TOP ACTIVATIONS
MAX = 1.153

an image falsely suggesting Kurt Cob ain had predicted Donald Trump
12 , 000 App rox imate number of adult Buddh
Wise ( SN ES , 1995 )
you of multiple incidence ( sic ) that occurred between Heather
where they are coun se lled by its rulers , Gal
performances .[ 13 ]: 177 Cob ain would describe his lyrics
asks Stephen , examining a peac ock 's tail feathers in
M itch has exce lled through his final stages of
[ 13 ]: 182 While Cob ain insisted on the subject
his songs .[ 36 ] Cob ain complained when fans and
which player out - per forms the other . Norman must
for both Square and SN ES sound tracks , and although
ST OF - Penn J illet - Fill The Ball on
35 ) Per form 2 aerial gestures before touching
re i Profile Blog Joined October 2002 United States 3
pur ak ushi Profile Joined August 2012 United States 3
and a bit of Paul Newman about him '. Photograph :
memories , old photos , etc .? Want to write a
13 ]: 168 169 Cob ain said in an interview
and a bit of Paul Newman about him . Coll ing

MIN ACTIVATIONS
MIN = -0.996

for all those programmers cr anking out the overhaul ed Firefox
, including headset , cr anks and brakes . The wheels
by clicking the box . Invalid email address . Please re
easily closed up with finger stock , b raid , or
to the report from Xin hua . The code
by clicking the box . Invalid email address . Please re
H enson 's post hum ous induction as a Disney Legend
said he ' could have slug ged ' Carter over this
, someone let a gir affe out of the Louisville zoo
is as American as apple pie . Nearly two
While in a " worthiness " interview , my bishop
Louisiana and talk to [ Louis ian ians ], they
. Future Hall of Fame slug ger Stan Mus ial ,
that he would like the embassy moved to Jerusalem , but
acing in reverse the crossing route of another celebrated inv ader
and other messages via Mi iverse . There are
lack character ? What about PK Sub ban ? ( Actually
isn 't that they should wel sh at putting you on
: " Trans sexual " refers to a more specific transgender
by clicking the box . Invalid email address . Please re

INTERVAL 0.616 - 1.153
CONTAINS 0.069%

himself . Coming back to Tal ul ah , he 's
<|endoftext|> Abstract Background Depression presents a significant burden to
kept relatively quiet in the meantime , because my instinct ,
in construction or manufacturing , etc . As we
Y alk ut Tal mud Torah ,

INTERVAL 0.079 - 0.616
CONTAINS 23.013%

Barack Obama , they in ­ v oke him .
always be the price of inflation ." He correctly predicted the
The integrated Lean Six Sigma management approach is being used across
s R haps ody In Blue
reserves its toughest penalties for those who " def raud or

INTERVAL -0.458 - 0.079
CONTAINS 76.373%

. Her body was still strong enough to fight the illness
lawyers in the Ecuador ian capital Qu ito to fight his
what usually happens at an event filled with Tor ont on
As with many things Trump , talk of his competence looks
been encouraging . Sy fy s return

INTERVAL -0.996 - -0.458
CONTAINS 0.545%

generation 3 . 5 - liter Eco Boost proved its met
the same with a Trap Card ! The best part is
what seem to be real disagreements in judgments about the performances
at all . Ichigo s next sentence
, too : These " lab yrinth ine worlds filled with
Token an
Token ID281
Feature activation+1.24e-01

Pos logit contributions
++)+0.054
ound+0.053
show+0.050
amara+0.049
 Stanley+0.049
Neg logit contributions
 Electricity-0.050
Shipping-0.048
Initialized-0.048
-0.047
Electric-0.047
Token image
Token ID2939
Feature activation+1.70e-01

Pos logit contributions
++)+0.204
ound+0.200
show+0.188
 Stanley+0.188
amara+0.186
Neg logit contributions
 Electricity-0.223
Shipping-0.219
Initialized-0.219
-0.215
Electric-0.214
Token falsely
Token ID24566
Feature activation-2.14e-01

Pos logit contributions
++)+0.306
ound+0.300
show+0.284
 Stanley+0.282
amara+0.281
Neg logit contributions
 Electricity-0.280
Initialized-0.273
Shipping-0.273
-0.269
Electric-0.267
Token suggesting
Token ID9524
Feature activation-1.04e-01

Pos logit contributions
 Electricity+0.354
Initialized+0.346
Shipping+0.346
+0.339
Electric+0.337
Neg logit contributions
++)-0.384
ound-0.376
show-0.355
 Stanley-0.353
amara-0.353
Token Kurt
Token ID20642
Feature activation-4.08e-01

Pos logit contributions
 Electricity+0.152
Initialized+0.148
Shipping+0.148
+0.144
Electric+0.144
Neg logit contributions
++)-0.206
ound-0.202
show-0.192
amara-0.191
 Stanley-0.190
Token Cob
Token ID14828
Feature activation+1.15e+00

Pos logit contributions
 Electricity+0.677
Shipping+0.655
Initialized+0.651
+0.651
_-_+0.641
Neg logit contributions
++)-0.716
ound-0.712
okia-0.668
amara-0.666
show-0.666
Tokenain
Token ID391
Feature activation-3.08e-01

Pos logit contributions
++)+1.641
ound+1.629
show+1.496
ourke+1.490
score+1.484
Neg logit contributions
 Electricity-2.364
Initialized-2.312
Shipping-2.308
-2.266
Electric-2.237
Token had
Token ID550
Feature activation+8.38e-02

Pos logit contributions
 Electricity+0.484
Shipping+0.470
Initialized+0.469
+0.462
Electric+0.459
Neg logit contributions
++)-0.577
ound-0.568
show-0.538
amara-0.536
 Stanley-0.533
Token predicted
Token ID11001
Feature activation-1.83e-01

Pos logit contributions
++)+0.147
ound+0.144
show+0.136
amara+0.135
 Stanley+0.134
Neg logit contributions
 Electricity-0.143
Initialized-0.139
Shipping-0.139
-0.137
Electric-0.136
Token Donald
Token ID3759
Feature activation+1.59e-03

Pos logit contributions
 Electricity+0.298
Shipping+0.289
Initialized+0.289
Electric+0.282
+0.282
Neg logit contributions
++)-0.337
ound-0.329
show-0.312
amara-0.311
ady-0.309
Token Trump
Token ID1301
Feature activation-8.59e-02

Pos logit contributions
++)+0.003
ound+0.003
show+0.003
amara+0.003
ady+0.003
Neg logit contributions
 Electricity-0.003
Initialized-0.002
Shipping-0.002
-0.002
Electric-0.002
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
++)+0.045
ound+0.044
show+0.042
amara+0.042
 Stanley+0.042
Neg logit contributions
 Electricity-0.043
Initialized-0.042
Shipping-0.042
-0.041
Electric-0.041
Token12
Token ID1065
Feature activation+1.88e-01

Pos logit contributions
++)+0.050
ound+0.049
show+0.047
 Stanley+0.047
amara+0.047
Neg logit contributions
 Electricity-0.038
Shipping-0.037
Initialized-0.037
-0.037
Electric-0.037
Token,
Token ID11
Feature activation+1.09e-02

Pos logit contributions
++)+0.328
ound+0.322
show+0.304
 Stanley+0.302
amara+0.301
Neg logit contributions
 Electricity-0.320
Shipping-0.312
Initialized-0.312
-0.307
Electric-0.305
Token000
Token ID830
Feature activation-2.79e-02

Pos logit contributions
++)+0.022
ound+0.022
show+0.021
 Stanley+0.021
amara+0.021
Neg logit contributions
 Electricity-0.015
Initialized-0.015
Shipping-0.015
-0.014
Electric-0.014
Token App
Token ID2034
Feature activation+4.31e-02

Pos logit contributions
 Electricity+0.049
Initialized+0.047
Shipping+0.047
+0.047
Electric+0.046
Neg logit contributions
++)-0.048
ound-0.046
show-0.044
amara-0.044
ady-0.044
Tokenrox
Token ID13907
Feature activation+9.98e-01

Pos logit contributions
++)+0.068
ound+0.066
show+0.063
 Stanley+0.062
amara+0.062
Neg logit contributions
 Electricity-0.080
Shipping-0.078
Initialized-0.078
-0.077
Electric-0.077
Tokenimate
Token ID1920
Feature activation+2.52e-01

Pos logit contributions
++)+1.448
ound+1.422
 Stanley+1.322
show+1.317
amara+1.305
Neg logit contributions
 Electricity-1.983
Initialized-1.952
Shipping-1.949
-1.927
Electric-1.911
Token number
Token ID1271
Feature activation+1.44e-01

Pos logit contributions
++)+0.414
ound+0.405
show+0.381
amara+0.378
 Stanley+0.378
Neg logit contributions
 Electricity-0.457
Shipping-0.446
Initialized-0.446
-0.438
Electric-0.437
Token of
Token ID286
Feature activation+1.16e-01

Pos logit contributions
++)+0.250
ound+0.245
show+0.230
amara+0.230
ady+0.229
Neg logit contributions
 Electricity-0.248
Shipping-0.240
Initialized-0.240
-0.236
Electric-0.235
Token adult
Token ID4044
Feature activation+3.70e-02

Pos logit contributions
++)+0.190
ound+0.186
show+0.175
 Stanley+0.174
amara+0.173
Neg logit contributions
 Electricity-0.211
Initialized-0.207
Shipping-0.207
-0.203
Electric-0.202
Token Buddh
Token ID20921
Feature activation-2.71e-01

Pos logit contributions
++)+0.058
ound+0.057
show+0.053
 Stanley+0.053
amara+0.053
Neg logit contributions
 Electricity-0.069
Initialized-0.068
Shipping-0.068
-0.067
Electric-0.066
Token Wise
Token ID28908
Feature activation-1.17e-02

Pos logit contributions
++)+0.192
ound+0.188
show+0.177
amara+0.176
 Stanley+0.176
Neg logit contributions
 Electricity-0.193
Initialized-0.188
Shipping-0.188
-0.185
Electric-0.184
Token
Token ID198
Feature activation-2.60e-03

Pos logit contributions
 Electricity+0.019
Shipping+0.019
Initialized+0.018
+0.018
Electric+0.018
Neg logit contributions
++)-0.021
ound-0.021
amara-0.020
show-0.020
 Stanley-0.019
Token
Token ID198
Feature activation+4.08e-04

Pos logit contributions
 Electricity+0.004
Initialized+0.004
Shipping+0.004
+0.004
Electric+0.004
Neg logit contributions
++)-0.005
ound-0.005
amara-0.004
show-0.004
 Stanley-0.004
Token(
Token ID7
Feature activation-1.30e-01

Pos logit contributions
++)+0.001
ound+0.001
 Stanley+0.001
amara+0.001
show+0.001
Neg logit contributions
 Electricity-0.001
Shipping-0.001
Initialized-0.001
-0.001
Electric-0.001
TokenSN
Token ID15571
Feature activation-1.40e-01

Pos logit contributions
 Electricity+0.206
Shipping+0.202
Initialized+0.201
+0.198
Electric+0.197
Neg logit contributions
++)-0.242
ound-0.238
amara-0.225
show-0.225
 Stanley-0.225
TokenES
Token ID1546
Feature activation+9.68e-01

Pos logit contributions
 Electricity+0.246
Initialized+0.241
Shipping+0.240
+0.237
Electric+0.236
Neg logit contributions
++)-0.234
ound-0.230
show-0.217
ady-0.216
 Stanley-0.215
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
++)+1.552
ound+1.518
show+1.426
 Stanley+1.419
amara+1.412
Neg logit contributions
 Electricity-1.786
Initialized-1.748
Shipping-1.748
-1.720
Electric-1.710
Token 1995
Token ID8735
Feature activation+7.45e-02

Pos logit contributions
++)+0.184
ound+0.181
show+0.171
 Stanley+0.171
amara+0.169
Neg logit contributions
 Electricity-0.176
Shipping-0.172
Initialized-0.172
-0.169
Electric-0.168
Token)
Token ID8
Feature activation+9.29e-02

Pos logit contributions
++)+0.070
ound+0.069
amara+0.062
ady+0.062
show+0.061
Neg logit contributions
 Electricity-0.185
Shipping-0.182
Initialized-0.181
-0.181
Electric-0.179
Token
Token ID198
Feature activation+2.18e-03

Pos logit contributions
++)+0.165
ound+0.162
show+0.153
amara+0.152
 Stanley+0.152
Neg logit contributions
 Electricity-0.156
Shipping-0.152
Initialized-0.152
-0.149
Electric-0.148
Token
Token ID198
Feature activation+1.17e-02

Pos logit contributions
++)+0.004
ound+0.004
amara+0.004
show+0.004
 Stanley+0.004
Neg logit contributions
 Electricity-0.004
Initialized-0.004
Shipping-0.004
-0.003
Electric-0.003
Token you
Token ID345
Feature activation+1.45e-01

Pos logit contributions
 Electricity+0.001
Shipping+0.001
Initialized+0.001
+0.001
Electric+0.001
Neg logit contributions
++)-0.001
ound-0.001
show-0.001
amara-0.001
 Stanley-0.001
Token of
Token ID286
Feature activation+2.48e-02

Pos logit contributions
++)+0.301
ound+0.297
show+0.283
 Stanley+0.282
amara+0.281
Neg logit contributions
 Electricity-0.199
Initialized-0.194
Shipping-0.193
-0.189
Electric-0.188
Token multiple
Token ID3294
Feature activation-4.61e-02

Pos logit contributions
++)+0.045
ound+0.044
show+0.042
amara+0.042
 Stanley+0.042
Neg logit contributions
 Electricity-0.040
Shipping-0.039
Initialized-0.039
-0.038
Electric-0.038
Token incidence
Token ID18349
Feature activation+1.22e-01

Pos logit contributions
 Electricity+0.076
Shipping+0.074
Initialized+0.074
+0.073
Electric+0.072
Neg logit contributions
++)-0.083
ound-0.081
show-0.077
amara-0.076
 Stanley-0.076
Token(
Token ID7
Feature activation-3.54e-02

Pos logit contributions
++)+0.215
ound+0.211
show+0.199
 Stanley+0.198
amara+0.198
Neg logit contributions
 Electricity-0.207
Shipping-0.202
Initialized-0.202
-0.199
Electric-0.197
Tokensic
Token ID21383
Feature activation+9.62e-01

Pos logit contributions
 Electricity+0.063
Shipping+0.062
Initialized+0.062
+0.061
Electric+0.060
Neg logit contributions
++)-0.059
ound-0.058
 Stanley-0.054
show-0.054
amara-0.054
Token)
Token ID8
Feature activation+4.68e-03

Pos logit contributions
++)+0.848
ound+0.816
show+0.723
 Stanley+0.716
amara+0.710
Neg logit contributions
 Electricity-2.470
Initialized-2.431
Shipping-2.431
-2.404
Electric-2.394
Token that
Token ID326
Feature activation+2.67e-02

Pos logit contributions
++)+0.008
ound+0.008
show+0.008
amara+0.008
 Stanley+0.008
Neg logit contributions
 Electricity-0.008
Shipping-0.008
Initialized-0.008
-0.007
Electric-0.007
Token occurred
Token ID5091
Feature activation+1.83e-01

Pos logit contributions
++)+0.048
ound+0.047
show+0.044
amara+0.044
 Stanley+0.044
Neg logit contributions
 Electricity-0.044
Shipping-0.043
Initialized-0.043
-0.042
Electric-0.042
Token between
Token ID1022
Feature activation+6.98e-02

Pos logit contributions
++)+0.347
ound+0.341
show+0.323
 Stanley+0.322
amara+0.321
Neg logit contributions
 Electricity-0.284
Initialized-0.277
Shipping-0.277
-0.272
Electric-0.270
Token Heather
Token ID24253
Feature activation+5.28e-01

Pos logit contributions
++)+0.129
ound+0.127
show+0.120
amara+0.119
 Stanley+0.119
Neg logit contributions
 Electricity-0.112
Shipping-0.109
Initialized-0.109
-0.107
Electric-0.106
Token where
Token ID810
Feature activation-5.36e-02

Pos logit contributions
 Electricity+0.023
Initialized+0.023
Shipping+0.023
+0.022
Electric+0.022
Neg logit contributions
++)-0.033
ound-0.032
show-0.031
 Stanley-0.031
amara-0.030
Token they
Token ID484
Feature activation+3.04e-03

Pos logit contributions
 Electricity+0.079
Initialized+0.076
Shipping+0.076
+0.074
Electric+0.074
Neg logit contributions
++)-0.107
ound-0.105
show-0.099
amara-0.098
ady-0.098
Token are
Token ID389
Feature activation-9.51e-02

Pos logit contributions
++)+0.005
ound+0.005
show+0.005
 Stanley+0.005
amara+0.005
Neg logit contributions
 Electricity-0.005
Shipping-0.005
Initialized-0.005
-0.005
Electric-0.005
Token coun
Token ID2289
Feature activation+1.37e-01

Pos logit contributions
 Electricity+0.153
Initialized+0.150
Shipping+0.149
+0.147
Electric+0.146
Neg logit contributions
++)-0.175
ound-0.172
show-0.163
 Stanley-0.162
amara-0.161
Tokense
Token ID325
Feature activation-1.55e-01

Pos logit contributions
++)+0.172
ound+0.167
show+0.154
 Stanley+0.154
amara+0.153
Neg logit contributions
 Electricity-0.300
Initialized-0.294
Shipping-0.294
-0.291
Electric-0.289
Tokenlled
Token ID3353
Feature activation+9.24e-01

Pos logit contributions
 Electricity+0.215
Initialized+0.209
Shipping+0.209
+0.205
Electric+0.203
Neg logit contributions
++)-0.320
ound-0.314
show-0.300
 Stanley-0.298
amara-0.297
Token by
Token ID416
Feature activation+8.73e-02

Pos logit contributions
++)+1.538
ound+1.513
 Stanley+1.433
show+1.431
ady+1.422
Neg logit contributions
 Electricity-1.639
Initialized-1.610
Shipping-1.597
Electric-1.573
-1.567
Token its
Token ID663
Feature activation-9.85e-03

