little
Token ID1310
Feature activation+2.60e+00

Pos logit contributions
 pleasure+0.144
 Deal+0.133
 learn+0.112
 welcome+0.109
 know+0.108
Neg logit contributions
led-0.257
ed-0.218
y-0.196
ling-0.195
ked-0.188
Token.
Token ID13
Feature activation-5.92e+00

Pos logit contributions
led+0.083
ed+0.069
awed+0.063
ied+0.063
ked+0.061
Neg logit contributions
 pleasure-0.049
 great-0.043
 have-0.042
 welcome-0.042
 be-0.042
Token No
Token ID1400
Feature activation+2.19e+00

Pos logit contributions
led+0.406
ed+0.362
ted+0.299
med+0.297
ked+0.292
Neg logit contributions
 pleasure-0.293
 welcome-0.265
 Deal-0.260
 think-0.257
 learn-0.254
Token one
Token ID530
Feature activation+8.65e+00

Pos logit contributions
 pleasure+0.077
 Deal+0.064
 welcome+0.060
 learn+0.056
 great+0.056
Neg logit contributions
led-0.195
ed-0.169
ied-0.150
ked-0.147
awed-0.147
Token would
Token ID561
Feature activation-5.15e+00

Pos logit contributions
 pleasure+0.446
 think+0.389
 welcome+0.388
 know+0.383
 great+0.374
Neg logit contributions
led-0.618
ed-0.499
ked-0.468
awed-0.449
ier-0.437
Token ever
Token ID1683
Feature activation-6.72e+00

Pos logit contributions
led+0.409
ed+0.358
ked+0.324
y+0.322
ier+0.319
Neg logit contributions
 pleasure-0.169
 Deal-0.164
 welcome-0.126
 meantime-0.118
 Today-0.117
Token guess
Token ID4724
Feature activation+1.73e+01

Pos logit contributions
led+0.633
ed+0.561
ked+0.496
y+0.492
ied+0.492
Neg logit contributions
 pleasure-0.180
 Deal-0.159
 welcome-0.123
 great-0.111
 meantime-0.102
Token it
Token ID340
Feature activation+5.53e+00

Pos logit contributions
 pleasure+0.738
 Deal+0.618
 welcome+0.609
 great+0.588
 learn+0.583
Neg logit contributions
led-1.398
ed-1.195
ied-1.049
awed-1.035
ked-1.028
Token was
Token ID373
Feature activation-1.61e+00

Pos logit contributions
 pleasure+0.285
 great+0.254
 welcome+0.253
 think+0.249
 learn+0.248
Neg logit contributions
led-0.385
ed-0.310
ied-0.278
awed-0.276
ked-0.273
Token a
Token ID257
Feature activation+3.30e+00

Pos logit contributions
led+0.127
ed+0.108
ied+0.094
awed+0.092
ked+0.092
Neg logit contributions
 pleasure-0.073
 welcome-0.062
 Deal-0.062
 great-0.059
 learn-0.058
Token lung
Token ID12317
Feature activation-2.25e+00

Pos logit contributions
 Deal+0.136
 pleasure+0.132
 learn+0.115
 welcome+0.113
 know+0.108
Neg logit contributions
led-0.241
ed-0.210
y-0.184
ling-0.179
ked-0.178
Token.
Token ID13
Feature activation-5.96e+00

Pos logit contributions
led+0.169
ed+0.141
ied+0.124
awed+0.122
ked+0.120
Neg logit contributions
 pleasure-0.112
 welcome-0.097
 great-0.093
 learn-0.090
 think-0.090
Token She
Token ID1375
Feature activation-3.81e+00

Pos logit contributions
led+0.470
ed+0.444
ted+0.379
ked+0.366
awed+0.365
Neg logit contributions
 pleasure-0.215
 deal-0.188
 plan-0.180
 Deal-0.179
 great-0.178
Token knew
Token ID2993
Feature activation-2.27e+00

Pos logit contributions
led+0.251
ed+0.206
ier+0.182
ied+0.181
ing+0.174
Neg logit contributions
 pleasure-0.204
 think-0.185
 learn-0.181
 great-0.181
 know-0.178
Token she
Token ID673
Feature activation-4.54e+00

Pos logit contributions
led+0.177
ed+0.149
ied+0.129
awed+0.129
ked+0.127
Neg logit contributions
 pleasure-0.106
 Deal-0.089
 welcome-0.089
 great-0.086
 learn-0.084
Token had
Token ID550
Feature activation-7.56e+00

Pos logit contributions
led+0.335
ed+0.272
awed+0.253
med+0.252
ked+0.251
Neg logit contributions
 pleasure-0.203
 have-0.189
 great-0.185
 think-0.184
 know-0.183
Token to
Token ID284
Feature activation-4.43e+00

Pos logit contributions
led+0.552
ed+0.458
ied+0.392
ked+0.389
ling+0.386
Neg logit contributions
 pleasure-0.389
 welcome-0.335
 great-0.330
 Deal-0.329
 learn-0.327
Token tell
Token ID1560
Feature activation+1.09e+01

Pos logit contributions
led+0.320
ed+0.274
ly+0.248
ling+0.244
ied+0.243
Neg logit contributions
 pleasure-0.168
 Deal-0.151
 Today-0.123
 Sometimes-0.122
 Not-0.117
Token her
Token ID607
Feature activation-2.33e+00

Pos logit contributions
 pleasure+0.539
 Deal+0.485
 welcome+0.452
 learn+0.428
 great+0.426
Neg logit contributions
led-0.796
ed-0.677
ied-0.586
ked-0.564
ted-0.563
Token dad
Token ID9955
Feature activation+7.02e+00

Pos logit contributions
led+0.211
ed+0.183
ied+0.162
awed+0.161
ked+0.161
Neg logit contributions
 pleasure-0.079
 Deal-0.064
 welcome-0.062
 learn-0.059
 great-0.059
Token about
Token ID546
Feature activation-1.97e+00

Pos logit contributions
 pleasure+0.291
 welcome+0.249
 learn+0.243
 great+0.237
 Deal+0.237
Neg logit contributions
led-0.569
ed-0.486
awed-0.429
ked-0.426
ied-0.418
Token the
Token ID262
Feature activation-1.96e+00

Pos logit contributions
led+0.157
ed+0.135
ied+0.119
ked+0.115
awed+0.115
Neg logit contributions
 pleasure-0.085
 Deal-0.075
 welcome-0.070
 learn-0.066
 great-0.065
Token bug
Token ID5434
Feature activation-5.88e+00

Pos logit contributions
led+0.155
ed+0.132
ied+0.116
awed+0.112
ked+0.112
Neg logit contributions
 pleasure-0.086
 Deal-0.076
 welcome-0.071
 learn-0.068
 great-0.066
Token handed
Token ID10158
Feature activation-7.39e+00