Pos logit contributions
++)+0.159
ound+0.156
show+0.148
amara+0.146
ady+0.146
Neg logit contributions
 Electricity-0.143
Initialized-0.139
Shipping-0.138
-0.136
Electric-0.135
Token rulers
Token ID24925
Feature activation+2.01e-01

Pos logit contributions
 Electricity+0.017
Shipping+0.017
Initialized+0.017
+0.017
Electric+0.017
Neg logit contributions
++)-0.017
ound-0.016
show-0.015
 Stanley-0.015
amara-0.015
Token,
Token ID11
Feature activation+6.56e-02

Pos logit contributions
++)+0.371
ound+0.366
show+0.346
 Stanley+0.346
amara+0.343
Neg logit contributions
 Electricity-0.321
Initialized-0.315
Shipping-0.314
-0.308
Electric-0.307
Token Gal
Token ID5027
Feature activation+1.40e-01

Pos logit contributions
++)+0.120
ound+0.117
show+0.111
 Stanley+0.111
amara+0.110
Neg logit contributions
 Electricity-0.107
Initialized-0.104
Shipping-0.104
-0.102
Electric-0.102
Token performances
Token ID13289
Feature activation+1.67e-01

Pos logit contributions
++)+0.027
ound+0.027
amara+0.025
show+0.025
ady+0.025
Neg logit contributions
 Electricity-0.025
Initialized-0.024
Shipping-0.024
-0.024
Electric-0.024
Token.[
Token ID3693
Feature activation+6.72e-02

Pos logit contributions
++)+0.318
ound+0.312
show+0.296
 Stanley+0.295
amara+0.294
Neg logit contributions
 Electricity-0.257
Shipping-0.250
Initialized-0.250
-0.245
Electric-0.243
Token13
Token ID1485
Feature activation+2.24e-01

Pos logit contributions
++)+0.129
ound+0.127
show+0.120
 Stanley+0.120
amara+0.120
Neg logit contributions
 Electricity-0.103
Shipping-0.100
Initialized-0.100
-0.098
Electric-0.098
Token]:
Token ID5974
Feature activation+1.36e-01

Pos logit contributions
++)+0.444
ound+0.436
show+0.415
 Stanley+0.413
amara+0.412
Neg logit contributions
 Electricity-0.329
Shipping-0.320
Initialized-0.319
-0.314
Electric-0.311
Token177
Token ID22413
Feature activation+1.83e-01

Pos logit contributions
++)+0.262
ound+0.257
show+0.244
 Stanley+0.243
amara+0.242
Neg logit contributions
 Electricity-0.207
Initialized-0.202
Shipping-0.201
-0.198
Electric-0.196
Token Cob
Token ID14828
Feature activation+9.21e-01

Pos logit contributions
++)+0.347
ound+0.341
show+0.323
amara+0.322
ady+0.321
Neg logit contributions
 Electricity-0.286
Shipping-0.277
Initialized-0.277
-0.272
Electric-0.270
Tokenain
Token ID391
Feature activation-2.21e-01

Pos logit contributions
++)+1.419
ound+1.391
show+1.302
 Stanley+1.292
amara+1.287
Neg logit contributions
 Electricity-1.760
Initialized-1.724
Shipping-1.723
-1.697
Electric-1.687
Token would
Token ID561
Feature activation-1.56e-01

Pos logit contributions
 Electricity+0.354
Shipping+0.344
Initialized+0.344
+0.339
Electric+0.335
Neg logit contributions
++)-0.407
ound-0.400
show-0.379
amara-0.376
 Stanley-0.375
Token describe
Token ID6901
Feature activation+1.43e-01

Pos logit contributions
 Electricity+0.269
Shipping+0.262
Initialized+0.262
+0.258
Electric+0.256
Neg logit contributions
++)-0.269
ound-0.264
show-0.249
 Stanley-0.248
amara-0.248
Token his
Token ID465
Feature activation+2.97e-02

Pos logit contributions
++)+0.262
ound+0.257
amara+0.243
show+0.243
ady+0.241
Neg logit contributions
 Electricity-0.232
Initialized-0.225
Shipping-0.225
-0.222
Electric-0.220
Token lyrics
Token ID15844
Feature activation-2.00e-01

Pos logit contributions
++)+0.050
ound+0.049
amara+0.047
show+0.047
ady+0.046
Neg logit contributions
 Electricity-0.052
Initialized-0.050
Shipping-0.050
-0.050
Electric-0.049
Token asks
Token ID7893
Feature activation-8.90e-02

Pos logit contributions
++)+0.011
ound+0.011
show+0.011
amara+0.010
ady+0.010
Neg logit contributions
 Electricity-0.010
Shipping-0.010
Initialized-0.010
-0.010
Electric-0.010
Token Stephen
Token ID7970
Feature activation-2.27e-01

Pos logit contributions
 Electricity+0.149
Initialized+0.144
Shipping+0.143
+0.141
Electric+0.140
Neg logit contributions
++)-0.159
ound-0.156
amara-0.147
show-0.147
cum-0.145
Token,
Token ID11
Feature activation+3.12e-02

Pos logit contributions
 Electricity+0.360
Shipping+0.349
Initialized+0.346
+0.344
Electric+0.340
Neg logit contributions
++)-0.424
ound-0.417
show-0.393
amara-0.391
okia-0.388
Token examining
Token ID17247
Feature activation+1.10e-01

Pos logit contributions
++)+0.057
ound+0.056
show+0.053
amara+0.052
 Stanley+0.052
Neg logit contributions
 Electricity-0.051
Shipping-0.050
Initialized-0.050
-0.049
Electric-0.048
Token a
Token ID257
Feature activation+1.02e-01

Pos logit contributions
++)+0.196
ound+0.192
show+0.182
amara+0.181
 Stanley+0.179
Neg logit contributions
 Electricity-0.184
Shipping-0.179
Initialized-0.179
-0.175
Electric-0.174
Token peac
Token ID41961
Feature activation+9.10e-01

Pos logit contributions
++)+0.174
ound+0.170
show+0.161
amara+0.160
 Stanley+0.159
Neg logit contributions
 Electricity-0.177
Initialized-0.174
Shipping-0.173
-0.170
Electric-0.169
Tokenock
Token ID735
Feature activation-2.90e-01

Pos logit contributions
++)+1.519
ound+1.498
show+1.405
amara+1.395
ady+1.395
Neg logit contributions
 Electricity-1.620
Initialized-1.587
Shipping-1.581
-1.564
Electric-1.547
Token's
Token ID338
Feature activation+5.54e-02

Pos logit contributions
 Electricity+0.462
Shipping+0.452
Initialized+0.449
Electric+0.438
+0.438
Neg logit contributions
++)-0.536
ound-0.525
show-0.496
amara-0.495
 Stanley-0.492
Token tail
Token ID7894
Feature activation-7.95e-02

Pos logit contributions
++)+0.094
ound+0.092
show+0.087
amara+0.087
ady+0.086
Neg logit contributions
 Electricity-0.097
Initialized-0.094
Shipping-0.094
-0.092
Electric-0.092
Token feathers
Token ID27400
Feature activation+3.10e-01

Pos logit contributions
 Electricity+0.126
Shipping+0.123
Initialized+0.122
+0.120
Electric+0.119
Neg logit contributions
++)-0.148
ound-0.146
show-0.138
 Stanley-0.137
amara-0.137
Token in
Token ID287
Feature activation+4.74e-02

Pos logit contributions
++)+0.580
ound+0.569
show+0.540
 Stanley+0.537
amara+0.535
Neg logit contributions
 Electricity-0.489
Shipping-0.477
Initialized-0.477
-0.468
Electric-0.465
Token
Token ID250
Feature activation+1.50e-02

Pos logit contributions
++)+0.163
ound+0.160
show+0.152
 Stanley+0.151
amara+0.151
Neg logit contributions
 Electricity-0.130
Shipping-0.127
Initialized-0.127
-0.124
Electric-0.123
TokenM
Token ID44
Feature activation+2.62e-03

Pos logit contributions
++)+0.030
ound+0.029
show+0.028
 Stanley+0.028
amara+0.028
Neg logit contributions
 Electricity-0.022
Shipping-0.021
Initialized-0.021
-0.021
Electric-0.021
Tokenitch
Token ID2007
Feature activation+7.95e-02

Pos logit contributions
++)+0.005
ound+0.005
show+0.005
 Stanley+0.005
amara+0.005
Neg logit contributions
 Electricity-0.004
Shipping-0.004
Initialized-0.004
-0.004
Electric-0.004
Token has
Token ID468
Feature activation+3.03e-03

Pos logit contributions
++)+0.149
ound+0.147
show+0.139
 Stanley+0.139
amara+0.138
Neg logit contributions
 Electricity-0.125
Initialized-0.122
Shipping-0.121
-0.119
Electric-0.119
Token exce
Token ID43748
Feature activation-3.11e-01

Pos logit contributions
++)+0.005
ound+0.005
show+0.005
amara+0.005
 Stanley+0.005
Neg logit contributions
 Electricity-0.005
Shipping-0.005
Initialized-0.005
-0.005
Electric-0.005
Tokenlled
Token ID3353
Feature activation+9.08e-01

Pos logit contributions
 Electricity+0.431
Initialized+0.419
Shipping+0.418
+0.410
Electric+0.407
Neg logit contributions
++)-0.643
ound-0.631
show-0.602
 Stanley-0.601
amara-0.598
Token through
Token ID832
Feature activation-1.02e-01

Pos logit contributions
++)+1.664
ound+1.637
 Stanley+1.557
show+1.553
amara+1.542
Neg logit contributions
 Electricity-1.458
Initialized-1.428
Shipping-1.422
-1.393
Electric-1.393
Token his
Token ID465
Feature activation+5.99e-03

Pos logit contributions
 Electricity+0.171
Shipping+0.165
Initialized+0.165
+0.163
Electric+0.162
Neg logit contributions
++)-0.183
ound-0.178
show-0.169
amara-0.168
 Stanley-0.167
Token final
Token ID2457
Feature activation+1.06e-01

Pos logit contributions
++)+0.010
ound+0.010
show+0.010
amara+0.010
 Stanley+0.009
Neg logit contributions
 Electricity-0.010
Initialized-0.010
Shipping-0.010
-0.010
Electric-0.010
Token stages
Token ID9539
Feature activation-5.87e-02

Pos logit contributions
++)+0.181
ound+0.177
show+0.167
amara+0.166
 Stanley+0.165
Neg logit contributions
 Electricity-0.186
Shipping-0.181
Initialized-0.181
-0.179
Electric-0.177
Token of
Token ID286
Feature activation+1.77e-02

Pos logit contributions
 Electricity+0.099
Shipping+0.096
Initialized+0.096
+0.095
Electric+0.094
Neg logit contributions
++)-0.104
ound-0.102
show-0.096
amara-0.095
 Stanley-0.095
Token [
Token ID685
Feature activation+1.17e-01

Pos logit contributions
++)+0.118
ound+0.115
show+0.109
amara+0.108
ady+0.108
Neg logit contributions
 Electricity-0.109
Shipping-0.106
Initialized-0.106
-0.104
Electric-0.104
Token13
Token ID1485
Feature activation+2.23e-01

Pos logit contributions
++)+0.229
ound+0.225
 Stanley+0.213
amara+0.213
show+0.213
Neg logit contributions
 Electricity-0.175
Shipping-0.172
Initialized-0.170
-0.168
Electric-0.166
Token]:
Token ID5974
Feature activation+1.18e-01

Pos logit contributions
++)+0.271
ound+0.263
show+0.241
amara+0.239
 Stanley+0.239
Neg logit contributions
 Electricity-0.498
Shipping-0.489
Initialized-0.488
-0.483
Electric-0.481
Token182
Token ID24294
Feature activation+1.94e-01

Pos logit contributions
++)+0.226
ound+0.222
show+0.210
 Stanley+0.209
amara+0.209
Neg logit contributions
 Electricity-0.182
Initialized-0.177
Shipping-0.177
-0.174
Electric-0.172
Token While
Token ID2893
Feature activation+1.43e-02

Pos logit contributions
++)+0.353
ound+0.347
show+0.328
 Stanley+0.326
amara+0.325
Neg logit contributions
 Electricity-0.317
Initialized-0.309
Shipping-0.309
-0.304
Electric-0.302
Token Cob
Token ID14828
Feature activation+8.81e-01

Pos logit contributions
++)+0.026
ound+0.026
show+0.024
amara+0.024
ady+0.024
Neg logit contributions
 Electricity-0.023
Shipping-0.022
Initialized-0.022
-0.022
Electric-0.022
Tokenain
Token ID391
Feature activation-1.90e-01

Pos logit contributions
++)+1.346
ound+1.325
show+1.239
 Stanley+1.225
ady+1.223
Neg logit contributions
 Electricity-1.698
Initialized-1.663
Shipping-1.661
-1.636
Electric-1.627
Token insisted
Token ID11189
Feature activation+2.82e-02

Pos logit contributions
 Electricity+0.308
Shipping+0.299
Initialized+0.299
+0.295
Electric+0.291
Neg logit contributions
++)-0.348
ound-0.342
show-0.324
amara-0.321
 Stanley-0.321
Token on
Token ID319
Feature activation-1.04e-01

Pos logit contributions
++)+0.059
ound+0.058
show+0.055
amara+0.055
 Stanley+0.055
Neg logit contributions
 Electricity-0.038
Shipping-0.037
Initialized-0.037
-0.037
Electric-0.036
Token the
Token ID262
Feature activation-7.22e-02

Pos logit contributions
 Electricity+0.165
Initialized+0.160
Shipping+0.160
+0.158
Electric+0.156
Neg logit contributions
++)-0.193
ound-0.189
show-0.179
amara-0.178
 Stanley-0.178
Token subject
Token ID2426
Feature activation+2.87e-01

Pos logit contributions
 Electricity+0.131
Initialized+0.128
Shipping+0.128
+0.127
Electric+0.125
Neg logit contributions
++)-0.118
ound-0.115
show-0.108
amara-0.108
ady-0.107
Token his
Token ID465
Feature activation+2.20e-02

Pos logit contributions
++)+0.055
ound+0.054
show+0.051
amara+0.051
ady+0.051
Neg logit contributions
 Electricity-0.053
Initialized-0.052
Shipping-0.052
-0.051
Electric-0.051
Token songs
Token ID7259
Feature activation+2.62e-02

Pos logit contributions
++)+0.037
ound+0.036
amara+0.034
show+0.034
ady+0.034
Neg logit contributions
 Electricity-0.039
Initialized-0.038
Shipping-0.038
-0.038
Electric-0.037
Token.[
Token ID3693
Feature activation+5.89e-02

Pos logit contributions
++)+0.047
ound+0.046
show+0.043
 Stanley+0.043
amara+0.043
Neg logit contributions
 Electricity-0.044
Initialized-0.043
Shipping-0.043
-0.042
Electric-0.042
Token36
Token ID2623
Feature activation+2.42e-01

Pos logit contributions
++)+0.122
ound+0.120
 Stanley+0.115
amara+0.114
show+0.114
Neg logit contributions
 Electricity-0.080
Shipping-0.079
Initialized-0.078
-0.077
Electric-0.076
Token]
Token ID60
Feature activation+1.44e-01

Pos logit contributions
++)+0.305
ound+0.297
show+0.273
amara+0.271
 Stanley+0.271
Neg logit contributions
 Electricity-0.529
Shipping-0.519
Initialized-0.517
-0.512
Electric-0.509
Token Cob
Token ID14828
Feature activation+8.74e-01

Pos logit contributions
++)+0.298
ound+0.293
show+0.280
 Stanley+0.279
amara+0.277
Neg logit contributions
 Electricity-0.199
Initialized-0.194
Shipping-0.193
-0.190
Electric-0.188
Tokenain
Token ID391
Feature activation-1.04e-01

Pos logit contributions
++)+1.338
ound+1.315
show+1.229
 Stanley+1.217
ady+1.214
Neg logit contributions
 Electricity-1.681
Initialized-1.647
Shipping-1.646
-1.621
Electric-1.611
Token complained
Token ID13832
Feature activation+7.36e-02

Pos logit contributions
 Electricity+0.168
Shipping+0.163
Initialized+0.163
+0.161
Electric+0.160
Neg logit contributions
++)-0.191
ound-0.187
show-0.177
amara-0.176
 Stanley-0.176
Token when
Token ID618
Feature activation-7.81e-02

Pos logit contributions
++)+0.152
ound+0.150
show+0.143
 Stanley+0.142
amara+0.142
Neg logit contributions
 Electricity-0.102
Initialized-0.099
Shipping-0.099
-0.097
Electric-0.096
Token fans
Token ID3296
Feature activation-1.18e-01

Pos logit contributions
 Electricity+0.128
Initialized+0.124
Shipping+0.124
+0.122
Electric+0.122
Neg logit contributions
++)-0.142
ound-0.139
show-0.131
amara-0.131
ady-0.130
Token and
Token ID290
Feature activation-6.35e-02

Pos logit contributions
 Electricity+0.204
Initialized+0.198
Shipping+0.198
+0.195
Electric+0.194
Neg logit contributions
++)-0.202
ound-0.198
show-0.186
amara-0.185
 Stanley-0.185
Token which
Token ID543
Feature activation-1.55e-02

Pos logit contributions
 Electricity+0.133
Initialized+0.130
Shipping+0.130
+0.127
Electric+0.127
Neg logit contributions
++)-0.141
ound-0.138
show-0.130
amara-0.129
 Stanley-0.129
Token player
Token ID2137
Feature activation-1.37e-01

Pos logit contributions
 Electricity+0.026
Shipping+0.026
Initialized+0.026
+0.025
Electric+0.025
Neg logit contributions
++)-0.027
ound-0.026
show-0.025
amara-0.025
 Stanley-0.025
Token out
Token ID503
Feature activation+1.38e-01

Pos logit contributions
 Electricity+0.218
Initialized+0.212
Shipping+0.212
+0.208
Electric+0.207
Neg logit contributions
++)-0.254
ound-0.249
show-0.236
amara-0.234
 Stanley-0.233
Token-
Token ID12
Feature activation+6.10e-02

Pos logit contributions
++)+0.236
ound+0.230
show+0.217
 Stanley+0.216
amara+0.215
Neg logit contributions
 Electricity-0.240
Initialized-0.235
Shipping-0.234
-0.230
Electric-0.230
Tokenper
Token ID525
Feature activation-3.81e-03

Pos logit contributions
++)+0.098
ound+0.096
 Stanley+0.090
show+0.090
amara+0.089
Neg logit contributions
 Electricity-0.112
Initialized-0.110
Shipping-0.110
-0.108
Electric-0.108
Tokenforms
Token ID23914
Feature activation+8.74e-01

Pos logit contributions
 Electricity+0.005
Shipping+0.005
Initialized+0.005
+0.005
Electric+0.005
Neg logit contributions
++)-0.008
ound-0.008
show-0.007
 Stanley-0.007
amara-0.007
Token the
Token ID262
Feature activation+6.68e-02

Pos logit contributions
++)+1.548
ound+1.525
 Stanley+1.443
show+1.442
ady+1.429
Neg logit contributions
 Electricity-1.459
Shipping-1.432
Initialized-1.429
-1.404
Electric-1.398
Token other
Token ID584
Feature activation+9.52e-02

Pos logit contributions
++)+0.119
ound+0.117
show+0.110
amara+0.110
 Stanley+0.109
Neg logit contributions
 Electricity-0.111
Initialized-0.109
Shipping-0.109
-0.107
Electric-0.106
Token.
Token ID13
Feature activation+9.15e-03

Pos logit contributions
++)+0.173
ound+0.170
show+0.161
 Stanley+0.160
amara+0.160
Neg logit contributions
 Electricity-0.155
Initialized-0.152
Shipping-0.151
-0.149
Electric-0.148
Token Norman
Token ID19636
Feature activation-7.56e-02

Pos logit contributions
++)+0.017
ound+0.017
show+0.016
 Stanley+0.016
amara+0.016
Neg logit contributions
 Electricity-0.015
Initialized-0.014
Shipping-0.014
-0.014
Electric-0.014
Token must
Token ID1276
Feature activation+6.30e-02

Pos logit contributions
 Electricity+0.118
Initialized+0.115
Shipping+0.115
+0.112
Electric+0.112
Neg logit contributions
++)-0.142
ound-0.140
show-0.132
amara-0.131
 Stanley-0.131
Token for
Token ID329
Feature activation+2.51e-02

Pos logit contributions
++)+0.321
ound+0.317
 Stanley+0.300
show+0.299
ady+0.297
Neg logit contributions
 Electricity-0.267
Initialized-0.261
Shipping-0.260
-0.254
Electric-0.254
Token both
Token ID1111
Feature activation+4.86e-02

Pos logit contributions
++)+0.044
ound+0.043
show+0.040
amara+0.040
 Stanley+0.040
Neg logit contributions
 Electricity-0.043
Initialized-0.042
Shipping-0.042
-0.041
Electric-0.041
Token Square
Token ID9276
Feature activation-2.67e-01

Pos logit contributions
++)+0.082
ound+0.080
show+0.075
amara+0.075
ady+0.075
Neg logit contributions
 Electricity-0.086
Shipping-0.084
Initialized-0.084
-0.083
Electric-0.082
Token and
Token ID290
Feature activation+1.27e-03

Pos logit contributions
 Electricity+0.399
Shipping+0.388
Initialized+0.385
Electric+0.379
+0.378
Neg logit contributions
++)-0.523
ound-0.514
show-0.488
amara-0.487
ady-0.485
Token SN
Token ID11346
Feature activation+1.40e-01

Pos logit contributions
++)+0.002
ound+0.002
show+0.002
amara+0.002
ady+0.002
Neg logit contributions
 Electricity-0.002
Initialized-0.002
Shipping-0.002
-0.002
Electric-0.002
TokenES
Token ID1546
Feature activation+8.66e-01

Pos logit contributions
++)+0.245
ound+0.239
amara+0.226
ady+0.226
show+0.226
Neg logit contributions
 Electricity-0.239
Shipping-0.232
Initialized-0.232
-0.228
Electric-0.228
Token sound
Token ID2128
Feature activation-2.09e-01

Pos logit contributions
++)+1.423
ound+1.402
show+1.313
 Stanley+1.313
amara+1.297
Neg logit contributions
 Electricity-1.558
Initialized-1.537
Shipping-1.531
-1.502
Electric-1.494
Tokentracks
Token ID46074
Feature activation+4.90e-01

Pos logit contributions
 Electricity+0.472
Shipping+0.464
Initialized+0.462
+0.458
Electric+0.457
Neg logit contributions
++)-0.247
ound-0.238
show-0.217
amara-0.217
 Stanley-0.217
Token,
Token ID11
Feature activation+5.29e-02

Pos logit contributions
++)+0.902
ound+0.891
 Stanley+0.842
show+0.840
amara+0.831
Neg logit contributions
 Electricity-0.784
Initialized-0.769
Shipping-0.763
Electric-0.748
-0.747
Token and
Token ID290
Feature activation+3.37e-02

Pos logit contributions
++)+0.095
ound+0.093
show+0.088
 Stanley+0.088
amara+0.087
Neg logit contributions
 Electricity-0.087
Initialized-0.086
Shipping-0.085
-0.084
Electric-0.083
Token although
Token ID3584
Feature activation+3.79e-02

Pos logit contributions
++)+0.063
ound+0.062
 Stanley+0.059
show+0.059
amara+0.058
Neg logit contributions
 Electricity-0.053
Initialized-0.052
Shipping-0.052
-0.051
Electric-0.050
TokenST
Token ID2257
Feature activation+1.97e-01

Pos logit contributions
 Electricity+0.025
Initialized+0.024
Shipping+0.024
+0.024
Electric+0.024
Neg logit contributions
++)-0.017
ound-0.017
show-0.015
 Stanley-0.015
amara-0.015
Token OF
Token ID3963
Feature activation-1.34e-01

Pos logit contributions
++)+0.442
ound+0.436
show+0.416
amara+0.415
 Stanley+0.414
Neg logit contributions
 Electricity-0.240
Shipping-0.231
Initialized-0.231
-0.226
Electric-0.224
Token-
Token ID12
Feature activation-2.16e-01

Pos logit contributions
 Electricity+0.254
Shipping+0.248
Initialized+0.247
+0.245
Electric+0.243
Neg logit contributions
++)-0.208
ound-0.204
amara-0.191
show-0.190
ady-0.190
TokenPenn
Token ID39899
Feature activation-1.23e-01

Pos logit contributions
 Electricity+0.354
Shipping+0.349
Initialized+0.347
Electric+0.342
+0.342
Neg logit contributions
++)-0.390
ound-0.383
amara-0.361
 Stanley-0.360
show-0.359
Token J
Token ID449
Feature activation-3.64e-01

Pos logit contributions
 Electricity+0.215
Shipping+0.210
Initialized+0.210
+0.206
Electric+0.205
Neg logit contributions
++)-0.209
ound-0.205
show-0.192
 Stanley-0.192
amara-0.191
Tokenillet
Token ID32512
Feature activation+8.64e-01

Pos logit contributions
 Electricity+0.663
Shipping+0.650
Initialized+0.642
+0.640
Electric+0.637
Neg logit contributions
++)-0.584
ound-0.565
show-0.536
 Stanley-0.534
amara-0.530
Token-
Token ID12
Feature activation-1.80e-01

Pos logit contributions
++)+1.422
ound+1.392
show+1.313
 Stanley+1.306
amara+1.297
Neg logit contributions
 Electricity-1.554
Initialized-1.526
Shipping-1.523
-1.500
Electric-1.490
TokenFill
Token ID33762
Feature activation-2.15e-02

Pos logit contributions
 Electricity+0.290
Shipping+0.286
Initialized+0.284
+0.280
Electric+0.279
Neg logit contributions
++)-0.330
ound-0.324
amara-0.306
 Stanley-0.305
show-0.305
Token The
Token ID383
Feature activation-1.36e-01

Pos logit contributions
 Electricity+0.038
Initialized+0.037
Shipping+0.037
+0.036
Electric+0.036
Neg logit contributions
++)-0.036
ound-0.036
show-0.034
 Stanley-0.034
amara-0.033
Token Ball
Token ID6932
Feature activation+5.85e-02

Pos logit contributions
 Electricity+0.224
Shipping+0.218
Initialized+0.217
+0.214
Electric+0.213
Neg logit contributions
++)-0.244
ound-0.239
show-0.226
amara-0.226
ady-0.224
Tokenon
Token ID261
Feature activation-1.86e-03

Pos logit contributions
++)+0.097
ound+0.095
show+0.089
 Stanley+0.089
amara+0.089
Neg logit contributions
 Electricity-0.105
Shipping-0.103
Initialized-0.103
-0.101
Electric-0.100
Token35
Token ID2327
Feature activation+9.53e-02

Pos logit contributions
 Electricity+0.157
Shipping+0.155
Initialized+0.153
+0.153
Electric+0.152
Neg logit contributions
++)-0.059
ound-0.058
show-0.052
amara-0.051
ady-0.051
Token)
Token ID8
Feature activation-1.09e-01

Pos logit contributions
++)+0.099
ound+0.097
show+0.087
amara+0.087
 Stanley+0.087
Neg logit contributions
 Electricity-0.229
Shipping-0.225
Initialized-0.224
-0.222
Electric-0.221
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
 Electricity+0.180
Shipping+0.176
Initialized+0.176
+0.173
Electric+0.171
Neg logit contributions
++)-0.195
ound-0.191
show-0.180
amara-0.180
 Stanley-0.179
Token
Token ID198
Feature activation-1.15e-01

Pos logit contributions
 Electricity+0.223
Initialized+0.218
Shipping+0.218
+0.214
Electric+0.213
Neg logit contributions
++)-0.245
ound-0.241
amara-0.227
show-0.226
 Stanley-0.226
TokenPer
Token ID5990
Feature activation-1.23e-01

Pos logit contributions
 Electricity+0.177
Shipping+0.174
Initialized+0.173
+0.170
Electric+0.169
Neg logit contributions
++)-0.219
ound-0.215
show-0.203
 Stanley-0.203
amara-0.203
Tokenform
Token ID687
Feature activation+8.62e-01

Pos logit contributions
 Electricity+0.261
Shipping+0.256
Initialized+0.256
+0.253
Electric+0.252
Neg logit contributions
++)-0.164
ound-0.157
show-0.146
 Stanley-0.146
amara-0.145
Token 2
Token ID362
Feature activation+1.70e-02

Pos logit contributions
++)+1.511
ound+1.494
 Stanley+1.410
show+1.400
ady+1.389
Neg logit contributions
 Electricity-1.441
Initialized-1.424
Shipping-1.423
-1.399
Electric-1.385
Token aerial
Token ID17789
Feature activation-1.35e-01

Pos logit contributions
++)+0.030
ound+0.029
show+0.028
 Stanley+0.028
amara+0.028
Neg logit contributions
 Electricity-0.029
Initialized-0.028
Shipping-0.028
-0.028
Electric-0.027
Token gestures
Token ID24621
Feature activation+1.16e-01

Pos logit contributions
 Electricity+0.222
Initialized+0.216
Shipping+0.216
+0.212
Electric+0.211
Neg logit contributions
++)-0.244
ound-0.238
show-0.225
 Stanley-0.224
amara-0.224
Token before
Token ID878
Feature activation+2.09e-01

Pos logit contributions
++)+0.226
ound+0.223
show+0.212
 Stanley+0.211
amara+0.210
Neg logit contributions
 Electricity-0.172
Initialized-0.168
Shipping-0.168
-0.165
Electric-0.163
Token touching
Token ID15241
Feature activation+8.68e-02

Pos logit contributions
++)+0.401
ound+0.395
 Stanley+0.375
show+0.374
amara+0.370
Neg logit contributions
 Electricity-0.316
Shipping-0.310
Initialized-0.310
-0.306
Electric-0.302
Token
Token ID198
Feature activation-5.62e-02

Pos logit contributions
 Electricity+0.131
Initialized+0.128
Shipping+0.128
+0.126
Electric+0.125
Neg logit contributions
++)-0.142
ound-0.140
amara-0.132
show-0.131
 Stanley-0.131
Tokenre
Token ID260
Feature activation+4.05e-02

Pos logit contributions
 Electricity+0.091
Shipping+0.089
Initialized+0.089
+0.088
Electric+0.087
Neg logit contributions
++)-0.103
ound-0.101
 Stanley-0.095
show-0.095
amara-0.094
Tokeni
Token ID72
Feature activation+1.43e-01

Pos logit contributions
++)+0.066
ound+0.064
show+0.060
 Stanley+0.060
amara+0.060
Neg logit contributions
 Electricity-0.074
Shipping-0.072
Initialized-0.072
-0.071
Electric-0.071
Token Profile
Token ID13118
Feature activation+1.82e-01

Pos logit contributions
++)+0.263
ound+0.258
show+0.244
 Stanley+0.244
amara+0.243
Neg logit contributions
 Electricity-0.232
Shipping-0.226
Initialized-0.226
-0.222
Electric-0.221
Token Blog
Token ID14001
Feature activation+7.52e-01

Pos logit contributions
++)+0.272
ound+0.266
show+0.249
 Stanley+0.247
amara+0.246
Neg logit contributions
 Electricity-0.354
Initialized-0.347
Shipping-0.347
-0.342
Electric-0.340
Token Joined
Token ID16709
Feature activation+8.62e-01

Pos logit contributions
++)+1.115
ound+1.087
show+1.040
 Stanley+1.036
cum+1.005
Neg logit contributions
 Electricity-1.466
Shipping-1.458
Initialized-1.430
Electric-1.422
-1.407
Token October
Token ID3267
Feature activation+2.48e-02

Pos logit contributions
++)+1.587
ound+1.558
 Stanley+1.504
show+1.494
ady+1.450
Neg logit contributions
Shipping-1.349
 Electricity-1.346
Initialized-1.341
-1.310
Electric-1.306
Token 2002
Token ID6244
Feature activation+2.36e-01

Pos logit contributions
++)+0.038
ound+0.037
 Stanley+0.035
show+0.035
ady+0.034
Neg logit contributions
 Electricity-0.047
Initialized-0.047
Shipping-0.047
-0.046
Electric-0.046
Token United
Token ID1578
Feature activation+1.88e-01

Pos logit contributions
++)+0.487
ound+0.480
 Stanley+0.460
show+0.459
ady+0.453
Neg logit contributions
 Electricity-0.324
Initialized-0.318
Shipping-0.318
-0.310
Electric-0.308
Token States
Token ID1829
Feature activation+1.03e-01

Pos logit contributions
++)+0.259
ound+0.254
show+0.236
 Stanley+0.235
amara+0.233
Neg logit contributions
 Electricity-0.387
Initialized-0.381
Shipping-0.380
-0.375
Electric-0.373
Token 3
Token ID513
Feature activation+1.43e-01

Pos logit contributions
++)+0.179
ound+0.176
show+0.166
 Stanley+0.166
amara+0.164
Neg logit contributions
 Electricity-0.177
Initialized-0.173
Shipping-0.173
-0.170
Electric-0.169
Token
Token ID198
Feature activation+8.94e-02

Pos logit contributions
++)+0.180
ound+0.177
show+0.167
 Stanley+0.166
amara+0.166
Neg logit contributions
 Electricity-0.173
Initialized-0.169
Shipping-0.169
-0.166
Electric-0.165
Tokenpur
Token ID14225
Feature activation+3.67e-01

Pos logit contributions
++)+0.163
ound+0.159
 Stanley+0.152
amara+0.151
ady+0.150
Neg logit contributions
 Electricity-0.144
Shipping-0.143
Initialized-0.142
-0.140
Electric-0.140
Tokenak
Token ID461
Feature activation+3.14e-01

Pos logit contributions
++)+0.666
ound+0.653
show+0.618
 Stanley+0.616
amara+0.613
Neg logit contributions
 Electricity-0.599
Shipping-0.584
Initialized-0.584
-0.574
Electric-0.570
Tokenushi
Token ID17731
Feature activation+1.55e-01

Pos logit contributions
++)+0.537
ound+0.526
show+0.496
 Stanley+0.494
amara+0.492
Neg logit contributions
 Electricity-0.548
Initialized-0.535
Shipping-0.535
-0.526
Electric-0.523
Token Profile
Token ID13118
Feature activation+2.78e-01

Pos logit contributions
++)+0.292
ound+0.286
show+0.271
 Stanley+0.271
amara+0.271
Neg logit contributions
 Electricity-0.244
Shipping-0.237
Initialized-0.237
-0.233
Electric-0.232
Token Joined
Token ID16709
Feature activation+8.56e-01

Pos logit contributions
++)+0.433
ound+0.423
show+0.396
 Stanley+0.394
amara+0.393
Neg logit contributions
 Electricity-0.526
Initialized-0.515
Shipping-0.514
-0.507
Electric-0.504
Token August
Token ID2932
Feature activation+3.70e-01

Pos logit contributions
++)+1.592
ound+1.552
 Stanley+1.506
show+1.496
ady+1.449
Neg logit contributions
Shipping-1.328
 Electricity-1.327
Initialized-1.319
-1.295
Electric-1.287
Token 2012
Token ID2321
Feature activation+2.39e-01

Pos logit contributions
++)+0.564
ound+0.551
 Stanley+0.519
show+0.518
ady+0.510
Neg logit contributions
 Electricity-0.710
Shipping-0.699
Initialized-0.699
-0.687
Electric-0.685
Token United
Token ID1578
Feature activation+1.77e-01