Pos logit contributions
 pleasure+0.133
 welcome+0.117
 learn+0.115
 have+0.112
 think+0.112
Neg logit contributions
led-0.240
ed-0.199
awed-0.182
ied-0.180
ked-0.178
Token the
Token ID262
Feature activation-2.46e+00

Pos logit contributions
led+0.641
ed+0.546
awed+0.491
ied+0.486
ked+0.479
Neg logit contributions
 pleasure-0.263
 welcome-0.219
 great-0.204
 Deal-0.204
 learn-0.201
Token ball
Token ID2613
Feature activation-1.48e+00

Pos logit contributions
led+0.160
ed+0.136
ked+0.113
awed+0.111
ied+0.110
Neg logit contributions
 pleasure-0.134
 Deal-0.129
 welcome-0.114
 learn-0.113
 know-0.111
Token to
Token ID284
Feature activation-4.94e+00

Pos logit contributions
led+0.131
awed+0.102
ed+0.100
we+0.100
med+0.098
Neg logit contributions
 pleasure-0.049
 welcome-0.048
 learn-0.046
 try-0.045
 great-0.043
Token the
Token ID262
Feature activation-2.49e+00

Pos logit contributions
led+0.369
ed+0.311
ied+0.270
ted+0.269
ked+0.266
Neg logit contributions
 pleasure-0.236
 Deal-0.215
 welcome-0.190
 learn-0.182
 think-0.180
Token dog
Token ID3290
Feature activation-2.94e+00

Pos logit contributions
led+0.165
ed+0.140
ling+0.116
awed+0.116
ked+0.115
Neg logit contributions
 pleasure-0.135
 Deal-0.127
 welcome-0.112
 learn-0.110
 know-0.110
Token.
Token ID13
Feature activation-6.42e+00

Pos logit contributions
led+0.209
ed+0.168
ied+0.149
awed+0.145
ier+0.141
Neg logit contributions
 pleasure-0.154
 learn-0.141
 welcome-0.141
 think-0.139
 know-0.135
Token
Token ID198
Feature activation+8.71e+00

Pos logit contributions
led+0.523
ed+0.473
ted+0.403
awed+0.399
ied+0.396
Neg logit contributions
 pleasure-0.249
 Deal-0.222
 great-0.201
 deal-0.198
 welcome-0.197
Token
Token ID198
Feature activation+8.71e+00

Pos logit contributions
 pleasure+0.358
 Deal+0.285
 deal+0.249
 meantime+0.235
 welcome+0.227
Neg logit contributions
led-0.725
ed-0.654
ied-0.581
med-0.570
awed-0.560
TokenThe
Token ID464
Feature activation-6.14e+00

Pos logit contributions
 pleasure+0.419
 Deal+0.351
 welcome+0.330
 great+0.308
 think+0.307
Neg logit contributions
led-0.669
ed-0.569
ied-0.501
med-0.492
awed-0.482
Token dog
Token ID3290
Feature activation-3.00e+00

Pos logit contributions
led+0.401
ed+0.331
ling+0.280
awed+0.271
ked+0.271
Neg logit contributions
 pleasure-0.354
 Deal-0.320
 welcome-0.283
 know-0.278
 learn-0.277
Token stop
Token ID2245
Feature activation+7.59e+00

Pos logit contributions
 pleasure+0.092
 Deal+0.080
 welcome+0.070
 learn+0.066
 great+0.065
Neg logit contributions
led-0.214
ed-0.187
ied-0.165
ked-0.163
y-0.162
Token.
Token ID13
Feature activation-6.45e+00

Pos logit contributions
 pleasure+0.430
 Deal+0.383
 welcome+0.379
 great+0.369
 learn+0.365
Neg logit contributions
led-0.506
ed-0.413
ied-0.357
awed-0.343
ked-0.335
Token He
Token ID679
Feature activation-4.79e+00

Pos logit contributions
led+0.481
ed+0.433
ked+0.355
ied+0.353
ted+0.353
Neg logit contributions
 pleasure-0.307
 Deal-0.260
 welcome-0.256
 great-0.240
 think-0.230
Token spun
Token ID26843
Feature activation-1.06e+01

Pos logit contributions
led+0.327
ed+0.270
ied+0.243
ked+0.234
ier+0.232
Neg logit contributions
 pleasure-0.235
 great-0.223
 think-0.222
 learn-0.218
 know-0.215
Token around
Token ID1088
Feature activation-9.62e+00

Pos logit contributions
led+0.717
ed+0.596
ied+0.503
ked+0.488
awed+0.486
Neg logit contributions
 pleasure-0.596
 Deal-0.536
 welcome-0.516
 learn-0.498
 great-0.494
Token and
Token ID290
Feature activation+2.96e+00

Pos logit contributions
led+0.688
ed+0.587
ied+0.494
ked+0.485
med+0.480
Neg logit contributions
 pleasure-0.495
 Deal-0.448
 welcome-0.418
 learn-0.399
 great-0.393
Token around
Token ID1088
Feature activation-9.63e+00

Pos logit contributions
 pleasure+0.181
 learn+0.164
 great+0.163
 think+0.163
 welcome+0.161
Neg logit contributions
led-0.173
ed-0.135
ied-0.119
awed-0.114
ier-0.112
Token until
Token ID1566
Feature activation+7.44e+00

Pos logit contributions
led+0.729
ed+0.624
ied+0.532
ked+0.523
awed+0.518
Neg logit contributions
 pleasure-0.458
 Deal-0.409
 welcome-0.383
 learn-0.365
 great-0.361
Token he
Token ID339
Feature activation-6.62e+00

Pos logit contributions
 pleasure+0.385
 Deal+0.340
 welcome+0.333
 great+0.326
 learn+0.325
Neg logit contributions
led-0.529
ed-0.438
ied-0.382
awed-0.373
ked-0.371
Token was
Token ID373
Feature activation-2.22e+00

Pos logit contributions
led+0.442
ed+0.349
ied+0.314
ked+0.311
lers+0.299
Neg logit contributions
 pleasure-0.349
 great-0.321
 welcome-0.307
 learn-0.307
 think-0.306
Token dizz
Token ID29527
Feature activation+5.03e-01

Pos logit contributions
led+0.165
ed+0.142
ied+0.122
med+0.119
awed+0.119
Neg logit contributions
 pleasure-0.104
 Deal-0.094
 welcome-0.085
 learn-0.083
 deal-0.083
Token saw
Token ID2497
Feature activation-2.45e+00

Pos logit contributions
 pleasure+0.172
 Deal+0.152
 welcome+0.149
 learn+0.145
 great+0.144
Neg logit contributions
led-0.198
ed-0.163
ied-0.139
awed-0.135
ked-0.134
Token how
Token ID703
Feature activation+5.69e+00

Pos logit contributions
led+0.218
ed+0.189
ied+0.168
awed+0.166
ked+0.166
Neg logit contributions
 pleasure-0.086
 welcome-0.067
 Deal-0.066
 great-0.064
 learn-0.062
Token happy
Token ID3772
Feature activation+1.06e+01

Pos logit contributions
 pleasure+0.185
 great+0.153
 welcome+0.145
 learn+0.135
 know+0.129
Neg logit contributions
led-0.499
ed-0.442
ked-0.405
awed-0.398
ted-0.392
Token and
Token ID290
Feature activation+3.11e+00

Pos logit contributions
 pleasure+0.417
 welcome+0.341
 great+0.335
 learn+0.325
 think+0.317
Neg logit contributions
led-0.879
ed-0.755
ied-0.671
awed-0.666
ked-0.664
Token safe
Token ID3338
Feature activation+3.31e+00

Pos logit contributions
 pleasure+0.114
 Deal+0.096
 welcome+0.090
 learn+0.085
 great+0.084
Neg logit contributions
led-0.271
ed-0.235
ied-0.208
ked-0.204
awed-0.203
Token the
Token ID262
Feature activation-2.39e+00

Pos logit contributions
 pleasure+0.166
 welcome+0.147
 great+0.142
 learn+0.138
 think+0.135
Neg logit contributions
led-0.237
ed-0.197
awed-0.175
ked-0.172
ied-0.170
Token area
Token ID1989
Feature activation-1.18e+00

Pos logit contributions
led+0.190
ed+0.162
ied+0.142
ling+0.140
ked+0.138
Neg logit contributions
 pleasure-0.098
 Deal-0.091
 welcome-0.079
 learn-0.077
 know-0.075
Token was
Token ID373
Feature activation-1.90e+00

Pos logit contributions
led+0.082
ed+0.068
awed+0.064
ked+0.063
ted+0.059
Neg logit contributions
 pleasure-0.057
 welcome-0.052
 great-0.052
 have-0.051
 learn-0.050
Token.
Token ID13
Feature activation-6.24e+00

Pos logit contributions
led+0.135
ed+0.113
awed+0.097
ked+0.096
ied+0.096
Neg logit contributions
 pleasure-0.101
 welcome-0.089
 great-0.087
 learn-0.084
 think-0.082
Token They
Token ID1119
Feature activation+9.08e-01

Pos logit contributions
led+0.481
ed+0.443
ted+0.386
awed+0.379
ied+0.368
Neg logit contributions
 pleasure-0.225
 Deal-0.204
 deal-0.200
 welcome-0.194
 great-0.194
Token knew
Token ID2993
Feature activation-2.59e+00

Pos logit contributions
 pleasure+0.049
 learn+0.043
 welcome+0.043
 think+0.042
 know+0.042
Neg logit contributions
led-0.062
ed-0.052
ied-0.044
awed-0.044
we-0.043
Token a
Token ID257
Feature activation+3.34e+00

Pos logit contributions
led+1.082
ed+0.941
ied+0.830
ked+0.814
awed+0.812
Neg logit contributions
 pleasure-0.472
 Deal-0.400
 welcome-0.375
 learn-0.352
 great-0.348
Token boy
Token ID2933
Feature activation-2.21e-01

Pos logit contributions
 pleasure+0.145
 Deal+0.124
 welcome+0.123
 great+0.118
 learn+0.116
Neg logit contributions
led-0.268
ed-0.229
ied-0.200
ked-0.196
awed-0.194
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
led+0.017
ed+0.014
ied+0.013
ier+0.012
awed+0.011
Neg logit contributions
 learn-0.010
 think-0.010
 pleasure-0.009
 have-0.009
 welcome-0.009
Token made
Token ID925
Feature activation-5.77e+00

Pos logit contributions
 think+0.165
 pleasure+0.163
 learn+0.162
 have+0.162
 know+0.161
Neg logit contributions
led-0.247
ed-0.207
ied-0.187
awed-0.181
ier-0.181
Token him
Token ID683
Feature activation+1.73e+00

Pos logit contributions
led+0.489
ed+0.424
ied+0.374
ked+0.365
awed+0.364
Neg logit contributions
 pleasure-0.223
 Deal-0.190
 welcome-0.179
 learn-0.169
 great-0.167
Token fall
Token ID2121
Feature activation+5.37e+00

Pos logit contributions
 pleasure+0.060
 Deal+0.049
 welcome+0.049
 learn+0.048
 great+0.046
Neg logit contributions
led-0.154
ed-0.133
ied-0.119
awed-0.117
ked-0.116
Token down
Token ID866
Feature activation-3.12e+00

Pos logit contributions
 pleasure+0.237
 great+0.230
 welcome+0.227
 OK+0.224
 try+0.221
Neg logit contributions
led-0.381
ed-0.297
awed-0.283
ied-0.282
ils-0.269
Token.
Token ID13
Feature activation-5.89e+00

Pos logit contributions
led+0.242
ed+0.198
ked+0.180
awed+0.179
ied+0.176
Neg logit contributions
 welcome-0.133
 pleasure-0.130
 great-0.128
 learn-0.123
 have-0.123
Token She
Token ID1375
Feature activation-3.83e+00

Pos logit contributions
led+0.531
ed+0.475
ted+0.415
awed+0.414
ied+0.411
Neg logit contributions
 pleasure-0.198
 Deal-0.162
 welcome-0.141
 great-0.130
 learn-0.130
Token felt
Token ID2936
Feature activation-1.90e+00

Pos logit contributions
led+0.274
ed+0.238
ied+0.215
ier+0.213
ked+0.208
Neg logit contributions
 have-0.153
 think-0.151
 great-0.151
 know-0.150
 be-0.148
Token very
Token ID845
Feature activation+5.21e+00

Pos logit contributions
led+0.150
ed+0.128
ied+0.110
ked+0.108
ted+0.107
Neg logit contributions
 pleasure-0.086
 Deal-0.076
 welcome-0.068
 deal-0.065
 learn-0.065
Token the
Token ID262
Feature activation-3.35e+00

Pos logit contributions
led+0.739
ed+0.633
ied+0.555
ked+0.538
awed+0.537
Neg logit contributions
 pleasure-0.399
 Deal-0.351
 welcome-0.329
 learn-0.316
 great-0.311
Token dinosaur
Token ID28257
Feature activation-8.42e+00

Pos logit contributions
led+0.258
ed+0.219
ied+0.190
ked+0.185
awed+0.185
Neg logit contributions
 pleasure-0.157
 Deal-0.137
 welcome-0.132
 great-0.126
 learn-0.126
Token.
Token ID13
Feature activation-7.05e+00

Pos logit contributions
led+0.600
ed+0.505
ied+0.435
awed+0.433
ted+0.427
Neg logit contributions
 pleasure-0.406
 learn-0.387
 deal-0.375
 plan-0.369
 think-0.367
Token He
Token ID679
Feature activation-5.27e+00

Pos logit contributions
led+0.486
ed+0.435
ked+0.355
ied+0.353
awed+0.352
Neg logit contributions
 pleasure-0.339
 Deal-0.309
 learn-0.289
 welcome-0.289
 great-0.285
Token couldn
Token ID3521
Feature activation-4.25e+00