Pos logit contributions
++)+0.499
ound+0.492
 Stanley+0.472
show+0.470
ady+0.465
Neg logit contributions
 Electricity-0.323
Initialized-0.317
Shipping-0.316
-0.308
Electric-0.306
Token States
Token ID1829
Feature activation+8.93e-02

Pos logit contributions
++)+0.249
ound+0.243
show+0.226
 Stanley+0.225
amara+0.224
Neg logit contributions
 Electricity-0.362
Initialized-0.355
Shipping-0.355
-0.350
Electric-0.348
Token 3
Token ID513
Feature activation+1.16e-01

Pos logit contributions
++)+0.155
ound+0.152
show+0.144
 Stanley+0.143
amara+0.142
Neg logit contributions
 Electricity-0.152
Initialized-0.149
Shipping-0.149
-0.147
Electric-0.146
Token and
Token ID290
Feature activation-1.28e-02

Pos logit contributions
 Electricity+0.129
Shipping+0.126
Initialized+0.126
+0.124
Electric+0.123
Neg logit contributions
++)-0.152
ound-0.149
show-0.141
 Stanley-0.140
amara-0.140
Token a
Token ID257
Feature activation-1.79e-02

Pos logit contributions
 Electricity+0.022
Shipping+0.021
Initialized+0.021
+0.021
Electric+0.021
Neg logit contributions
++)-0.022
ound-0.022
show-0.020
amara-0.020
 Stanley-0.020
Token bit
Token ID1643
Feature activation+1.46e-02

Pos logit contributions
 Electricity+0.032
Initialized+0.031
Shipping+0.031
+0.031
Electric+0.030
Neg logit contributions
++)-0.030
ound-0.029
show-0.028
amara-0.027
 Stanley-0.027
Token of
Token ID286
Feature activation+1.65e-02

Pos logit contributions
++)+0.026
ound+0.025
amara+0.023
show+0.023
 Stanley+0.023
Neg logit contributions
 Electricity-0.025
Initialized-0.024
Shipping-0.024
-0.024
Electric-0.024
Token Paul
Token ID3362
Feature activation+9.70e-02

Pos logit contributions
++)+0.028
ound+0.028
show+0.026
amara+0.026
 Stanley+0.026
Neg logit contributions
 Electricity-0.029
Initialized-0.028
Shipping-0.028
-0.028
Electric-0.027
Token Newman
Token ID27698
Feature activation+8.44e-01

Pos logit contributions
++)+0.158
ound+0.155
show+0.145
amara+0.144
ady+0.144
Neg logit contributions
 Electricity-0.177
Shipping-0.172
Initialized-0.172
-0.169
Electric-0.168
Token about
Token ID546
Feature activation-7.05e-02

Pos logit contributions
++)+1.480
ound+1.455
show+1.379
 Stanley+1.373
ady+1.362
Neg logit contributions
 Electricity-1.419
Initialized-1.405
Shipping-1.398
Electric-1.358
-1.356
Token him
Token ID683
Feature activation-8.76e-02

Pos logit contributions
 Electricity+0.094
Shipping+0.091
Initialized+0.091
+0.089
Electric+0.088
Neg logit contributions
++)-0.149
ound-0.147
show-0.140
amara-0.139
 Stanley-0.139
Token'.
Token ID4458
Feature activation-3.88e-02

Pos logit contributions
 Electricity+0.132
Shipping+0.129
Initialized+0.128
+0.127
Electric+0.125
Neg logit contributions
++)-0.170
ound-0.167
show-0.158
 Stanley-0.157
amara-0.157
Token Photograph
Token ID18903
Feature activation-2.80e-01

Pos logit contributions
 Electricity+0.050
Initialized+0.049
Shipping+0.049
+0.048
Electric+0.047
Neg logit contributions
++)-0.084
ound-0.082
show-0.079
amara-0.078
 Stanley-0.078
Token:
Token ID25
Feature activation-2.09e-01

Pos logit contributions
 Electricity+0.320
Initialized+0.309
Shipping+0.309
+0.301
Electric+0.298
Neg logit contributions
++)-0.647
ound-0.637
show-0.611
 Stanley-0.609
amara-0.606
Token memories
Token ID9846
Feature activation+3.74e-02

Pos logit contributions
 Electricity+0.130
Shipping+0.127
Initialized+0.126
+0.125
Electric+0.124
Neg logit contributions
++)-0.132
ound-0.129
show-0.121
 Stanley-0.121
amara-0.121
Token,
Token ID11
Feature activation-9.50e-02

Pos logit contributions
++)+0.064
ound+0.062
show+0.058
amara+0.058
 Stanley+0.058
Neg logit contributions
 Electricity-0.066
Shipping-0.064
Initialized-0.064
-0.063
Electric-0.063
Token old
Token ID1468
Feature activation-1.11e-01

Pos logit contributions
 Electricity+0.164
Shipping+0.160
Initialized+0.159
+0.158
Electric+0.156
Neg logit contributions
++)-0.164
ound-0.160
show-0.151
amara-0.150
 Stanley-0.150
Token photos
Token ID5205
Feature activation+6.97e-02

Pos logit contributions
 Electricity+0.179
Shipping+0.174
Initialized+0.173
+0.171
Electric+0.169
Neg logit contributions
++)-0.203
ound-0.199
show-0.188
amara-0.188
ady-0.187
Token,
Token ID11
Feature activation-1.40e-01

Pos logit contributions
++)+0.118
ound+0.114
amara+0.108
show+0.108
 Stanley+0.107
Neg logit contributions
 Electricity-0.123
Shipping-0.120
Initialized-0.120
-0.118
Electric-0.117
Token etc
Token ID3503
Feature activation+8.43e-01

Pos logit contributions
 Electricity+0.237
Shipping+0.231
Initialized+0.230
+0.228
Electric+0.225
Neg logit contributions
++)-0.246
ound-0.240
show-0.226
amara-0.226
 Stanley-0.225
Token.?
Token ID40791
Feature activation+2.47e-01

Pos logit contributions
++)+1.566
ound+1.543
show+1.462
 Stanley+1.454
amara+1.448
Neg logit contributions
 Electricity-1.338
Initialized-1.311
Shipping-1.306
-1.279
Electric-1.272
Token Want
Token ID16168
Feature activation+2.60e-01

Pos logit contributions
++)+0.484
ound+0.476
show+0.451
 Stanley+0.450
amara+0.449
Neg logit contributions
 Electricity-0.369
Shipping-0.359
Initialized-0.358
-0.352
Electric-0.349
Token to
Token ID284
Feature activation+7.15e-02

Pos logit contributions
++)+0.503
ound+0.493
show+0.468
 Stanley+0.466
amara+0.466
Neg logit contributions
 Electricity-0.397
Shipping-0.384
Initialized-0.383
-0.378
Electric-0.375
Token write
Token ID3551
Feature activation-4.14e-03

Pos logit contributions
++)+0.111
ound+0.109
show+0.102
 Stanley+0.102
amara+0.101
Neg logit contributions
 Electricity-0.135
Shipping-0.132
Initialized-0.132
-0.130
Electric-0.130
Token a
Token ID257
Feature activation+5.24e-02

Pos logit contributions
 Electricity+0.007
Shipping+0.006
Initialized+0.006
+0.006
Electric+0.006
Neg logit contributions
++)-0.008
ound-0.008
show-0.007
amara-0.007
 Stanley-0.007
Token13
Token ID1485
Feature activation+1.17e-01

Pos logit contributions
++)+0.009
ound+0.009
amara+0.008
 Stanley+0.008
show+0.008
Neg logit contributions
 Electricity-0.008
Shipping-0.008
Initialized-0.008
-0.008
Electric-0.008
Token]:
Token ID5974
Feature activation+8.19e-02

Pos logit contributions
++)+0.262
ound+0.257
show+0.247
 Stanley+0.246
ady+0.243
Neg logit contributions
 Electricity-0.144
Initialized-0.139
Shipping-0.138
-0.135
Electric-0.134
Token168
Token ID14656
Feature activation+2.20e-02

Pos logit contributions
++)+0.164
ound+0.161
show+0.153
 Stanley+0.153
amara+0.152
Neg logit contributions
 Electricity-0.118
Initialized-0.115
Shipping-0.115
-0.113
Electric-0.112
Token
Token ID1906
Feature activation-2.70e-01

Pos logit contributions
++)+0.043
ound+0.042
show+0.040
amara+0.040
ady+0.040
Neg logit contributions
 Electricity-0.033
Initialized-0.032
Shipping-0.032
-0.032
Electric-0.031
Token169
Token ID22172
Feature activation+1.33e-01

Pos logit contributions
 Electricity+0.403
Shipping+0.393
Initialized+0.393
+0.385
Electric+0.383
Neg logit contributions
++)-0.528
ound-0.520
show-0.493
 Stanley-0.491
amara-0.490
Token Cob
Token ID14828
Feature activation+8.41e-01

Pos logit contributions
++)+0.260
ound+0.255
show+0.242
amara+0.241
 Stanley+0.241
Neg logit contributions
 Electricity-0.200
Initialized-0.194
Shipping-0.194
-0.190
Electric-0.189
Tokenain
Token ID391
Feature activation-2.41e-01

Pos logit contributions
++)+1.299
ound+1.272
show+1.191
 Stanley+1.183
amara+1.178
Neg logit contributions
 Electricity-1.606
Initialized-1.572
Shipping-1.572
-1.548
Electric-1.539
Token said
Token ID531
Feature activation-7.77e-02

Pos logit contributions
 Electricity+0.394
Shipping+0.383
Initialized+0.383
+0.377
Electric+0.374
Neg logit contributions
++)-0.439
ound-0.431
show-0.408
amara-0.405
 Stanley-0.404
Token in
Token ID287
Feature activation-3.93e-02

Pos logit contributions
 Electricity+0.109
Shipping+0.105
Initialized+0.105
+0.103
Electric+0.103
Neg logit contributions
++)-0.159
ound-0.156
show-0.149
amara-0.148
ady-0.148
Token an
Token ID281
Feature activation+1.95e-02

Pos logit contributions
 Electricity+0.066
Initialized+0.064
Shipping+0.064
+0.063
Electric+0.063
Neg logit contributions
++)-0.070
ound-0.068
show-0.065
amara-0.064
ady-0.064
Token interview
Token ID2720
Feature activation+5.05e-02

Pos logit contributions
++)+0.028
ound+0.028
show+0.026
 Stanley+0.026
amara+0.025
Neg logit contributions
 Electricity-0.039
Initialized-0.038
Shipping-0.038
-0.038
Electric-0.037
Token and
Token ID290
Feature activation-2.18e-02

Pos logit contributions
 Electricity+0.174
Shipping+0.169
Initialized+0.169
+0.167
Electric+0.165
Neg logit contributions
++)-0.182
ound-0.177
show-0.167
amara-0.166
 Stanley-0.166
Token a
Token ID257
Feature activation-1.99e-02

Pos logit contributions
 Electricity+0.038
Initialized+0.037
Shipping+0.037
+0.036
Electric+0.036
Neg logit contributions
++)-0.037
ound-0.036
show-0.034
amara-0.034
 Stanley-0.034
Token bit
Token ID1643
Feature activation-2.97e-02

Pos logit contributions
 Electricity+0.037
Shipping+0.036
Initialized+0.036
+0.036
Electric+0.035
Neg logit contributions
++)-0.032
ound-0.031
amara-0.029
show-0.029
ady-0.029
Token of
Token ID286
Feature activation+9.66e-03

Pos logit contributions
 Electricity+0.051
Shipping+0.050
Initialized+0.050
+0.049
Electric+0.049
Neg logit contributions
++)-0.051
ound-0.050
amara-0.047
show-0.047
 Stanley-0.047
Token Paul
Token ID3362
Feature activation+1.16e-01

Pos logit contributions
++)+0.016
ound+0.015
amara+0.014
show+0.014
ady+0.014
Neg logit contributions
 Electricity-0.018
Initialized-0.017
Shipping-0.017
-0.017
Electric-0.017
Token Newman
Token ID27698
Feature activation+8.38e-01

Pos logit contributions
++)+0.104
ound+0.101
show+0.089
amara+0.088
 Stanley+0.087
Neg logit contributions
 Electricity-0.296
Initialized-0.290
Shipping-0.290
-0.287
Electric-0.285
Token about
Token ID546
Feature activation-9.22e-02

Pos logit contributions
++)+1.715
ound+1.687
show+1.616
 Stanley+1.607
ady+1.596
Neg logit contributions
 Electricity-1.164
Initialized-1.144
Shipping-1.137
-1.108
Electric-1.107
Token him
Token ID683
Feature activation-8.73e-02

Pos logit contributions
 Electricity+0.117
Initialized+0.114
Shipping+0.114
+0.111
Electric+0.110
Neg logit contributions
++)-0.201
ound-0.198
show-0.189
 Stanley-0.188
amara-0.188
Token.
Token ID13
Feature activation+7.58e-03

Pos logit contributions
 Electricity+0.138
Shipping+0.134
Initialized+0.134
+0.132
Electric+0.131
Neg logit contributions
++)-0.164
ound-0.160
show-0.152
amara-0.151
 Stanley-0.151
Token Coll
Token ID7778
Feature activation+9.00e-05

Pos logit contributions
++)+0.015
ound+0.014
show+0.014
amara+0.014
ady+0.014
Neg logit contributions
 Electricity-0.012
Initialized-0.011
Shipping-0.011
-0.011
Electric-0.011
Tokening
Token ID278
Feature activation+3.94e-02

Pos logit contributions
++)+0.000
ound+0.000
show+0.000
 Stanley+0.000
amara+0.000
Neg logit contributions
 Electricity-0.000
Shipping-0.000
Initialized-0.000
-0.000
Electric-0.000
Token for
Token ID329
Feature activation+1.98e-02

Pos logit contributions
++)+0.467
ound+0.460
show+0.436
 Stanley+0.436
ady+0.431
Neg logit contributions
 Electricity-0.409
Initialized-0.401
Shipping-0.400
-0.393
Electric-0.390
Token all
Token ID477
Feature activation-8.20e-03

Pos logit contributions
++)+0.036
ound+0.035
show+0.033
 Stanley+0.033
amara+0.033
Neg logit contributions
 Electricity-0.032
Shipping-0.031
Initialized-0.031
-0.031
Electric-0.031
Token those
Token ID883
Feature activation+1.48e-01

Pos logit contributions
 Electricity+0.012
Shipping+0.012
Initialized+0.012
+0.012
Electric+0.012
Neg logit contributions
++)-0.016
ound-0.016
show-0.015
amara-0.015
 Stanley-0.015
Token programmers
Token ID24867
Feature activation+3.60e-01

Pos logit contributions
++)+0.257
ound+0.252
show+0.237
 Stanley+0.236
amara+0.236
Neg logit contributions
 Electricity-0.256
Shipping-0.249
Initialized-0.249
-0.245
Electric-0.244
Token cr
Token ID1067
Feature activation+4.10e-01

Pos logit contributions
++)+0.660
ound+0.648
show+0.614
 Stanley+0.613
amara+0.605
Neg logit contributions
 Electricity-0.581
Initialized-0.570
Shipping-0.569
-0.557
Electric-0.554
Tokenanking
Token ID15230
Feature activation-9.96e-01

Pos logit contributions
++)+0.705
ound+0.694
show+0.651
 Stanley+0.648
amara+0.648
Neg logit contributions
 Electricity-0.710
Shipping-0.694
Initialized-0.694
-0.683
Electric-0.678
Token out
Token ID503
Feature activation+1.57e-01

Pos logit contributions
 Electricity+1.442
Initialized+1.389
Shipping+1.368
Electric+1.352
+1.351
Neg logit contributions
++)-1.993
ound-1.950
amara-1.866
ourke-1.856
show-1.854
Token the
Token ID262
Feature activation+7.50e-02

Pos logit contributions
++)+0.283
ound+0.278
show+0.263
 Stanley+0.262
amara+0.260
Neg logit contributions
 Electricity-0.258
Initialized-0.252
Shipping-0.252
-0.247
Electric-0.246
Token overhaul
Token ID18708
Feature activation+2.13e-01

Pos logit contributions
++)+0.129
ound+0.127
show+0.120
amara+0.119
 Stanley+0.119
Neg logit contributions
 Electricity-0.130
Shipping-0.126
Initialized-0.126
-0.124
Electric-0.123
Tokened
Token ID276
Feature activation-1.15e-01

Pos logit contributions
++)+0.382
ound+0.375
show+0.355
 Stanley+0.354
amara+0.351
Neg logit contributions
 Electricity-0.353
Initialized-0.346
Shipping-0.344
-0.339
Electric-0.337
Token Firefox
Token ID16802
Feature activation-3.78e-02

Pos logit contributions
 Electricity+0.187
Shipping+0.181
Initialized+0.181
+0.178
Electric+0.177
Neg logit contributions
++)-0.212
ound-0.208
show-0.197
amara-0.196
 Stanley-0.195
Token,
Token ID11
Feature activation-4.60e-02

Pos logit contributions
 Electricity+0.019
Shipping+0.018
Initialized+0.018
Electric+0.018
+0.018
Neg logit contributions
++)-0.020
ound-0.019
show-0.018
 Stanley-0.018
amara-0.018
Token including
Token ID1390
Feature activation-1.38e-01

Pos logit contributions
 Electricity+0.075
Shipping+0.073
Initialized+0.073
+0.072
Electric+0.072
Neg logit contributions
++)-0.084
ound-0.082
show-0.078
 Stanley-0.077
amara-0.077
Token headset
Token ID23492
Feature activation-2.78e-01

Pos logit contributions
 Electricity+0.227
Shipping+0.220
Initialized+0.219
Electric+0.216
+0.216
Neg logit contributions
++)-0.250
ound-0.244
show-0.231
amara-0.230
ady-0.228
Token,
Token ID11
Feature activation-6.59e-02

Pos logit contributions
 Electricity+0.470
Shipping+0.461
Initialized+0.458
Electric+0.451
+0.450
Neg logit contributions
++)-0.491
ound-0.473
show-0.449
ady-0.444
amara-0.444
Token cr
Token ID1067
Feature activation+1.11e-01