Pos logit contributions
led+0.348
ed+0.289
ied+0.250
ier+0.238
ked+0.235
Neg logit contributions
 pleasure-0.293
 Deal-0.260
 great-0.255
 learn-0.254
 welcome-0.253
Token't
Token ID470
Feature activation+2.12e+00

Pos logit contributions
led+0.357
ed+0.323
med+0.276
ied+0.275
ted+0.271
Neg logit contributions
 pleasure-0.167
 Deal-0.131
 welcome-0.121
 deal-0.113
 great-0.110
Token believe
Token ID1975
Feature activation+1.14e+01

Pos logit contributions
 pleasure+0.064
 Deal+0.051
 welcome+0.044
 great+0.040
 meantime+0.038
Neg logit contributions
led-0.195
ed-0.173
ked-0.154
ly-0.151
ier-0.150
Token that
Token ID326
Feature activation-1.81e+00

Pos logit contributions
 pleasure+0.401
 welcome+0.330
 think+0.328
 great+0.324
 Deal+0.322
Neg logit contributions
led-0.973
ed-0.855
awed-0.754
ked-0.733
ied-0.732
Token a
Token ID257
Feature activation+2.58e+00

Pos logit contributions
led+0.140
ed+0.120
ied+0.104
ked+0.101
awed+0.101
Neg logit contributions
 pleasure-0.084
 Deal-0.074
 welcome-0.070
 learn-0.067
 great-0.066
Token real
Token ID1103
Feature activation-1.06e+00

Pos logit contributions
 pleasure+0.106
 Deal+0.094
 welcome+0.087
 learn+0.084
 think+0.081
Neg logit contributions
led-0.209
ed-0.181
ied-0.156
ked-0.154
awed-0.153
Token,
Token ID11
Feature activation+4.69e+00

Pos logit contributions
led+0.075
ed+0.062
ied+0.054
awed+0.052
ked+0.052
Neg logit contributions
 pleasure-0.056
 Deal-0.049
 welcome-0.048
 great-0.046
 learn-0.046
Token nap
Token ID25422
Feature activation+5.49e+00

Pos logit contributions
led+0.888
ed+0.799
y+0.698
ied+0.693
ling+0.677
Neg logit contributions
 pleasure-0.352
 Deal-0.292
 great-0.234
 welcome-0.223
 meantime-0.212
Token under
Token ID739
Feature activation-1.61e+01

Pos logit contributions
 pleasure+0.333
 Deal+0.304
 welcome+0.299
 great+0.291
 learn+0.288
Neg logit contributions
led-0.334
ed-0.275
ied-0.233
ked-0.228
awed-0.226
Token the
Token ID262
Feature activation-2.14e+00

Pos logit contributions
led+1.210
ed+1.035
ted+0.890
med+0.885
ied+0.869
Neg logit contributions
 pleasure-0.748
 Deal-0.669
 welcome-0.614
 deal-0.578
 think-0.569
Token big
Token ID1263
Feature activation-7.88e-01

Pos logit contributions
led+0.206
ed+0.182
ied+0.163
ked+0.162
awed+0.160
Neg logit contributions
 pleasure-0.059
 Deal-0.046
 welcome-0.044
 learn-0.040
 great-0.040
Token tree
Token ID5509
Feature activation+1.89e-01

Pos logit contributions
led+0.068
ed+0.059
ied+0.052
ked+0.051
awed+0.051
Neg logit contributions
 pleasure-0.029
 Deal-0.025
 welcome-0.024
 learn-0.022
 great-0.022
Token in
Token ID287
Feature activation-1.21e+01

Pos logit contributions
 pleasure+0.010
 learn+0.009
 welcome+0.009
 think+0.009
 have+0.009
Neg logit contributions
led-0.013
ed-0.011
ked-0.010
ied-0.009
awed-0.009
Token the
Token ID262
Feature activation-2.10e+00

Pos logit contributions
led+0.837
ed+0.714
ied+0.604
med+0.596
y+0.594
Neg logit contributions
 pleasure-0.615
 Deal-0.555
 welcome-0.484
 deal-0.484
 learn-0.480
Token park
Token ID3952
Feature activation+8.76e+00

Pos logit contributions
led+0.165
ed+0.142
ied+0.123
awed+0.121
ted+0.119
Neg logit contributions
 pleasure-0.093
 Deal-0.081
 welcome-0.075
 learn-0.073
 think-0.072
Token.
Token ID13
Feature activation-5.97e+00

Pos logit contributions
 pleasure+0.474
 welcome+0.432
 learn+0.427
 think+0.413
 have+0.405
Neg logit contributions
led-0.602
ed-0.487
ied-0.422
ked-0.421
awed-0.417
Token Her
Token ID2332
Feature activation-5.01e+00

Pos logit contributions
led+0.460
ed+0.425
ted+0.368
y+0.361
awed+0.360
Neg logit contributions
 pleasure-0.247
 Deal-0.218
 welcome-0.195
 great-0.189
 deal-0.185
Token mom
Token ID1995
Feature activation+6.24e+00

Pos logit contributions
led+0.423
ed+0.375
ied+0.326
awed+0.318
y+0.317
Neg logit contributions
 pleasure-0.172
 Deal-0.152
 welcome-0.134
 learn-0.133
 think-0.130
Token was
Token ID373
Feature activation-4.11e+00

Pos logit contributions
 pleasure+0.126
 think+0.111
 great+0.110
 learn+0.109
 welcome+0.107
Neg logit contributions
led-0.183
ed-0.150
awed-0.138
ied-0.135
ked-0.134
Token too
Token ID1165
Feature activation+5.28e+00

Pos logit contributions
led+0.362
ed+0.310
ied+0.282
y+0.270
ling+0.268
Neg logit contributions
 pleasure-0.135
 Deal-0.114
 learn-0.105
 welcome-0.097
 think-0.094
Token big
Token ID1263
Feature activation-2.58e+00

Pos logit contributions
 pleasure+0.217
 Deal+0.187
 welcome+0.178
 great+0.169
 learn+0.169
Neg logit contributions
led-0.436
ed-0.376
ied-0.330
ked-0.324
awed-0.322
Token to
Token ID284
Feature activation-6.13e+00

Pos logit contributions
led+0.207
ed+0.170
ied+0.157
awed+0.155
ked+0.152
Neg logit contributions
 pleasure-0.110
 welcome-0.094
 think-0.089
 learn-0.088
 deal-0.087
Token fit
Token ID4197
Feature activation-4.94e+00

Pos logit contributions
led+0.506
ed+0.432
y+0.389
ied+0.388
ling+0.384
Neg logit contributions
 pleasure-0.233
 Deal-0.201
 welcome-0.159
 great-0.151
 meantime-0.147
Token in
Token ID287
Feature activation-1.33e+01