Pos logit contributions
 Electricity+0.109
Shipping+0.106
Initialized+0.106
+0.104
Electric+0.104
Neg logit contributions
++)-0.119
ound-0.116
show-0.110
amara-0.109
 Stanley-0.109
Tokenanks
Token ID2283
Feature activation-9.57e-01

Pos logit contributions
++)+0.159
ound+0.152
show+0.143
 Stanley+0.143
ourke+0.141
Neg logit contributions
 Electricity-0.224
Shipping-0.220
Initialized-0.218
Electric-0.216
-0.215
Token and
Token ID290
Feature activation-1.72e-02

Pos logit contributions
 Electricity+2.173
Shipping+2.153
Initialized+2.148
Electric+2.146
+2.103
Neg logit contributions
++)-1.101
ound-0.961
ourke-0.951
ady-0.942
 Stanley-0.931
Token brakes
Token ID23746
Feature activation+1.06e-01

Pos logit contributions
 Electricity+0.028
Shipping+0.028
Initialized+0.028
Electric+0.027
+0.027
Neg logit contributions
++)-0.031
ound-0.030
show-0.029
amara-0.028
ady-0.028
Token.
Token ID13
Feature activation-3.43e-02

Pos logit contributions
++)+0.195
ound+0.190
show+0.181
 Stanley+0.180
amara+0.180
Neg logit contributions
 Electricity-0.169
Shipping-0.165
Initialized-0.165
-0.162
Electric-0.161
Token The
Token ID383
Feature activation-1.18e-01

Pos logit contributions
 Electricity+0.047
Shipping+0.045
Initialized+0.045
+0.044
Electric+0.044
Neg logit contributions
++)-0.071
ound-0.070
show-0.067
 Stanley-0.067
amara-0.067
Token wheels
Token ID13666
Feature activation-4.70e-02

Pos logit contributions
 Electricity+0.209
Shipping+0.204
Initialized+0.203
+0.200
Electric+0.199
Neg logit contributions
++)-0.201
ound-0.196
show-0.184
amara-0.183
 Stanley-0.182
Token by
Token ID416
Feature activation+1.57e-02

Pos logit contributions
 Electricity+0.388
Initialized+0.379
Shipping+0.379
+0.373
Electric+0.371
Neg logit contributions
++)-0.362
ound-0.355
show-0.334
 Stanley-0.332
amara-0.332
Token clicking
Token ID12264
Feature activation-5.81e-02

Pos logit contributions
++)+0.021
ound+0.021
show+0.019
 Stanley+0.019
ady+0.019
Neg logit contributions
 Electricity-0.033
Initialized-0.033
Shipping-0.032
-0.032
Electric-0.032
Token the
Token ID262
Feature activation-2.47e-02

Pos logit contributions
 Electricity+0.100
Shipping+0.098
Initialized+0.098
+0.096
Electric+0.095
Neg logit contributions
++)-0.101
ound-0.099
show-0.093
 Stanley-0.092
amara-0.092
Token box
Token ID3091
Feature activation+3.03e-02

Pos logit contributions
 Electricity+0.033
Shipping+0.032
Initialized+0.032
+0.031
Electric+0.031
Neg logit contributions
++)-0.052
ound-0.051
show-0.049
 Stanley-0.048
amara-0.048
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
++)+0.057
ound+0.056
show+0.054
 Stanley+0.053
amara+0.053
Neg logit contributions
 Electricity-0.047
Shipping-0.046
Initialized-0.046
-0.045
Electric-0.045
Token Invalid
Token ID17665
Feature activation-8.83e-01

Pos logit contributions
 Electricity+0.182
Shipping+0.178
Initialized+0.178
+0.174
Electric+0.173
Neg logit contributions
++)-0.296
ound-0.290
 Stanley-0.279
show-0.279
cum-0.274
Token email
Token ID3053
Feature activation-2.47e-01

Pos logit contributions
 Electricity+1.032
Initialized+0.987
Shipping+0.987
+0.959
Electric+0.948
Neg logit contributions
++)-2.026
ound-1.992
show-1.905
amara-1.900
 Stanley-1.899
Token address
Token ID2209
Feature activation-3.88e-02

Pos logit contributions
 Electricity+0.399
Shipping+0.391
Initialized+0.389
+0.385
Electric+0.383
Neg logit contributions
++)-0.453
ound-0.444
show-0.423
 Stanley-0.418
ady-0.418
Token.
Token ID13
Feature activation-1.90e-01

Pos logit contributions
 Electricity+0.061
Shipping+0.059
Initialized+0.059
+0.058
Electric+0.058
Neg logit contributions
++)-0.073
ound-0.071
show-0.068
 Stanley-0.068
ady-0.067
Token Please
Token ID4222
Feature activation-3.49e-01

Pos logit contributions
 Electricity+0.219
Initialized+0.215
Shipping+0.214
Electric+0.208
+0.208
Neg logit contributions
++)-0.434
ound-0.425
show-0.411
 Stanley-0.410
cum-0.405
Token re
Token ID302
Feature activation-1.78e-01

Pos logit contributions
 Electricity+0.568
Initialized+0.554
Shipping+0.554
+0.545
Electric+0.541
Neg logit contributions
++)-0.635
ound-0.623
show-0.590
 Stanley-0.587
amara-0.584
Token easily
Token ID3538
Feature activation-2.41e-01

Pos logit contributions
 Electricity+0.163
Initialized+0.159
Shipping+0.159
+0.156
Electric+0.155
Neg logit contributions
++)-0.176
ound-0.173
show-0.164
 Stanley-0.163
amara-0.162
Token closed
Token ID4838
Feature activation-7.58e-02

Pos logit contributions
 Electricity+0.374
Initialized+0.364
Shipping+0.363
+0.356
Electric+0.355
Neg logit contributions
++)-0.457
ound-0.448
show-0.425
 Stanley-0.423
amara-0.423
Token up
Token ID510
Feature activation-6.22e-02

Pos logit contributions
 Electricity+0.125
Initialized+0.122
Shipping+0.122
+0.120
Electric+0.119
Neg logit contributions
++)-0.137
ound-0.134
show-0.127
 Stanley-0.127
ady-0.126
Token with
Token ID351
Feature activation-3.22e-02

Pos logit contributions
 Electricity+0.102
Initialized+0.100
Shipping+0.100
+0.098
Electric+0.097
Neg logit contributions
++)-0.112
ound-0.110
show-0.104
 Stanley-0.104
amara-0.103
Token finger
Token ID7660
Feature activation-7.45e-02

Pos logit contributions
 Electricity+0.054
Shipping+0.052
Initialized+0.052
+0.052
Electric+0.051
Neg logit contributions
++)-0.057
ound-0.056
show-0.053
 Stanley-0.053
amara-0.053
Tokenstock
Token ID13578
Feature activation-8.53e-01

Pos logit contributions
 Electricity+0.132
Initialized+0.129
Shipping+0.129
+0.127
Electric+0.126
Neg logit contributions
++)-0.126
ound-0.123
show-0.116
 Stanley-0.115
amara-0.115
Token,
Token ID11
Feature activation-5.02e-03

Pos logit contributions
 Electricity+1.351
Shipping+1.310
Initialized+1.305
+1.279
Electric+1.278
Neg logit contributions
++)-1.593
ound-1.558
show-1.477
amara-1.472
 Stanley-1.463
Token b
Token ID275
Feature activation+2.18e-02

Pos logit contributions
 Electricity+0.008
Shipping+0.008
Initialized+0.008
+0.007
Electric+0.007
Neg logit contributions
++)-0.009
ound-0.009
show-0.009
 Stanley-0.009
amara-0.009
Tokenraid
Token ID7086
Feature activation-9.49e-02

Pos logit contributions
++)+0.034
ound+0.034
show+0.031
 Stanley+0.031
amara+0.031
Neg logit contributions
 Electricity-0.041
Shipping-0.040
Initialized-0.040
-0.040
Electric-0.039
Token,
Token ID11
Feature activation-3.21e-02

Pos logit contributions
 Electricity+0.165
Shipping+0.161
Initialized+0.161
+0.159
Electric+0.158
Neg logit contributions
++)-0.162
ound-0.158
show-0.149
amara-0.148
 Stanley-0.148
Token or
Token ID393
Feature activation+3.05e-04

Pos logit contributions
 Electricity+0.054
Shipping+0.052
Initialized+0.052
+0.051
Electric+0.051
Neg logit contributions
++)-0.057
ound-0.056
show-0.053
amara-0.053
 Stanley-0.052
Token to
Token ID284
Feature activation-1.04e-01

Pos logit contributions
 Electricity+0.007
Shipping+0.006
Initialized+0.006
+0.006
Electric+0.006
Neg logit contributions
++)-0.009
ound-0.009
show-0.008
 Stanley-0.008
amara-0.008
Token the
Token ID262
Feature activation+1.49e-04

Pos logit contributions
 Electricity+0.175
Shipping+0.170
Initialized+0.170
+0.168
Electric+0.166
Neg logit contributions
++)-0.184
ound-0.180
show-0.169
amara-0.169
 Stanley-0.168
Token report
Token ID989
Feature activation+3.25e-02

Pos logit contributions
++)+0.000
ound+0.000
show+0.000
 Stanley+0.000
amara+0.000
Neg logit contributions
 Electricity-0.000
Shipping-0.000
Initialized-0.000
-0.000
Electric-0.000
Token from
Token ID422
Feature activation-8.12e-04

Pos logit contributions
++)+0.063
ound+0.061
show+0.058
 Stanley+0.058
amara+0.058
Neg logit contributions
 Electricity-0.050
Shipping-0.048
Initialized-0.048
-0.048
Electric-0.047
Token Xin
Token ID25426
Feature activation-2.97e-01

Pos logit contributions
 Electricity+0.001
Shipping+0.001
Initialized+0.001
+0.001
Electric+0.001
Neg logit contributions
++)-0.001
ound-0.001
show-0.001
amara-0.001
ady-0.001
Tokenhua
Token ID33061
Feature activation-8.36e-01

Pos logit contributions
 Electricity+0.271
Shipping+0.260
Initialized+0.257
+0.249
Electric+0.247
Neg logit contributions
++)-0.756
ound-0.745
show-0.715
 Stanley-0.713
amara-0.712
Token.
Token ID764
Feature activation+8.76e-02

Pos logit contributions
 Electricity+1.400
Shipping+1.346
Initialized+1.327
Electric+1.316
+1.316
Neg logit contributions
++)-1.503
ound-1.470
amara-1.401
show-1.388
cum-1.375
Token
Token ID198
Feature activation-2.17e-02

Pos logit contributions
++)+0.161
ound+0.158
show+0.150
 Stanley+0.149
amara+0.148
Neg logit contributions
 Electricity-0.141
Initialized-0.138
Shipping-0.138
-0.135
Electric-0.134
Token
Token ID198
Feature activation-2.02e-02

Pos logit contributions
 Electricity+0.036
Initialized+0.035
Shipping+0.035
+0.035
Electric+0.034
Neg logit contributions
++)-0.039
ound-0.038
amara-0.036
show-0.036
 Stanley-0.036
TokenThe
Token ID464
Feature activation+4.48e-02

Pos logit contributions
 Electricity+0.029
Initialized+0.028
Shipping+0.028
+0.027
Electric+0.027
Neg logit contributions
++)-0.041
ound-0.040
show-0.038
 Stanley-0.038
amara-0.038
Token code
Token ID2438
Feature activation-1.31e-01

Pos logit contributions
++)+0.077
ound+0.075
show+0.071
 Stanley+0.071
amara+0.070
Neg logit contributions
 Electricity-0.078
Shipping-0.076
Initialized-0.076
-0.075
Electric-0.074
Token by
Token ID416
Feature activation-4.73e-02

Pos logit contributions
 Electricity+0.446
Initialized+0.436
Shipping+0.436
+0.428
Electric+0.426
Neg logit contributions
++)-0.418
ound-0.410
show-0.386
 Stanley-0.384
amara-0.383
Token clicking
Token ID12264
Feature activation-8.63e-02

Pos logit contributions
 Electricity+0.099
Initialized+0.098
Shipping+0.098
+0.097
Electric+0.096
Neg logit contributions
++)-0.063
ound-0.062
show-0.057
 Stanley-0.057
ady-0.057
Token the
Token ID262
Feature activation-9.99e-02

Pos logit contributions
 Electricity+0.149
Shipping+0.146
Initialized+0.146
+0.143
Electric+0.142
Neg logit contributions
++)-0.149
ound-0.146
show-0.137
 Stanley-0.137
amara-0.137
Token box
Token ID3091
Feature activation-1.75e-02

Pos logit contributions
 Electricity+0.135
Shipping+0.131
Initialized+0.130
+0.128
Electric+0.127
Neg logit contributions
++)-0.210
ound-0.207
show-0.197
 Stanley-0.196
amara-0.196
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
 Electricity+0.027
Shipping+0.026
Initialized+0.026
+0.026
Electric+0.026
Neg logit contributions
++)-0.033
ound-0.033
show-0.031
 Stanley-0.031
amara-0.031
Token Invalid
Token ID17665
Feature activation-8.35e-01

Pos logit contributions
 Electricity+0.244
Shipping+0.239
Initialized+0.238
+0.234
Electric+0.231
Neg logit contributions
++)-0.403
ound-0.394
 Stanley-0.379
show-0.378
cum-0.372
Token email
Token ID3053
Feature activation-2.51e-01

Pos logit contributions
 Electricity+0.982
Initialized+0.943
Shipping+0.941
+0.915
Electric+0.906
Neg logit contributions
++)-1.907
ound-1.876
show-1.794
amara-1.789
 Stanley-1.789
Token address
Token ID2209
Feature activation-2.86e-02

Pos logit contributions
 Electricity+0.407
Shipping+0.399
Initialized+0.397
+0.393
Electric+0.390
Neg logit contributions
++)-0.458
ound-0.450
show-0.428
 Stanley-0.423
ady-0.423
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 Electricity+0.045
Shipping+0.044
Initialized+0.043
+0.043
Electric+0.042
Neg logit contributions
++)-0.054
ound-0.053
show-0.050
 Stanley-0.050
ady-0.050
Token Please
Token ID4222
Feature activation-3.47e-01

Pos logit contributions
 Electricity+0.280
Initialized+0.275
Shipping+0.275
+0.267
Electric+0.267
Neg logit contributions
++)-0.543
ound-0.531
show-0.514
 Stanley-0.513
cum-0.507
Token re
Token ID302
Feature activation-1.99e-01

Pos logit contributions
 Electricity+0.568
Initialized+0.555
Shipping+0.555
+0.546
Electric+0.542
Neg logit contributions
++)-0.627
ound-0.616
show-0.583
 Stanley-0.580
ady-0.577
Token H
Token ID367
Feature activation-3.04e-03

Pos logit contributions
 Electricity+0.030
Shipping+0.029
Initialized+0.028
+0.028
Electric+0.028
Neg logit contributions
++)-0.038
ound-0.037
show-0.035
amara-0.035
ady-0.035
Tokenenson
Token ID19069
Feature activation+5.44e-01

Pos logit contributions
 Electricity+0.007
Shipping+0.007
Initialized+0.007
+0.007
Electric+0.007
Neg logit contributions
++)-0.004
ound-0.003
 Stanley-0.003
show-0.003
amara-0.003
Token's
Token ID338
Feature activation-7.02e-02

Pos logit contributions
++)+0.980
ound+0.963
show+0.912
 Stanley+0.910
amara+0.903
Neg logit contributions
 Electricity-0.896
Initialized-0.876
Shipping-0.875
-0.860
Electric-0.854
Token post
Token ID1281
Feature activation+1.71e-03

Pos logit contributions
 Electricity+0.121
Initialized+0.118
Shipping+0.118
+0.116
Electric+0.115
Neg logit contributions
++)-0.121
ound-0.118
show-0.112
amara-0.111
ady-0.111
Tokenhum
Token ID17047
Feature activation-8.93e-02

Pos logit contributions
++)+0.003
ound+0.003
amara+0.003
ady+0.003
ourke+0.003
Neg logit contributions
 Electricity-0.003
Shipping-0.003
Initialized-0.003
-0.003
Electric-0.003
Tokenous
Token ID516
Feature activation-8.28e-01

Pos logit contributions
 Electricity+0.155
Initialized+0.151
Shipping+0.151
+0.149
Electric+0.148
Neg logit contributions
++)-0.153
ound-0.150
show-0.142
 Stanley-0.141
amara-0.140
Token induction
Token ID28471
Feature activation-1.21e-01

Pos logit contributions
 Electricity+1.475
Shipping+1.429
Initialized+1.427
+1.410
Electric+1.403
Neg logit contributions
++)-1.393
ound-1.344
amara-1.270
show-1.263
ady-1.262
Token as
Token ID355
Feature activation-7.74e-02

Pos logit contributions
 Electricity+0.198
Initialized+0.193
Shipping+0.193
+0.190
Electric+0.188
Neg logit contributions
++)-0.219
ound-0.213
amara-0.201
show-0.201
ady-0.201
Token a
Token ID257
Feature activation-3.07e-02

Pos logit contributions
 Electricity+0.134
Initialized+0.128
+0.128
Shipping+0.128
Electric+0.126
Neg logit contributions
++)-0.135
ound-0.131
amara-0.124
ady-0.123
okia-0.123
Token Disney
Token ID8519
Feature activation+3.60e-03

Pos logit contributions
 Electricity+0.056
Initialized+0.055
Shipping+0.055
+0.054
Electric+0.054
Neg logit contributions
++)-0.050
ound-0.048
amara-0.046
okia-0.045
show-0.045
Token Legend
Token ID9883
Feature activation+1.66e-01

Pos logit contributions
++)+0.006
ound+0.006
amara+0.005
okia+0.005
show+0.005
Neg logit contributions
 Electricity-0.007
Shipping-0.006
Initialized-0.006
-0.006
Electric-0.006
Token said
Token ID531
Feature activation-8.37e-02