Pos logit contributions
led+0.325
ed+0.265
awed+0.235
ked+0.234
ied+0.226
Neg logit contributions
 pleasure-0.271
 welcome-0.244
 great-0.239
 think-0.234
 Deal-0.232
Token the
Token ID262
Feature activation-3.22e+00

Pos logit contributions
led+0.967
ed+0.830
ied+0.749
med+0.722
y+0.709
Neg logit contributions
 pleasure-0.598
 Deal-0.544
 welcome-0.478
 learn-0.464
 deal-0.455
Token suitcase
Token ID45391
Feature activation-3.07e+00

Pos logit contributions
led+0.247
ed+0.210
ied+0.183
ling+0.177
awed+0.176
Neg logit contributions
 pleasure-0.144
 Deal-0.128
 welcome-0.117
 learn-0.115
 know-0.112
Token,
Token ID11
Feature activation+4.30e+00

Pos logit contributions
led+0.212
ed+0.174
awed+0.152
ked+0.151
ied+0.147
Neg logit contributions
 pleasure-0.165
 welcome-0.149
 learn-0.144
 think-0.140
 great-0.140
Token and
Token ID290
Feature activation+2.59e+00

Pos logit contributions
 pleasure+0.189
 Deal+0.171
 welcome+0.156
 learn+0.149
 great+0.146
Neg logit contributions
led-0.332
ed-0.285
ied-0.246
ked-0.243
awed-0.239
Token that
Token ID326
Feature activation-1.93e+00

Pos logit contributions
 pleasure+0.121
 welcome+0.103
 Deal+0.102
 learn+0.100
 think+0.099
Neg logit contributions
led-0.196
ed-0.164
ied-0.144
awed-0.144
ked-0.142
Token look
Token ID804
Feature activation+1.48e+01

Pos logit contributions
led+0.384
ed+0.343
ied+0.310
y+0.304
ted+0.294
Neg logit contributions
 pleasure-0.182
 Deal-0.169
 Today-0.121
 great-0.120
 welcome-0.118
Token for
Token ID329
Feature activation-1.19e+00

Pos logit contributions
 pleasure+0.700
 welcome+0.624
 Deal+0.611
 great+0.604
 learn+0.588
Neg logit contributions
led-1.087
ed-0.932
awed-0.833
ked-0.822
ied-0.796
Token her
Token ID607
Feature activation-2.81e+00

Pos logit contributions
led+0.083
ed+0.070
ied+0.060
ted+0.058
ked+0.058
Neg logit contributions
 pleasure-0.061
 Deal-0.057
 welcome-0.052
 learn-0.050
 think-0.049
Token dolls
Token ID36062
Feature activation-3.58e+00

Pos logit contributions
led+0.213
ed+0.180
ied+0.156
ked+0.152
awed+0.152
Neg logit contributions
 pleasure-0.135
 Deal-0.119
 welcome-0.114
 learn-0.109
 great-0.109
Token again
Token ID757
Feature activation-1.10e+00

Pos logit contributions
led+0.266
ed+0.217
awed+0.196
ied+0.193
med+0.187
Neg logit contributions
 pleasure-0.169
 welcome-0.153
 learn-0.153
 think-0.147
 have-0.143
Token.
Token ID13
Feature activation-6.29e+00

Pos logit contributions
led+0.068
ed+0.055
ied+0.046
awed+0.044
ked+0.044
Neg logit contributions
 pleasure-0.068
 Deal-0.062
 welcome-0.059
 learn-0.057
 great-0.057
Token She
Token ID1375
Feature activation-4.21e+00

Pos logit contributions
led+0.398
ed+0.373
ted+0.294
ked+0.293
ied+0.293
Neg logit contributions
 pleasure-0.328
 Deal-0.294
 great-0.284
 welcome-0.278
 plan-0.266
Token opened
Token ID4721
Feature activation-1.28e+01

Pos logit contributions
led+0.300
ed+0.248
ier+0.231
ing+0.227
ied+0.224
Neg logit contributions
 think-0.188
 pleasure-0.188
 learn-0.183
 great-0.179
 see-0.179
Token the
Token ID262
Feature activation-2.33e+00

Pos logit contributions
led+1.035
ed+0.885
ied+0.773
awed+0.758
ked+0.757
Neg logit contributions
 pleasure-0.550
 Deal-0.470
 welcome-0.452
 great-0.432
 learn-0.430
Token case
Token ID1339
Feature activation+5.32e-01

Pos logit contributions
led+0.171
ed+0.144
ied+0.123
ked+0.120
awed+0.120
Neg logit contributions
 pleasure-0.118
 Deal-0.105
 welcome-0.101
 learn-0.097
 great-0.096
Token and
Token ID290
Feature activation+3.26e+00

Pos logit contributions
 pleasure+0.021
 welcome+0.019
 learn+0.018
 think+0.017
 Deal+0.017
Neg logit contributions
led-0.042
ed-0.035
ked-0.032
awed-0.031
med-0.031
Token pony
Token ID26902
Feature activation-6.42e+00

Pos logit contributions
led+0.204
ed+0.171
ied+0.145
ked+0.141
awed+0.140
Neg logit contributions
 pleasure-0.160
 Deal-0.144
 welcome-0.137
 learn-0.133
 great-0.131
Token stopped
Token ID5025
Feature activation-5.25e+00

Pos logit contributions
led+0.410
ed+0.327
ied+0.303
ier+0.287
awed+0.285
Neg logit contributions
 pleasure-0.335
 learn-0.315
 think-0.309
 have-0.307
 know-0.307
Token in
Token ID287
Feature activation-1.28e+01

Pos logit contributions
led+0.375
ed+0.309
ied+0.271
awed+0.258
ier+0.255
Neg logit contributions
 pleasure-0.269
 welcome-0.245
 Deal-0.238
 think-0.235
 great-0.231
Token her
Token ID607
Feature activation-3.10e+00

Pos logit contributions
led+0.946
ed+0.824
ied+0.690
ted+0.687
y+0.685
Neg logit contributions
 pleasure-0.582
 Deal-0.511
 learn-0.466
 welcome-0.464
 great-0.456
Token tracks
Token ID8339
Feature activation-2.07e+00

Pos logit contributions
led+0.242
ed+0.207
ied+0.179
awed+0.175
ked+0.175
Neg logit contributions
 pleasure-0.139
 Deal-0.124
 welcome-0.116
 learn-0.111
 great-0.110
Token.
Token ID13
Feature activation-6.56e+00

Pos logit contributions
led+0.152
ed+0.121
awed+0.113
we+0.111
ied+0.109
Neg logit contributions
 pleasure-0.087
 -0.080
 welcome-0.079
 learn-0.072
 be-0.072
Token She
Token ID1375
Feature activation-4.46e+00

Pos logit contributions
led+0.508
ed+0.460
ted+0.389
awed+0.383
med+0.382
Neg logit contributions
 pleasure-0.264
 Deal-0.232
 learn-0.219
 deal-0.219
 great-0.216
Token felt
Token ID2936
Feature activation-2.48e+00

Pos logit contributions
led+0.290
ed+0.240
ied+0.210
ier+0.208
awed+0.199
Neg logit contributions
 pleasure-0.241
 think-0.216
 great-0.214
 learn-0.213
 know-0.211
Token a
Token ID257
Feature activation+2.78e+00

Pos logit contributions
led+0.201
ed+0.172
ied+0.147
ling+0.144
med+0.143
Neg logit contributions
 pleasure-0.101
 Deal-0.095
 deal-0.080
 learn-0.078
 welcome-0.078
Token bit
Token ID1643
Feature activation-6.94e-01

Pos logit contributions
 pleasure+0.136
 Deal+0.127
 welcome+0.117
 learn+0.116
 think+0.109
Neg logit contributions
led-0.198
ed-0.165
ling-0.142
ked-0.138
y-0.138
Token scared
Token ID12008
Feature activation-3.85e+00

Pos logit contributions
led+0.054
ed+0.046
ied+0.041
awed+0.040
ked+0.040
Neg logit contributions
 pleasure-0.031
 welcome-0.027
 Deal-0.027
 great-0.026
 think-0.026
Token He
Token ID679
Feature activation-4.19e+00

Pos logit contributions
led+0.396
ed+0.346
ied+0.278
ked+0.278
ted+0.275
Neg logit contributions
 pleasure-0.312
 Deal-0.272
 welcome-0.257
 great-0.253
 learn-0.252
Token showed
Token ID3751
Feature activation-5.65e+00

Pos logit contributions
led+0.309
ed+0.263
ing+0.241
ied+0.241
ting+0.240
Neg logit contributions
 think-0.170
 pleasure-0.169
 know-0.163
 have-0.162
 learn-0.161
Token her
Token ID607
Feature activation-2.33e+00

Pos logit contributions
led+0.490
ed+0.411
awed+0.380
ked+0.372
ling+0.366
Neg logit contributions
 pleasure-0.198
 welcome-0.166
 great-0.160
 learn-0.158
 Deal-0.152
Token a
Token ID257
Feature activation+3.35e+00

Pos logit contributions
led+0.189
ed+0.160
awed+0.142
ked+0.140
ied+0.139
Neg logit contributions
 pleasure-0.097
 learn-0.081
 welcome-0.081
 great-0.079
 Deal-0.079
Token soft
Token ID2705
Feature activation-1.07e+00

Pos logit contributions
 pleasure+0.163
 Deal+0.149
 welcome+0.133
 learn+0.132
 think+0.129
Neg logit contributions
led-0.236
ed-0.204
ied-0.177
y-0.173
ked-0.168
Token bear
Token ID6842
Feature activation-5.69e+00

Pos logit contributions
led+0.081
ed+0.068
ied+0.059
ked+0.058
awed+0.058
Neg logit contributions
 pleasure-0.052
 Deal-0.046
 welcome-0.044
 learn-0.042
 great-0.042
Token.
Token ID13
Feature activation-5.89e+00

Pos logit contributions
led+0.480
ed+0.372
awed+0.357
ied+0.352
attered+0.334
Neg logit contributions
 learn-0.214
 think-0.196
 have-0.195
 pleasure-0.194
 welcome-0.189
Token He
Token ID679
Feature activation-4.21e+00

Pos logit contributions
led+0.425
ed+0.370
ied+0.306
ked+0.305
ted+0.304
Neg logit contributions
 pleasure-0.290
 Deal-0.254
 welcome-0.237
 great-0.232
 learn-0.232
Token said
Token ID531
Feature activation-1.50e+00

Pos logit contributions
led+0.314
ed+0.268
ied+0.251
ing+0.248
ting+0.247
Neg logit contributions
 think-0.162
 pleasure-0.155
 have-0.154
 know-0.153
 learn-0.153
Token the
Token ID262
Feature activation-1.99e+00

Pos logit contributions
led+0.113
ed+0.095
ied+0.082
awed+0.081
ked+0.080
Neg logit contributions
 pleasure-0.073
 Deal-0.063
 welcome-0.062
 great-0.060
 learn-0.059
Token bear
Token ID6842
Feature activation-5.70e+00

Pos logit contributions
led+0.140
ed+0.118
ied+0.101
ked+0.098
awed+0.097
Neg logit contributions
 pleasure-0.104
 Deal-0.093
 welcome-0.088
 learn-0.086
 great-0.084
Token eat
Token ID4483
Feature activation+6.53e+00

Pos logit contributions
led+0.419
ed+0.352
ted+0.313
ling+0.313
ied+0.312
Neg logit contributions
 pleasure-0.202
 Deal-0.185
 Today-0.134
 welcome-0.133
 great-0.132
Token.
Token ID13
Feature activation-6.57e+00

Pos logit contributions
 pleasure+0.362
 welcome+0.332
 great+0.321
 learn+0.316
 Deal+0.315
Neg logit contributions
led-0.426
ed-0.355
ked-0.304
awed-0.296
ied-0.296
Token
Token ID198
Feature activation+8.57e+00

Pos logit contributions
led+0.582
ed+0.522
awed+0.457
ted+0.454
ied+0.453
Neg logit contributions
 pleasure-0.234
 Deal-0.200
 welcome-0.183
 learn-0.163
 great-0.161
Token
Token ID198
Feature activation+8.56e+00

Pos logit contributions
 pleasure+0.335
 Deal+0.279
 welcome+0.238
 deal+0.234
 learn+0.212
Neg logit contributions
led-0.745
ed-0.659
ied-0.596
awed-0.582
y-0.581
TokenL
Token ID43
Feature activation-7.41e+00

Pos logit contributions
 pleasure+0.396
 Deal+0.345
 welcome+0.329
 learn+0.313
 great+0.310
Neg logit contributions
led-0.668
ed-0.569
ied-0.496
awed-0.482
ked-0.482
Tokenily
Token ID813
Feature activation-1.73e+01

Pos logit contributions
led+0.438
ed+0.354
ked+0.295
ted+0.285
awed+0.283
Neg logit contributions
 pleasure-0.458
 Deal-0.421
 welcome-0.416
 learn-0.400
 great-0.397
Token was
Token ID373
Feature activation-2.27e+00

Pos logit contributions
led+1.192
ed+0.993
ied+0.848
ked+0.825
awed+0.816
Neg logit contributions
 pleasure-0.928
 Deal-0.836
 welcome-0.803
 learn-0.799
 great-0.785
Token happy
Token ID3772
Feature activation+1.03e+01

Pos logit contributions
led+0.171
ed+0.149
awed+0.125
ked+0.125
ied+0.124
Neg logit contributions
 pleasure-0.102
 Deal-0.095
 deal-0.081
 meantime-0.078
 welcome-0.078
Token to
Token ID284
Feature activation-5.20e+00