Pos logit contributions
++)+0.377
ound+0.370
show+0.350
 Stanley+0.350
ady+0.347
Neg logit contributions
 Electricity-0.364
Initialized-0.355
Shipping-0.355
-0.349
Electric-0.347
Token he
Token ID339
Feature activation-1.31e-02

Pos logit contributions
 Electricity+0.134
Initialized+0.131
Shipping+0.131
+0.129
Electric+0.128
Neg logit contributions
++)-0.155
ound-0.152
show-0.143
amara-0.142
 Stanley-0.142
Token '
Token ID705
Feature activation-1.21e-01

Pos logit contributions
 Electricity+0.022
Shipping+0.021
Initialized+0.021
+0.021
Electric+0.021
Neg logit contributions
++)-0.023
ound-0.023
show-0.022
 Stanley-0.022
amara-0.022
Tokencould
Token ID24089
Feature activation-1.10e-01

Pos logit contributions
 Electricity+0.225
Initialized+0.222
Shipping+0.222
+0.219
Electric+0.218
Neg logit contributions
++)-0.189
ound-0.185
 Stanley-0.174
amara-0.172
show-0.172
Token have
Token ID423
Feature activation-4.34e-02

Pos logit contributions
 Electricity+0.211
Shipping+0.207
Initialized+0.206
+0.204
Electric+0.203
Neg logit contributions
++)-0.166
ound-0.161
 Stanley-0.151
amara-0.150
show-0.150
Token slug
Token ID31065
Feature activation-8.24e-01

Pos logit contributions
 Electricity+0.071
Initialized+0.069
Shipping+0.069
+0.068
Electric+0.068
Neg logit contributions
++)-0.079
ound-0.077
show-0.073
 Stanley-0.073
amara-0.072
Tokenged
Token ID2004
Feature activation+1.77e-01

Pos logit contributions
 Electricity+0.625
Initialized+0.591
Shipping+0.591
+0.571
Electric+0.561
Neg logit contributions
++)-2.215
ound-2.183
show-2.108
 Stanley-2.101
amara-2.097
Token'
Token ID6
Feature activation+3.21e-01

Pos logit contributions
++)+0.340
ound+0.334
show+0.317
 Stanley+0.316
amara+0.315
Neg logit contributions
 Electricity-0.271
Shipping-0.264
Initialized-0.264
-0.259
Electric-0.257
Token Carter
Token ID10831
Feature activation-1.50e-01

Pos logit contributions
++)+0.531
ound+0.520
show+0.489
 Stanley+0.488
amara+0.484
Neg logit contributions
 Electricity-0.575
Shipping-0.563
Initialized-0.563
-0.554
Electric-0.551
Token over
Token ID625
Feature activation-1.15e-01

Pos logit contributions
 Electricity+0.234
Initialized+0.228
Shipping+0.228
+0.224
Electric+0.223
Neg logit contributions
++)-0.283
ound-0.278
show-0.264
 Stanley-0.263
amara-0.262
Token this
Token ID428
Feature activation+1.25e-02

Pos logit contributions
 Electricity+0.185
Initialized+0.179
Shipping+0.179
+0.176
Electric+0.175
Neg logit contributions
++)-0.212
ound-0.207
show-0.195
amara-0.195
 Stanley-0.194
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
 Electricity+0.281
Shipping+0.274
Initialized+0.272
+0.270
Electric+0.267
Neg logit contributions
++)-0.275
ound-0.267
show-0.251
amara-0.250
 Stanley-0.250
Token someone
Token ID2130
Feature activation-2.07e-01

Pos logit contributions
 Electricity+0.236
Initialized+0.228
Shipping+0.228
+0.224
Electric+0.223
Neg logit contributions
++)-0.267
ound-0.260
show-0.246
amara-0.245
ady-0.244
Token let
Token ID1309
Feature activation-2.35e-01

Pos logit contributions
 Electricity+0.333
Initialized+0.325
Shipping+0.325
+0.319
Electric+0.317
Neg logit contributions
++)-0.380
ound-0.373
show-0.353
 Stanley-0.352
amara-0.351
Token a
Token ID257
Feature activation-9.62e-02

Pos logit contributions
 Electricity+0.372
Initialized+0.363
Shipping+0.361
+0.355
Electric+0.353
Neg logit contributions
++)-0.437
ound-0.429
show-0.406
amara-0.405
 Stanley-0.403
Token gir
Token ID37370
Feature activation-1.17e-01

Pos logit contributions
 Electricity+0.184
Shipping+0.180
Initialized+0.179
+0.177
Electric+0.175
Neg logit contributions
++)-0.148
ound-0.145
amara-0.136
show-0.135
ady-0.134
Tokenaffe
Token ID21223
Feature activation-8.14e-01

Pos logit contributions
 Electricity+0.138
Shipping+0.133
Initialized+0.133
+0.129
Electric+0.128
Neg logit contributions
++)-0.265
ound-0.259
show-0.249
 Stanley-0.248
amara-0.248
Token out
Token ID503
Feature activation+6.90e-02

Pos logit contributions
 Electricity+1.281
Initialized+1.246
Shipping+1.244
+1.215
Electric+1.213
Neg logit contributions
++)-1.510
ound-1.493
amara-1.412
show-1.398
 Stanley-1.395
Token of
Token ID286
Feature activation-1.07e-01

Pos logit contributions
++)+0.124
ound+0.122
show+0.115
 Stanley+0.115
amara+0.114
Neg logit contributions
 Electricity-0.114
Shipping-0.111
Initialized-0.111
-0.109
Electric-0.109
Token the
Token ID262
Feature activation-1.12e-01

Pos logit contributions
 Electricity+0.177
Initialized+0.173
Shipping+0.172
+0.169
Electric+0.168
Neg logit contributions
++)-0.192
ound-0.188
amara-0.178
show-0.178
 Stanley-0.176
Token Louisville
Token ID21525
Feature activation-4.64e-03

Pos logit contributions
 Electricity+0.173
Initialized+0.169
Shipping+0.168
+0.165
Electric+0.164
Neg logit contributions
++)-0.213
ound-0.209
show-0.198
amara-0.198
ady-0.196
Token zoo
Token ID26626
Feature activation-1.65e-01

Pos logit contributions
 Electricity+0.007
Shipping+0.007
Initialized+0.007
+0.007
Electric+0.007
Neg logit contributions
++)-0.009
ound-0.009
show-0.008
amara-0.008
 Stanley-0.008
Token is
Token ID318
Feature activation-3.05e-02

Pos logit contributions
 Electricity+0.082
Shipping+0.080
Initialized+0.079
+0.078
Electric+0.078
Neg logit contributions
++)-0.092
ound-0.091
show-0.086
 Stanley-0.085
amara-0.085
Token as
Token ID355
Feature activation-1.92e-02

Pos logit contributions
 Electricity+0.050
Shipping+0.049
Initialized+0.049
+0.048
Electric+0.047
Neg logit contributions
++)-0.055
ound-0.054
show-0.051
 Stanley-0.051
amara-0.051
Token American
Token ID1605
Feature activation+2.24e-01

Pos logit contributions
 Electricity+0.035
Initialized+0.034
Shipping+0.034
+0.033
Electric+0.033
Neg logit contributions
++)-0.031
ound-0.031
 Stanley-0.029
show-0.029
ady-0.029
Token as
Token ID355
Feature activation+1.44e-03

Pos logit contributions
++)+0.385
ound+0.374
show+0.353
amara+0.351
 Stanley+0.350
Neg logit contributions
 Electricity-0.391
Shipping-0.381
Initialized-0.380
-0.376
Electric-0.372
Token apple
Token ID17180
Feature activation-2.60e-01

Pos logit contributions
++)+0.003
ound+0.003
show+0.002
amara+0.002
 Stanley+0.002
Neg logit contributions
 Electricity-0.002
Shipping-0.002
Initialized-0.002
-0.002
Electric-0.002
Token pie
Token ID2508
Feature activation-8.09e-01

Pos logit contributions
 Electricity+0.444
Shipping+0.436
Initialized+0.429
+0.427
Electric+0.420
Neg logit contributions
++)-0.454
ound-0.445
amara-0.418
show-0.418
 Stanley-0.414
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
 Electricity+1.262
Shipping+1.226
Initialized+1.224
+1.209
Electric+1.191
Neg logit contributions
++)-1.529
ound-1.495
show-1.420
amara-1.413
ady-1.410
Token
Token ID198
Feature activation+1.20e-02

Pos logit contributions
 Electricity+0.024
Shipping+0.023
Initialized+0.023
+0.023
Electric+0.022
Neg logit contributions
++)-0.034
ound-0.034
show-0.032
 Stanley-0.032
amara-0.032
Token
Token ID198
Feature activation-8.72e-03

Pos logit contributions
++)+0.022
ound+0.021
amara+0.020
show+0.020
 Stanley+0.020
Neg logit contributions
 Electricity-0.020
Initialized-0.019
Shipping-0.019
-0.019
Electric-0.019
TokenNearly
Token ID27927
Feature activation-2.54e-03

Pos logit contributions
 Electricity+0.012
Shipping+0.012
Initialized+0.012
+0.012
Electric+0.012
Neg logit contributions
++)-0.018
ound-0.017
show-0.017
 Stanley-0.017
amara-0.017
Token two
Token ID734
Feature activation-7.81e-02

Pos logit contributions
 Electricity+0.004
Shipping+0.004
Initialized+0.004
+0.004
Electric+0.004
Neg logit contributions
++)-0.005
ound-0.005
show-0.004
amara-0.004
ady-0.004
Token
Token ID198
Feature activation-1.18e-02

Pos logit contributions
 Electricity+0.016
Initialized+0.016
Shipping+0.016
+0.016
Electric+0.016
Neg logit contributions
++)-0.018
ound-0.018
amara-0.017
show-0.017
 Stanley-0.016
TokenWhile
Token ID3633
Feature activation+1.84e-01

Pos logit contributions
 Electricity+0.017
Shipping+0.017
Initialized+0.017
+0.017
Electric+0.017
Neg logit contributions
++)-0.023
ound-0.023
 Stanley-0.022
amara-0.022
show-0.022
Token in
Token ID287
Feature activation-7.13e-02

Pos logit contributions
++)+0.341
ound+0.335
show+0.317
 Stanley+0.316
amara+0.315
Neg logit contributions
 Electricity-0.293
Initialized-0.285
Shipping-0.285
-0.280
Electric-0.278
Token a
Token ID257
Feature activation-9.29e-02

Pos logit contributions
 Electricity+0.129
Initialized+0.126
Shipping+0.125
+0.124
Electric+0.122
Neg logit contributions
++)-0.118
ound-0.115
show-0.108
amara-0.107
 Stanley-0.107
Token "
Token ID366
Feature activation-1.79e-01

Pos logit contributions
 Electricity+0.174
Initialized+0.170
Shipping+0.169
+0.168
Electric+0.165
Neg logit contributions
++)-0.147
ound-0.143
show-0.134
amara-0.133
ady-0.133
Tokenworthiness
Token ID48756
Feature activation-7.98e-01

Pos logit contributions
 Electricity+0.359
Shipping+0.356
Initialized+0.356
+0.352
Electric+0.350
Neg logit contributions
++)-0.254
ound-0.246
 Stanley-0.230
amara-0.226
ady-0.225
Token"
Token ID1
Feature activation+1.45e-02

Pos logit contributions
 Electricity+1.361
Initialized+1.344
Shipping+1.342
+1.328
_(+1.304
Neg logit contributions
++)-1.383
ound-1.315
show-1.242
amara-1.242
 Stanley-1.236
Token interview
Token ID2720
Feature activation+1.49e-02

Pos logit contributions
++)+0.024
ound+0.023
show+0.022
amara+0.021
 Stanley+0.021
Neg logit contributions
 Electricity-0.026
Initialized-0.026
Shipping-0.026
-0.026
Electric-0.025
Token,
Token ID11
Feature activation-9.14e-02

Pos logit contributions
++)+0.029
ound+0.028
show+0.027
amara+0.027
 Stanley+0.027
Neg logit contributions
 Electricity-0.023
Initialized-0.022
Shipping-0.022
-0.022
Electric-0.021
Token my
Token ID616
Feature activation+1.20e-01

Pos logit contributions
 Electricity+0.152
Shipping+0.147
Initialized+0.147
+0.145
Electric+0.144
Neg logit contributions
++)-0.165
ound-0.160
show-0.151
amara-0.150
ady-0.150
Token bishop
Token ID24233
Feature activation-6.42e-02

Pos logit contributions
++)+0.169
ound+0.164
show+0.153
amara+0.152
 Stanley+0.151
Neg logit contributions
 Electricity-0.246
Initialized-0.240
Shipping-0.240
-0.238
Electric-0.236
Token Louisiana
Token ID13340
Feature activation-4.47e-01

Pos logit contributions
 Electricity+0.026
Initialized+0.025
Shipping+0.025
+0.025
Electric+0.025
Neg logit contributions
++)-0.024
ound-0.023
show-0.022
 Stanley-0.022
amara-0.022
Token and
Token ID290
Feature activation-4.23e-02

Pos logit contributions
 Electricity+0.775
Shipping+0.757
Initialized+0.755
+0.744
Electric+0.739
Neg logit contributions
++)-0.768
ound-0.752
show-0.709
 Stanley-0.706
amara-0.705
Token talk
Token ID1561
Feature activation+2.32e-02

Pos logit contributions
 Electricity+0.066
Initialized+0.064
Shipping+0.064
+0.063
Electric+0.062
Neg logit contributions
++)-0.080
ound-0.079
show-0.075
 Stanley-0.075
ady-0.074
Token to
Token ID284
Feature activation-1.84e-02

Pos logit contributions
++)+0.046
ound+0.045
show+0.043
 Stanley+0.043
amara+0.043
Neg logit contributions
 Electricity-0.034
Shipping-0.033
Initialized-0.033
-0.032
Electric-0.032
Token [
Token ID685
Feature activation+1.50e-01

Pos logit contributions
 Electricity+0.029
Shipping+0.028
Initialized+0.028
+0.028
Electric+0.027
Neg logit contributions
++)-0.035
ound-0.034
show-0.032
amara-0.032
 Stanley-0.032
TokenLouis
Token ID32117
Feature activation-7.92e-01

Pos logit contributions
++)+0.269
ound+0.264
show+0.250
 Stanley+0.249
amara+0.248
Neg logit contributions
 Electricity-0.248
Shipping-0.242
Initialized-0.242
-0.238
Electric-0.237
Tokenian
Token ID666
Feature activation-1.32e-03

Pos logit contributions
 Electricity+1.255
Shipping+1.226
Initialized+1.210
Electric+1.197
+1.192
Neg logit contributions
++)-1.453
ound-1.430
 Stanley-1.357
show-1.354
cum-1.340
Tokenians
Token ID1547
Feature activation+8.97e-03

Pos logit contributions
 Electricity+0.002
Shipping+0.002
Initialized+0.002
+0.002
Electric+0.002
Neg logit contributions
++)-0.002
ound-0.002
show-0.002
 Stanley-0.002
amara-0.002
Token],
Token ID4357
Feature activation+2.25e-01

Pos logit contributions
++)+0.014
ound+0.013
show+0.012
 Stanley+0.012
amara+0.012
Neg logit contributions
 Electricity-0.017
Shipping-0.017
Initialized-0.017
-0.017
Electric-0.017
Token they
Token ID484
Feature activation-1.92e-02

Pos logit contributions
++)+0.444
ound+0.437
show+0.415
 Stanley+0.414
amara+0.412
Neg logit contributions
 Electricity-0.331
Initialized-0.322
Shipping-0.322
-0.315
Electric-0.313
Token
Token ID447
Feature activation-4.74e-02

Pos logit contributions
 Electricity+0.034
Shipping+0.033
Initialized+0.033
+0.033
Electric+0.033
Neg logit contributions
++)-0.032
ound-0.032
show-0.030
 Stanley-0.030
amara-0.030
Token.
Token ID13
Feature activation+4.21e-02

Pos logit contributions
++)+0.266
ound+0.261
show+0.248
 Stanley+0.247
amara+0.246
Neg logit contributions
 Electricity-0.223
Initialized-0.218
Shipping-0.218
-0.214
Electric-0.212
Token Future
Token ID10898
Feature activation+2.19e-01

Pos logit contributions
++)+0.082
ound+0.081
show+0.077
 Stanley+0.077
amara+0.076
Neg logit contributions
 Electricity-0.063
Initialized-0.061
Shipping-0.061
-0.060
Electric-0.059
Token Hall
Token ID4789
Feature activation-4.95e-02

Pos logit contributions
++)+0.340
ound+0.333
show+0.312
 Stanley+0.311
amara+0.308
Neg logit contributions
 Electricity-0.416
Initialized-0.407
Shipping-0.407
-0.401
Electric-0.399
Token of
Token ID286
Feature activation+1.01e-02

Pos logit contributions
 Electricity+0.084
Initialized+0.081
Shipping+0.080
+0.079
Electric+0.079
Neg logit contributions
++)-0.088
ound-0.086
amara-0.081
show-0.081
ady-0.080
Token Fame
Token ID18864
Feature activation+2.16e-01

Pos logit contributions
++)+0.016
ound+0.016
show+0.015
amara+0.015
ady+0.015
Neg logit contributions
 Electricity-0.019
Initialized-0.018
Shipping-0.018
Electric-0.018
-0.017
Token slug
Token ID31065
Feature activation-7.90e-01

Pos logit contributions
++)+0.332
ound+0.324
show+0.304
 Stanley+0.302
amara+0.301
Neg logit contributions
 Electricity-0.412
Initialized-0.403
Shipping-0.403
-0.397
Electric-0.395
Tokenger
Token ID1362
Feature activation+8.14e-02

Pos logit contributions
 Electricity+0.805
Shipping+0.781
+0.752
Electric+0.748
Initialized+0.746
Neg logit contributions
++)-1.916
ound-1.851
amara-1.786
okia-1.781
show-1.780
Token Stan
Token ID7299
Feature activation-3.69e-02