Pos logit contributions
 pleasure+0.490
 learn+0.423
 welcome+0.422
 think+0.419
 Deal+0.404
Neg logit contributions
led-0.784
ed-0.648
ied-0.574
ked-0.563
awed-0.550
Token learn
Token ID2193
Feature activation+1.36e+01

Pos logit contributions
led+0.418
ed+0.394
red+0.337
ked+0.337
ted+0.331
Neg logit contributions
 pleasure-0.179
 Deal-0.145
 great-0.101
 meantime-0.096
 Sometimes-0.094
Token about
Token ID546
Feature activation-2.75e+00

Pos logit contributions
 pleasure+0.580
 welcome+0.499
 learn+0.490
 Deal+0.485
 great+0.483
Neg logit contributions
led-1.093
ed-0.935
ked-0.816
ied-0.803
awed-0.803
Token loud
Token ID7812
Feature activation+5.48e-01

Pos logit contributions
led+0.131
ed+0.109
awed+0.103
ied+0.101
attered+0.099
Neg logit contributions
 welcome-0.055
 pleasure-0.054
 great-0.054
 Deal-0.050
 learn-0.049
Token.
Token ID13
Feature activation-6.09e+00

Pos logit contributions
 pleasure+0.026
 welcome+0.025
 Deal+0.024
 learn+0.024
 think+0.024
Neg logit contributions
led-0.038
ed-0.030
ied-0.029
awed-0.026
attered-0.026
Token
Token ID198
Feature activation+9.07e+00

Pos logit contributions
led+0.488
ed+0.453
awed+0.381
ted+0.378
med+0.370
Neg logit contributions
 pleasure-0.249
 Deal-0.188
 deal-0.177
 promise-0.173
 learn-0.172
Token
Token ID198
Feature activation+9.08e+00

Pos logit contributions
 pleasure+0.395
 Deal+0.302
 deal+0.293
 welcome+0.264
 meantime+0.262
Neg logit contributions
led-0.707
ed-0.647
ied-0.554
awed-0.549
es-0.540
TokenL
Token ID43
Feature activation-6.88e+00

Pos logit contributions
 pleasure+0.390
 Deal+0.338
 welcome+0.321
 learn+0.306
 great+0.304
Neg logit contributions
led-0.737
ed-0.633
ied-0.554
ked-0.541
awed-0.540
Tokenily
Token ID813
Feature activation-1.68e+01

Pos logit contributions
led+0.437
ed+0.347
ked+0.298
lers+0.291
ted+0.290
Neg logit contributions
 pleasure-0.395
 Deal-0.379
 welcome-0.375
 learn-0.356
 think-0.347
Token is
Token ID318
Feature activation+4.49e+00

Pos logit contributions
led+1.341
ed+1.128
ied+1.035
ked+0.984
ier+0.970
Neg logit contributions
 pleasure-0.668
 Deal-0.628
 learn-0.604
 welcome-0.597
 think-0.585
Token scared
Token ID12008
Feature activation-3.48e+00

Pos logit contributions
 pleasure+0.192
 welcome+0.178
 Deal+0.175
 great+0.169
 learn+0.166
Neg logit contributions
led-0.349
ed-0.298
ied-0.266
ted-0.259
ked-0.256
Token.
Token ID13
Feature activation-6.00e+00

Pos logit contributions
led+0.242
ed+0.199
ied+0.172
ked+0.170
awed+0.168
Neg logit contributions
 pleasure-0.178
 welcome-0.171
 Deal-0.168
 learn-0.160
 think-0.158
Token She
Token ID1375
Feature activation-3.94e+00

Pos logit contributions
led+0.353
ed+0.328
awed+0.254
ted+0.248
y+0.246
Neg logit contributions
 pleasure-0.379
 Deal-0.314
 great-0.307
 deal-0.304
 plan-0.298
Token runs
Token ID4539
Feature activation-5.62e+00

Pos logit contributions
led+0.289
ed+0.243
ied+0.207
ked+0.203
awed+0.203
Neg logit contributions
 pleasure-0.202
 Deal-0.176
 welcome-0.169
 learn-0.161
 great-0.160
Token snow
Token ID6729
Feature activation+1.53e+00

Pos logit contributions
 pleasure+0.064
 Deal+0.060
 welcome+0.053
 learn+0.052
 think+0.050
Neg logit contributions
led-0.104
ed-0.088
y-0.076
ling-0.076
ied-0.075
Tokenman
Token ID805
Feature activation-1.24e+01

Pos logit contributions
 pleasure+0.087
 welcome+0.078
 great+0.076
 deal+0.076
 think+0.075
Neg logit contributions
led-0.094
ed-0.076
ied-0.068
awed-0.066
ked-0.065
Token.
Token ID13
Feature activation-7.26e+00

Pos logit contributions
led+0.883
ed+0.733
ied+0.652
awed+0.636
ked+0.616
Neg logit contributions
 pleasure-0.637
 welcome-0.563
 learn-0.541
 Deal-0.540
 great-0.537
Token<|endoftext|>
Token ID50256
Feature activation+8.81e-01

Pos logit contributions
led+0.465
ed+0.417
y+0.362
ted+0.357
med+0.353
Neg logit contributions
 pleasure-0.337
 great-0.297
 Deal-0.286
 plan-0.283
 deal-0.283
TokenL
Token ID43
Feature activation-7.87e+00

Pos logit contributions
 pleasure+0.034
 Deal+0.029
 learn+0.026
 welcome+0.025
 deal+0.025
Neg logit contributions
led-0.074
ed-0.066
ied-0.056
awed-0.056
y-0.056
Tokenily
Token ID813
Feature activation-1.77e+01

Pos logit contributions
led+0.476
ed+0.386
ied+0.319
ked+0.306
awed+0.306
Neg logit contributions
 pleasure-0.497
 Deal-0.451
 welcome-0.436
 learn-0.423
 great-0.421
Token was
Token ID373
Feature activation-2.53e+00

Pos logit contributions
led+1.289
ed+1.080
ied+0.957
ked+0.945
awed+0.918
Neg logit contributions
 pleasure-0.854
 welcome-0.750
 Deal-0.734
 learn-0.731
 think-0.722
Token a
Token ID257
Feature activation+2.42e+00

Pos logit contributions
led+0.176
ed+0.148
ied+0.125
awed+0.123
ked+0.120
Neg logit contributions
 pleasure-0.134
 Deal-0.120
 deal-0.113
 learn-0.112
 welcome-0.111
Token creative
Token ID7325
Feature activation+2.13e+00

Pos logit contributions
 pleasure+0.100
 Deal+0.087
 welcome+0.079
 learn+0.078
 know+0.074
Neg logit contributions
led-0.195
ed-0.167
y-0.146
ling-0.145
ied-0.144
Token girl
Token ID2576
Feature activation-3.53e+00