Pos logit contributions
++)+0.129
ound+0.126
show+0.119
amara+0.118
 Stanley+0.117
Neg logit contributions
 Electricity-0.152
Shipping-0.148
Initialized-0.148
-0.146
Electric-0.145
Token Mus
Token ID2629
Feature activation+1.55e-01

Pos logit contributions
 Electricity+0.064
Initialized+0.062
Shipping+0.062
+0.061
Electric+0.061
Neg logit contributions
++)-0.063
ound-0.062
show-0.058
amara-0.058
ady-0.058
Tokenial
Token ID498
Feature activation-2.88e-01

Pos logit contributions
++)+0.222
ound+0.214
 Stanley+0.198
amara+0.197
show+0.197
Neg logit contributions
 Electricity-0.312
Shipping-0.306
Initialized-0.305
-0.301
Electric-0.301
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
 Electricity+0.480
Shipping+0.468
Initialized+0.468
+0.461
Electric+0.458
Neg logit contributions
++)-0.512
ound-0.502
show-0.474
amara-0.470
 Stanley-0.468
Token that
Token ID326
Feature activation+5.93e-02

Pos logit contributions
 Electricity+0.117
Shipping+0.114
Initialized+0.114
+0.111
Electric+0.110
Neg logit contributions
++)-0.184
ound-0.181
show-0.173
 Stanley-0.172
amara-0.172
Token he
Token ID339
Feature activation+4.77e-02

Pos logit contributions
++)+0.114
ound+0.112
show+0.106
 Stanley+0.106
amara+0.105
Neg logit contributions
 Electricity-0.091
Initialized-0.089
Shipping-0.089
-0.087
Electric-0.086
Token would
Token ID561
Feature activation-1.31e-01

Pos logit contributions
++)+0.086
ound+0.085
show+0.080
 Stanley+0.080
amara+0.080
Neg logit contributions
 Electricity-0.078
Shipping-0.076
Initialized-0.076
-0.075
Electric-0.074
Token like
Token ID588
Feature activation-3.22e-02

Pos logit contributions
 Electricity+0.214
Shipping+0.209
Initialized+0.209
+0.205
Electric+0.204
Neg logit contributions
++)-0.239
ound-0.234
show-0.221
 Stanley-0.221
amara-0.220
Token the
Token ID262
Feature activation-2.60e-02

Pos logit contributions
 Electricity+0.050
Initialized+0.048
Shipping+0.048
+0.047
Electric+0.047
Neg logit contributions
++)-0.062
ound-0.060
show-0.057
 Stanley-0.057
amara-0.057
Token embassy
Token ID18613
Feature activation-7.88e-01

Pos logit contributions
 Electricity+0.039
Initialized+0.038
Shipping+0.038
+0.038
Electric+0.037
Neg logit contributions
++)-0.050
ound-0.050
show-0.047
 Stanley-0.047
amara-0.047
Token moved
Token ID3888
Feature activation-1.13e-01

Pos logit contributions
 Electricity+1.173
Shipping+1.139
Initialized+1.139
+1.119
Electric+1.105
Neg logit contributions
++)-1.547
ound-1.514
show-1.436
amara-1.431
 Stanley-1.428
Token to
Token ID284
Feature activation-6.47e-03

Pos logit contributions
 Electricity+0.173
Initialized+0.169
Shipping+0.167
+0.165
Electric+0.164
Neg logit contributions
++)-0.218
ound-0.215
show-0.205
 Stanley-0.204
ady-0.203
Token Jerusalem
Token ID10843
Feature activation-2.45e-01

Pos logit contributions
 Electricity+0.013
Initialized+0.013
Shipping+0.013
+0.012
Electric+0.012
Neg logit contributions
++)-0.009
ound-0.009
show-0.009
 Stanley-0.009
amara-0.009
Token,
Token ID11
Feature activation-3.44e-02

Pos logit contributions
 Electricity+0.375
Shipping+0.365
Initialized+0.365
+0.358
Electric+0.355
Neg logit contributions
++)-0.469
ound-0.461
show-0.437
 Stanley-0.435
amara-0.434
Token but
Token ID475
Feature activation-4.03e-02

Pos logit contributions
 Electricity+0.052
Initialized+0.051
Shipping+0.051
+0.050
Electric+0.049
Neg logit contributions
++)-0.067
ound-0.065
show-0.062
 Stanley-0.062
amara-0.062
Tokenacing
Token ID4092
Feature activation+6.75e-02

Pos logit contributions
 Electricity+0.332
Initialized+0.323
Shipping+0.323
+0.317
Electric+0.314
Neg logit contributions
++)-0.429
ound-0.422
show-0.400
 Stanley-0.398
amara-0.398
Token in
Token ID287
Feature activation-8.02e-03

Pos logit contributions
++)+0.120
ound+0.118
show+0.112
amara+0.111
 Stanley+0.110
Neg logit contributions
 Electricity-0.113
Initialized-0.109
Shipping-0.109
-0.108
Electric-0.107
Token reverse
Token ID9575
Feature activation-7.54e-02

Pos logit contributions
 Electricity+0.014
Shipping+0.014
Initialized+0.014
+0.013
Electric+0.013
Neg logit contributions
++)-0.014
ound-0.013
show-0.013
amara-0.013
 Stanley-0.012
Token the
Token ID262
Feature activation-7.00e-02

Pos logit contributions
 Electricity+0.120
Initialized+0.117
Shipping+0.117
+0.115
Electric+0.114
Neg logit contributions
++)-0.140
ound-0.138
show-0.130
 Stanley-0.130
amara-0.129
Token crossing
Token ID12538
Feature activation+1.06e-01

Pos logit contributions
 Electricity+0.109
Shipping+0.106
Initialized+0.106
+0.104
Electric+0.103
Neg logit contributions
++)-0.133
ound-0.130
show-0.123
amara-0.123
 Stanley-0.122
Token route
Token ID6339
Feature activation-7.83e-01

Pos logit contributions
++)+0.185
ound+0.181
show+0.171
 Stanley+0.170
amara+0.170
Neg logit contributions
 Electricity-0.179
Shipping-0.175
Initialized-0.175
-0.172
Electric-0.171
Token of
Token ID286
Feature activation-8.23e-02

Pos logit contributions
 Electricity+1.185
Shipping+1.147
Initialized+1.138
+1.125
Electric+1.111
Neg logit contributions
++)-1.520
ound-1.483
amara-1.411
show-1.400
 Stanley-1.391
Token another
Token ID1194
Feature activation-1.36e-01

Pos logit contributions
 Electricity+0.140
Initialized+0.136
Shipping+0.135
+0.134
Electric+0.132
Neg logit contributions
++)-0.145
ound-0.142
show-0.134
amara-0.133
ady-0.132
Token celebrated
Token ID13943
Feature activation-6.38e-02

Pos logit contributions
 Electricity+0.249
Shipping+0.242
Initialized+0.241
+0.238
Electric+0.236
Neg logit contributions
++)-0.223
ound-0.217
show-0.204
amara-0.203
ady-0.201
Token inv
Token ID800
Feature activation+1.12e-01

Pos logit contributions
 Electricity+0.118
Shipping+0.115
Initialized+0.115
+0.113
Electric+0.112
Neg logit contributions
++)-0.102
ound-0.100
show-0.094
amara-0.094
ady-0.093
Tokenader
Token ID5067
Feature activation-2.79e-02

Pos logit contributions
++)+0.142
ound+0.134
show+0.126
 Stanley+0.124
amara+0.124
Neg logit contributions
 Electricity-0.245
Shipping-0.241
Initialized-0.240
_-_-0.238
_(-0.236
Token and
Token ID290
Feature activation+1.92e-02

Pos logit contributions
 Electricity+0.087
Shipping+0.085
Initialized+0.084
+0.084
Electric+0.083
Neg logit contributions
++)-0.092
ound-0.088
amara-0.083
ady-0.083
 Stanley-0.083
Token other
Token ID584
Feature activation+7.65e-02

Pos logit contributions
++)+0.033
ound+0.033
show+0.031
amara+0.031
 Stanley+0.031
Neg logit contributions
 Electricity-0.033
Shipping-0.032
Initialized-0.032
-0.031
Electric-0.031
Token messages
Token ID6218
Feature activation+1.34e-01

Pos logit contributions
++)+0.127
ound+0.124
show+0.117
 Stanley+0.116
amara+0.116
Neg logit contributions
 Electricity-0.137
Shipping-0.134
Initialized-0.134
-0.132
Electric-0.131
Token via
Token ID2884
Feature activation-1.19e-01

Pos logit contributions
++)+0.260
ound+0.256
show+0.243
 Stanley+0.242
amara+0.241
Neg logit contributions
 Electricity-0.200
Initialized-0.195
Shipping-0.195
-0.191
Electric-0.190
Token Mi
Token ID13756
Feature activation-4.92e-02

Pos logit contributions
 Electricity+0.200
Shipping+0.194
Initialized+0.193
+0.192
Electric+0.189
Neg logit contributions
++)-0.211
ound-0.206
show-0.195
amara-0.193
 Stanley-0.192
Tokeniverse
Token ID3997
Feature activation-7.77e-01

Pos logit contributions
 Electricity+0.064
Shipping+0.062
Initialized+0.062
+0.061
Electric+0.060
Neg logit contributions
++)-0.106
ound-0.104
show-0.099
 Stanley-0.099
amara-0.099
Token.
Token ID13
Feature activation-9.06e-02

Pos logit contributions
 Electricity+1.239
Shipping+1.210
Initialized+1.199
+1.190
Electric+1.166
Neg logit contributions
++)-1.445
ound-1.401
show-1.328
 Stanley-1.323
amara-1.321
Token
Token ID198
Feature activation+9.89e-03

Pos logit contributions
 Electricity+0.137
Shipping+0.133
Initialized+0.133
+0.130
Electric+0.129
Neg logit contributions
++)-0.176
ound-0.173
show-0.164
 Stanley-0.163
amara-0.163
Token
Token ID198
Feature activation+7.99e-03

Pos logit contributions
++)+0.018
ound+0.017
amara+0.016
show+0.016
 Stanley+0.016
Neg logit contributions
 Electricity-0.016
Initialized-0.016
Shipping-0.016
-0.016
Electric-0.016
TokenThere
Token ID1858
Feature activation-1.72e-02

Pos logit contributions
++)+0.016
ound+0.016
show+0.015
 Stanley+0.015
amara+0.015
Neg logit contributions
 Electricity-0.011
Shipping-0.011
Initialized-0.011
-0.011
Electric-0.011
Token are
Token ID389
Feature activation-1.63e-01

Pos logit contributions
 Electricity+0.028
Shipping+0.027
Initialized+0.027
+0.027
Electric+0.027
Neg logit contributions
++)-0.032
ound-0.031
show-0.029
 Stanley-0.029
amara-0.029
Token lack
Token ID3092
Feature activation-3.87e-01

Pos logit contributions
++)+0.054
ound+0.053
show+0.050
 Stanley+0.050
ady+0.050
Neg logit contributions
 Electricity-0.058
Initialized-0.056
Shipping-0.056
-0.055
Electric-0.055
Token character
Token ID2095
Feature activation-1.21e-01

Pos logit contributions
 Electricity+0.569
Shipping+0.555
Initialized+0.548
+0.546
Electric+0.535
Neg logit contributions
++)-0.764
ound-0.747
amara-0.708
show-0.706
okia-0.699
Token?
Token ID30
Feature activation+4.29e-02

Pos logit contributions
 Electricity+0.171
Shipping+0.166
Initialized+0.166
+0.163
Electric+0.161
Neg logit contributions
++)-0.248
ound-0.243
show-0.231
amara-0.230
 Stanley-0.230
Token What
Token ID1867
Feature activation+3.89e-02

Pos logit contributions
++)+0.086
ound+0.085
show+0.080
amara+0.080
 Stanley+0.080
Neg logit contributions
 Electricity-0.062
Shipping-0.060
Initialized-0.060
-0.059
Electric-0.058
Token about
Token ID546
Feature activation-1.15e-01

Pos logit contributions
++)+0.076
ound+0.075
show+0.071
amara+0.071
 Stanley+0.070
Neg logit contributions
 Electricity-0.058
Shipping-0.057
Initialized-0.056
-0.056
Electric-0.055
Token PK
Token ID29673
Feature activation-7.76e-01

Pos logit contributions
 Electricity+0.199
Shipping+0.194
Initialized+0.193
+0.191
Electric+0.189
Neg logit contributions
++)-0.200
ound-0.195
amara-0.184
show-0.184
ady-0.182
Token Sub
Token ID3834
Feature activation+2.45e-01

Pos logit contributions
 Electricity+1.352
Shipping+1.316
+1.314
Initialized+1.311
_-_+1.295
Neg logit contributions
++)-1.309
ound-1.274
show-1.193
amara-1.182
ady-1.179
Tokenban
Token ID3820
Feature activation+1.33e-01

Pos logit contributions
++)+0.281
ound+0.272
show+0.249
 Stanley+0.247
amara+0.246
Neg logit contributions
 Electricity-0.564
Shipping-0.554
Initialized-0.553
-0.547
Electric-0.544
Token?
Token ID30
Feature activation+4.50e-02

Pos logit contributions
++)+0.250
ound+0.246
show+0.233
 Stanley+0.231
amara+0.231
Neg logit contributions
 Electricity-0.208
Shipping-0.202
Initialized-0.202
-0.199
Electric-0.197
Token (
Token ID357
Feature activation+3.82e-02

Pos logit contributions
++)+0.091
ound+0.089
show+0.085
 Stanley+0.085
amara+0.084
Neg logit contributions
 Electricity-0.064
Initialized-0.063
Shipping-0.063
-0.061
Electric-0.061
TokenActually
Token ID26417
Feature activation-3.37e-01

Pos logit contributions
++)+0.074
ound+0.073
show+0.069
 Stanley+0.069
amara+0.069
Neg logit contributions
 Electricity-0.057
Shipping-0.056
Initialized-0.056
-0.055
Electric-0.055
Token isn
Token ID2125
Feature activation+8.48e-02

Pos logit contributions
++)+0.296
ound+0.290
show+0.274
 Stanley+0.273
amara+0.273
Neg logit contributions
 Electricity-0.259
Shipping-0.252
Initialized-0.252
-0.248
Electric-0.246
Token't
Token ID470
Feature activation+8.33e-03

Pos logit contributions
++)+0.157
ound+0.154
show+0.146
 Stanley+0.145
amara+0.145
Neg logit contributions
 Electricity-0.135
Initialized-0.132
Shipping-0.132
-0.130
Electric-0.129
Token that
Token ID326
Feature activation-4.15e-02

Pos logit contributions
++)+0.016
ound+0.016
show+0.015
 Stanley+0.015
amara+0.015
Neg logit contributions
 Electricity-0.013
Shipping-0.012
Initialized-0.012
-0.012
Electric-0.012
Token they
Token ID484
Feature activation-3.37e-02

Pos logit contributions
 Electricity+0.064
Initialized+0.062
Shipping+0.062
+0.061
Electric+0.060
Neg logit contributions
++)-0.080
ound-0.078
show-0.074
amara-0.074
 Stanley-0.074
Token should
Token ID815
Feature activation+2.21e-01

Pos logit contributions
 Electricity+0.058
Initialized+0.056
Shipping+0.056
+0.055
Electric+0.055
Neg logit contributions
++)-0.058
ound-0.057
show-0.054
amara-0.054
 Stanley-0.054
Token wel
Token ID5029
Feature activation-7.76e-01

Pos logit contributions
++)+0.363
ound+0.356
show+0.335
 Stanley+0.333
ady+0.331
Neg logit contributions
 Electricity-0.399
Initialized-0.391
Shipping-0.391
-0.384
Electric-0.382
Tokensh
Token ID1477
Feature activation+4.25e-02

Pos logit contributions
 Electricity+1.366
Shipping+1.347
Initialized+1.333
Electric+1.310
+1.307
Neg logit contributions
++)-1.278
ound-1.235
 Stanley-1.180
amara-1.177
show-1.165
Token at
Token ID379
Feature activation+1.60e-02

Pos logit contributions
++)+0.080
ound+0.079
show+0.075
amara+0.074
 Stanley+0.074
Neg logit contributions
 Electricity-0.066
Initialized-0.064
Shipping-0.064
-0.063
Electric-0.063
Token putting
Token ID5137
Feature activation+5.65e-02

Pos logit contributions
++)+0.030
ound+0.030
show+0.028
amara+0.028
 Stanley+0.028
Neg logit contributions
 Electricity-0.025
Initialized-0.024
Shipping-0.024
-0.023
Electric-0.023
Token you
Token ID345
Feature activation+1.12e-01

Pos logit contributions
++)+0.106
ound+0.104
show+0.098
amara+0.098
ady+0.097
Neg logit contributions
 Electricity-0.089
Initialized-0.087
Shipping-0.086
-0.085
Electric-0.084
Token on
Token ID319
Feature activation-6.35e-04

Pos logit contributions
++)+0.217
ound+0.213
show+0.202
 Stanley+0.202
amara+0.201
Neg logit contributions
 Electricity-0.170
Shipping-0.166
Initialized-0.165
-0.162
Electric-0.161
Token:
Token ID25
Feature activation+7.16e-02

Pos logit contributions
 Electricity+0.358
Initialized+0.350
Shipping+0.350
+0.345
Electric+0.342
Neg logit contributions
++)-0.327
ound-0.320
show-0.301
 Stanley-0.299
amara-0.298
Token "
Token ID366
Feature activation-2.70e-02

Pos logit contributions
++)+0.145
ound+0.142
show+0.135
 Stanley+0.135
amara+0.134
Neg logit contributions
 Electricity-0.102
Shipping-0.099
Initialized-0.099
-0.097
Electric-0.097
TokenTrans
Token ID8291
Feature activation+1.08e-01

Pos logit contributions
 Electricity+0.037
Initialized+0.036
Shipping+0.036
+0.035
Electric+0.035
Neg logit contributions
++)-0.056
ound-0.055
 Stanley-0.053
show-0.053
amara-0.052
Tokensexual
Token ID18338
Feature activation-2.32e-01