Pos logit contributions
 pleasure+0.101
 Deal+0.087
 welcome+0.086
 great+0.082
 learn+0.081
Neg logit contributions
led-0.163
ed-0.139
ied-0.121
awed-0.118
ked-0.118
Token who
Token ID508
Feature activation-2.73e+00

Pos logit contributions
led+0.272
ed+0.227
ied+0.206
ked+0.198
awed+0.197
Neg logit contributions
 pleasure-0.161
 welcome-0.151
 have-0.147
 learn-0.145
 think-0.144
Token loudly
Token ID23112
Feature activation-7.97e+00

Pos logit contributions
led+1.564
ed+1.269
ied+1.177
ier+1.156
awed+1.149
Neg logit contributions
 pleasure-0.880
 great-0.831
 welcome-0.826
 learn-0.791
 try-0.780
Token.
Token ID13
Feature activation-6.07e+00

Pos logit contributions
led+0.586
ied+0.466
ed+0.443
awed+0.431
attered+0.424
Neg logit contributions
 pleasure-0.339
 welcome-0.313
 great-0.299
 learn-0.295
 try-0.293
Token He
Token ID679
Feature activation-4.38e+00

Pos logit contributions
led+0.423
ed+0.375
ked+0.308
ted+0.308
med+0.303
Neg logit contributions
 pleasure-0.307
 Deal-0.264
 welcome-0.253
 learn-0.253
 think-0.248
Token pe
Token ID613
Feature activation-2.87e+00

Pos logit contributions
led+0.290
ed+0.246
ied+0.229
ier+0.220
ing+0.212
Neg logit contributions
 pleasure-0.203
 think-0.200
 great-0.197
 learn-0.192
 have-0.189
Tokenck
Token ID694
Feature activation-5.90e+00

Pos logit contributions
led+0.150
ed+0.133
ly+0.120
attered+0.118
ol+0.117
Neg logit contributions
 think-0.126
 Deal-0.124
 guess-0.121
 pleasure-0.120
 know-0.118
Tokened
Token ID276
Feature activation-2.07e+01

Pos logit contributions
led+0.094
web+0.085
attered+0.074
rying+0.074
year+0.073
Neg logit contributions
 great-0.437
 see-0.424
 have-0.419
 be-0.418
 try-0.418
Token at
Token ID379
Feature activation-7.90e+00

Pos logit contributions
led+1.523
ed+1.216
ied+1.195
ier+1.179
awed+1.126
Neg logit contributions
 pleasure-0.884
 great-0.798
 welcome-0.773
 think-0.735
 Deal-0.729
Token their
Token ID511
Feature activation+8.16e-03

Pos logit contributions
led+0.600
ed+0.512
ied+0.443
ked+0.435
ted+0.434
Neg logit contributions
 pleasure-0.379
 Deal-0.330
 welcome-0.309
 learn-0.298
 great-0.292
Token shoes
Token ID10012
Feature activation+2.36e+00

Pos logit contributions
 pleasure+0.000
 Deal+0.000
 welcome+0.000
 learn+0.000
 great+0.000
Neg logit contributions
led-0.001
ed-0.000
ied-0.000
ked-0.000
awed-0.000
Token and
Token ID290
Feature activation+3.32e+00

Pos logit contributions
 pleasure+0.082
 learn+0.076
 think+0.072
 welcome+0.072
 have+0.071
Neg logit contributions
led-0.197
ed-0.163
ied-0.147
awed-0.144
we-0.140
Token legs
Token ID7405
Feature activation-4.98e-02

Pos logit contributions
 pleasure+0.155
 think+0.148
 learn+0.144
 be+0.144
 great+0.143
Neg logit contributions
led-0.220
ed-0.183
ied-0.178
ier-0.172
ing-0.162
Token it
Token ID340
Feature activation+5.00e+00

Pos logit contributions
led+0.236
ed+0.204
ied+0.180
ked+0.176
awed+0.176
Neg logit contributions
 pleasure-0.108
 Deal-0.092
 welcome-0.087
 learn-0.083
 great-0.082
Token."
Token ID526
Feature activation+1.81e+00

Pos logit contributions
 pleasure+0.250
 welcome+0.218
 Deal+0.215
 great+0.209
 learn+0.205
Neg logit contributions
led-0.363
ed-0.303
ied-0.265
ked-0.265
awed-0.264
Token
Token ID198
Feature activation+8.74e+00

Pos logit contributions
 pleasure+0.055
 Deal+0.045
 great+0.040
 welcome+0.038
 deal+0.036
Neg logit contributions
led-0.165
ed-0.148
ted-0.129
awed-0.129
ied-0.128
Token
Token ID198
Feature activation+8.77e+00

Pos logit contributions
 pleasure+0.318
 Deal+0.258
 great+0.222
 deal+0.222
 welcome+0.221
Neg logit contributions
led-0.749
ed-0.659
ied-0.595
awed-0.583
med-0.575
TokenL
Token ID43
Feature activation-7.17e+00

Pos logit contributions
 pleasure+0.453
 Deal+0.388
 welcome+0.365
 great+0.353
 deal+0.345
Neg logit contributions
led-0.621
ed-0.527
ied-0.464
med-0.449
awed-0.449
Tokenily
Token ID813
Feature activation-1.71e+01

Pos logit contributions
led+0.437
ed+0.349
ked+0.291
ted+0.282
awed+0.282
Neg logit contributions
 pleasure-0.445
 Deal-0.414
 welcome-0.407
 learn-0.391
 think-0.384
Token felt
Token ID2936
Feature activation-2.29e+00

Pos logit contributions
led+1.119
ed+0.913
ied+0.789
ked+0.766
awed+0.754
Neg logit contributions
 pleasure-0.963
 Deal-0.863
 welcome-0.850
 learn-0.849
 think-0.834
Token happy
Token ID3772
Feature activation+1.07e+01

Pos logit contributions
led+0.195
ed+0.169
ied+0.144
ling+0.142
ier+0.140
Neg logit contributions
 pleasure-0.086
 Deal-0.078
 deal-0.064
 welcome-0.063
 learn-0.062
Token that
Token ID326
Feature activation-1.35e+00

Pos logit contributions
 pleasure+0.560
 Deal+0.488
 welcome+0.479
 learn+0.464
 great+0.457
Neg logit contributions
led-0.769
ed-0.643
ied-0.555
ked-0.540
awed-0.536
Token she
Token ID673
Feature activation-4.90e+00

Pos logit contributions
led+0.083
ed+0.070
ied+0.058
y+0.054
ted+0.053
Neg logit contributions
 pleasure-0.082
 Deal-0.076
 welcome-0.070
 great-0.068
 learn-0.067
Token was
Token ID373
Feature activation-1.88e+00

Pos logit contributions
led+0.315
ied+0.252
ed+0.247
ked+0.234
awed+0.234
Neg logit contributions
 pleasure-0.248
 have-0.233
 welcome-0.230
 think-0.229
 see-0.225