Pos logit contributions
++)+0.150
ound+0.146
show+0.135
 Stanley+0.134
amara+0.133
Neg logit contributions
 Electricity-0.222
Initialized-0.218
Shipping-0.218
-0.215
Electric-0.213
Token"
Token ID1
Feature activation+8.29e-02

Pos logit contributions
 Electricity+0.363
Initialized+0.354
Shipping+0.353
+0.349
Electric+0.343
Neg logit contributions
++)-0.436
ound-0.427
show-0.405
 Stanley-0.403
amara-0.402
Token refers
Token ID10229
Feature activation-7.73e-01

Pos logit contributions
++)+0.157
ound+0.154
show+0.146
 Stanley+0.146
amara+0.145
Neg logit contributions
 Electricity-0.129
Shipping-0.126
Initialized-0.126
-0.123
Electric-0.122
Token to
Token ID284
Feature activation-8.21e-02

Pos logit contributions
 Electricity+1.069
Shipping+1.039
Initialized+1.034
+1.025
Electric+1.009
Neg logit contributions
++)-1.603
ound-1.557
amara-1.486
show-1.485
 Stanley-1.476
Token a
Token ID257
Feature activation-6.87e-02

Pos logit contributions
 Electricity+0.131
Initialized+0.128
Shipping+0.127
+0.126
Electric+0.124
Neg logit contributions
++)-0.152
ound-0.149
show-0.141
amara-0.140
ady-0.140
Token more
Token ID517
Feature activation-7.12e-02

Pos logit contributions
 Electricity+0.121
Initialized+0.118
Shipping+0.117
+0.116
Electric+0.114
Neg logit contributions
++)-0.116
ound-0.114
show-0.107
amara-0.107
ady-0.106
Token specific
Token ID2176
Feature activation+1.72e-02

Pos logit contributions
 Electricity+0.119
Initialized+0.116
Shipping+0.116
+0.114
Electric+0.113
Neg logit contributions
++)-0.127
ound-0.124
show-0.117
amara-0.116
 Stanley-0.116
Token transgender
Token ID10637
Feature activation+1.41e-01

Pos logit contributions
++)+0.025
ound+0.024
show+0.022
amara+0.022
ady+0.022
Neg logit contributions
 Electricity-0.035
Initialized-0.034
Shipping-0.034
-0.034
Electric-0.033
Token by
Token ID416
Feature activation+1.74e-02

Pos logit contributions
 Electricity+0.226
Initialized+0.221
Shipping+0.221
+0.217
Electric+0.216
Neg logit contributions
++)-0.208
ound-0.204
show-0.192
 Stanley-0.191
amara-0.190
Token clicking
Token ID12264
Feature activation+1.81e-02

Pos logit contributions
++)+0.023
ound+0.022
show+0.021
 Stanley+0.021
ady+0.020
Neg logit contributions
 Electricity-0.037
Initialized-0.037
Shipping-0.036
-0.036
Electric-0.036
Token the
Token ID262
Feature activation-2.85e-02

Pos logit contributions
++)+0.031
ound+0.031
show+0.029
 Stanley+0.029
amara+0.029
Neg logit contributions
 Electricity-0.031
Shipping-0.031
Initialized-0.031
-0.030
Electric-0.030
Token box
Token ID3091
Feature activation+6.79e-02

Pos logit contributions
 Electricity+0.039
Shipping+0.037
Initialized+0.037
+0.037
Electric+0.036
Neg logit contributions
++)-0.060
ound-0.059
show-0.056
 Stanley-0.056
amara-0.055
Token.
Token ID13
Feature activation-9.56e-02

Pos logit contributions
++)+0.128
ound+0.126
show+0.120
 Stanley+0.120
amara+0.118
Neg logit contributions
 Electricity-0.106
Shipping-0.103
Initialized-0.103
-0.101
Electric-0.101
Token Invalid
Token ID17665
Feature activation-7.73e-01

Pos logit contributions
 Electricity+0.124
Shipping+0.122
Initialized+0.121
+0.118
Electric+0.118
Neg logit contributions
++)-0.204
ound-0.199
 Stanley-0.192
show-0.192
cum-0.188
Token email
Token ID3053
Feature activation-2.00e-01

Pos logit contributions
 Electricity+0.910
Initialized+0.874
Shipping+0.874
+0.851
Electric+0.840
Neg logit contributions
++)-1.763
ound-1.734
show-1.659
 Stanley-1.654
amara-1.653
Token address
Token ID2209
Feature activation-1.44e-02

Pos logit contributions
 Electricity+0.323
Shipping+0.316
Initialized+0.315
+0.311
Electric+0.309
Neg logit contributions
++)-0.366
ound-0.360
show-0.342
 Stanley-0.338
ady-0.338
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 Electricity+0.023
Initialized+0.022
Shipping+0.022
+0.022
Electric+0.022
Neg logit contributions
++)-0.027
ound-0.027
show-0.025
 Stanley-0.025
ady-0.025
Token Please
Token ID4222
Feature activation-2.89e-01

Pos logit contributions
 Electricity+0.160
Initialized+0.157
Shipping+0.156
Electric+0.152
+0.151
Neg logit contributions
++)-0.316
ound-0.310
show-0.300
 Stanley-0.299
cum-0.295
Token re
Token ID302
Feature activation-1.65e-01

Pos logit contributions
 Electricity+0.479
Initialized+0.468
Shipping+0.467
+0.460
Electric+0.458
Neg logit contributions
++)-0.517
ound-0.508
show-0.481
 Stanley-0.478
ady-0.476
Token himself
Token ID2241
Feature activation-6.52e-02

Pos logit contributions
 Electricity+0.023
Shipping+0.023
Initialized+0.023
+0.022
Electric+0.022
Neg logit contributions
++)-0.036
ound-0.035
show-0.034
 Stanley-0.034
amara-0.033
Token.
Token ID13
Feature activation-3.41e-02

Pos logit contributions
 Electricity+0.100
Shipping+0.098
Initialized+0.097
+0.096
Electric+0.095
Neg logit contributions
++)-0.125
ound-0.123
show-0.116
 Stanley-0.116
amara-0.116
Token Coming
Token ID21808
Feature activation-2.51e-01

Pos logit contributions
 Electricity+0.044
Initialized+0.043
Shipping+0.043
+0.042
Electric+0.042
Neg logit contributions
++)-0.073
ound-0.072
 Stanley-0.069
show-0.069
ady-0.068
Token back
Token ID736
Feature activation-1.06e-01

Pos logit contributions
 Electricity+0.349
Initialized+0.338
Shipping+0.338
+0.331
Electric+0.329
Neg logit contributions
++)-0.517
ound-0.508
show-0.484
 Stanley-0.482
amara-0.481
Token to
Token ID284
Feature activation-3.60e-02

Pos logit contributions
 Electricity+0.154
Shipping+0.149
Initialized+0.149
+0.146
Electric+0.145
Neg logit contributions
++)-0.211
ound-0.207
show-0.197
 Stanley-0.196
amara-0.196
Token Tal
Token ID7193
Feature activation+6.17e-01

Pos logit contributions
 Electricity+0.056
Initialized+0.055
Shipping+0.055
+0.054
Electric+0.054
Neg logit contributions
++)-0.068
ound-0.066
show-0.063
amara-0.063
 Stanley-0.063
Tokenul
Token ID377
Feature activation+2.49e-01

Pos logit contributions
++)+1.143
ound+1.139
show+1.079
amara+1.062
 Stanley+1.059
Neg logit contributions
 Electricity-0.991
Initialized-0.965
Shipping-0.965
-0.949
Electric-0.934
Tokenah
Token ID993
Feature activation+1.09e-02

Pos logit contributions
++)+0.321
ound+0.312
show+0.289
 Stanley+0.286
amara+0.285
Neg logit contributions
 Electricity-0.540
Initialized-0.529
Shipping-0.529
-0.522
Electric-0.520
Token,
Token ID11
Feature activation-7.43e-03

Pos logit contributions
++)+0.019
ound+0.019
show+0.018
 Stanley+0.018
amara+0.018
Neg logit contributions
 Electricity-0.018
Shipping-0.018
Initialized-0.018
-0.018
Electric-0.017
Token he
Token ID339
Feature activation+4.97e-02

Pos logit contributions
 Electricity+0.011
Initialized+0.011
Shipping+0.011
+0.011
Electric+0.010
Neg logit contributions
++)-0.015
ound-0.014
show-0.014
 Stanley-0.014
amara-0.013
Token's
Token ID338
Feature activation-9.67e-02

Pos logit contributions
++)+0.090
ound+0.088
show+0.084
amara+0.083
 Stanley+0.083
Neg logit contributions
 Electricity-0.081
Shipping-0.079
Initialized-0.079
-0.078
Electric-0.077
Token<|endoftext|>
Token ID50256
Feature activation-1.55e-02

Pos logit contributions
++)+0.085
ound+0.083
show+0.079
 Stanley+0.079
amara+0.078
Neg logit contributions
 Electricity-0.066
Initialized-0.064
Shipping-0.064
-0.063
Electric-0.062
TokenAbstract
Token ID23839
Feature activation-4.01e-01

Pos logit contributions
 Electricity+0.023
Shipping+0.023
Initialized+0.022
+0.022
Electric+0.022
Neg logit contributions
++)-0.030
ound-0.030
 Stanley-0.028
show-0.028
amara-0.028
Token
Token ID198
Feature activation-6.50e-05

Pos logit contributions
 Electricity+0.644
Shipping+0.618
Initialized+0.615
+0.610
Electric+0.605
Neg logit contributions
++)-0.748
ound-0.730
amara-0.691
show-0.691
ady-0.686
Token
Token ID198
Feature activation+1.74e-02

Pos logit contributions
 Electricity+0.000
Initialized+0.000
Shipping+0.000
+0.000
Electric+0.000
Neg logit contributions
++)-0.000
ound-0.000
show-0.000
amara-0.000
 Stanley-0.000
TokenBackground
Token ID21756
Feature activation+1.34e-01

Pos logit contributions
++)+0.033
ound+0.033
 Stanley+0.031
show+0.031
amara+0.031
Neg logit contributions
 Electricity-0.027
Shipping-0.026
Initialized-0.026
-0.026
Electric-0.026
Token Depression
Token ID22483
Feature activation+7.34e-01

Pos logit contributions
++)+0.262
ound+0.257
show+0.244
amara+0.243
 Stanley+0.243
Neg logit contributions
 Electricity-0.201
Shipping-0.195
Initialized-0.195
-0.191
Electric-0.190
Token presents
Token ID10969
Feature activation-2.26e-01

Pos logit contributions
++)+1.329
ound+1.306
show+1.234
 Stanley+1.232
amara+1.223
Neg logit contributions
 Electricity-1.201
Initialized-1.176
Shipping-1.175
-1.152
Electric-1.149
Token a
Token ID257
Feature activation-3.92e-02

Pos logit contributions
 Electricity+0.365
Shipping+0.355
+0.351
Initialized+0.351
Electric+0.346
Neg logit contributions
++)-0.418
ound-0.404
show-0.387
 Stanley-0.381
amara-0.381
Token significant
Token ID2383
Feature activation+1.10e-01

Pos logit contributions
 Electricity+0.071
Initialized+0.069
Shipping+0.069
+0.068
Electric+0.068
Neg logit contributions
++)-0.065
ound-0.063
show-0.059
 Stanley-0.059
amara-0.059
Token burden
Token ID10538
Feature activation+3.21e-01

Pos logit contributions
++)+0.157
ound+0.152
show+0.142
amara+0.140
 Stanley+0.140
Neg logit contributions
 Electricity-0.223
Initialized-0.218
Shipping-0.218
-0.216
Electric-0.214
Token to
Token ID284
Feature activation+2.05e-02

Pos logit contributions
++)+0.589
ound+0.571
show+0.542
 Stanley+0.540
amara+0.538
Neg logit contributions
 Electricity-0.521
Shipping-0.508
Initialized-0.504
-0.499
Electric-0.493
Token kept
Token ID4030
Feature activation-1.90e-02

Pos logit contributions
++)+0.041
ound+0.041
show+0.038
amara+0.038
 Stanley+0.038
Neg logit contributions
 Electricity-0.040
Initialized-0.039
Shipping-0.039
-0.038
Electric-0.038
Token relatively
Token ID5365
Feature activation-2.67e-01

Pos logit contributions
 Electricity+0.029
Shipping+0.028
Initialized+0.028
+0.028
Electric+0.028
Neg logit contributions
++)-0.036
ound-0.036
show-0.034
 Stanley-0.034
amara-0.034
Token quiet
Token ID5897
Feature activation-2.53e-01

Pos logit contributions
 Electricity+0.446
Initialized+0.435
Shipping+0.434
+0.428
Electric+0.424
Neg logit contributions
++)-0.477
ound-0.467
show-0.442
 Stanley-0.438
amara-0.438
Token in
Token ID287
Feature activation+4.21e-02

Pos logit contributions
 Electricity+0.372
Shipping+0.362
Initialized+0.360
+0.355
Electric+0.350
Neg logit contributions
++)-0.501
ound-0.491
show-0.466
amara-0.465
 Stanley-0.464
Token the
Token ID262
Feature activation-5.02e-02

Pos logit contributions
++)+0.077
ound+0.075
show+0.071
amara+0.071
 Stanley+0.071
Neg logit contributions
 Electricity-0.068
Initialized-0.066
Shipping-0.066
-0.065
Electric-0.065
Token meantime
Token ID14324
Feature activation+6.33e-01

Pos logit contributions
 Electricity+0.094
Initialized+0.092
Shipping+0.091
+0.090
Electric+0.090
Neg logit contributions
++)-0.079
ound-0.078
show-0.073
amara-0.073
 Stanley-0.072
Token,
Token ID11
Feature activation+3.02e-03

Pos logit contributions
++)+1.176
ound+1.155
show+1.095
 Stanley+1.090
amara+1.084
Neg logit contributions
 Electricity-1.009
Initialized-0.985
Shipping-0.983
-0.965
Electric-0.960
Token because
Token ID780
Feature activation+6.32e-02

Pos logit contributions
++)+0.006
ound+0.006
show+0.005
 Stanley+0.005
amara+0.005
Neg logit contributions
 Electricity-0.005
Initialized-0.005
Shipping-0.005
-0.004
Electric-0.004
Token my
Token ID616
Feature activation+6.39e-02

Pos logit contributions
++)+0.123
ound+0.120
show+0.114
amara+0.114
 Stanley+0.114
Neg logit contributions
 Electricity-0.095
Initialized-0.093
Shipping-0.093
-0.091
Electric-0.090
Token instinct
Token ID13311
Feature activation-1.63e-01

Pos logit contributions
++)+0.104
ound+0.101
show+0.095
amara+0.094
 Stanley+0.094
Neg logit contributions
 Electricity-0.117
Initialized-0.114
Shipping-0.114
-0.113
Electric-0.112
Token,
Token ID11
Feature activation-1.21e-02

Pos logit contributions
 Electricity+0.258
Initialized+0.252
Shipping+0.250
+0.248
Electric+0.245
Neg logit contributions
++)-0.302
ound-0.297
show-0.280
amara-0.279
 Stanley-0.279
Token in
Token ID287
Feature activation+3.83e-03

Pos logit contributions
 Electricity+0.584
Shipping+0.567
Initialized+0.562
+0.558
Electric+0.554
Neg logit contributions
++)-0.590
ound-0.573
show-0.542
amara-0.539
ady-0.538
Token construction
Token ID5103
Feature activation-1.77e-01

Pos logit contributions
++)+0.007
ound+0.007
show+0.007
 Stanley+0.007
amara+0.007
Neg logit contributions
 Electricity-0.006
Shipping-0.006
Initialized-0.006
-0.006
Electric-0.006
Token or
Token ID393
Feature activation-5.89e-03

Pos logit contributions
 Electricity+0.309
Shipping+0.300
Initialized+0.298
Electric+0.294
+0.294
Neg logit contributions
++)-0.307
ound-0.298
show-0.281
amara-0.279
ady-0.278
Token manufacturing
Token ID9138
Feature activation+2.73e-02

Pos logit contributions
 Electricity+0.009
Shipping+0.008
Initialized+0.008
+0.008
Electric+0.008
Neg logit contributions
++)-0.012
ound-0.012
show-0.011
 Stanley-0.011
amara-0.011
Token,
Token ID11
Feature activation-4.40e-02

Pos logit contributions
++)+0.046
ound+0.045
show+0.043
amara+0.042
ady+0.042
Neg logit contributions
 Electricity-0.048
Shipping-0.047
Initialized-0.047
-0.046
Electric-0.046
Token etc
Token ID3503
Feature activation+7.13e-01

Pos logit contributions
 Electricity+0.074
Shipping+0.072
Initialized+0.072
+0.070
Electric+0.070
Neg logit contributions
++)-0.079
ound-0.077
show-0.073
 Stanley-0.072
amara-0.072
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
++)+1.314
ound+1.290
show+1.222
 Stanley+1.216
amara+1.212
Neg logit contributions
 Electricity-1.144
Initialized-1.116
Shipping-1.116
-1.096
Electric-1.088
Token
Token ID198
Feature activation+5.95e-02

Pos logit contributions
++)+0.265
ound+0.260
show+0.247
amara+0.246
 Stanley+0.246
Neg logit contributions
 Electricity-0.203
Shipping-0.197
Initialized-0.197
-0.193
Electric-0.192
Token
Token ID198
Feature activation+1.95e-02

Pos logit contributions
++)+0.106
ound+0.105
amara+0.099
show+0.098
 Stanley+0.098
Neg logit contributions
 Electricity-0.099
Initialized-0.096
Shipping-0.096
-0.094
Electric-0.094
TokenAs
Token ID1722
Feature activation+2.81e-02

Pos logit contributions
++)+0.041
ound+0.040
 Stanley+0.038
show+0.038
amara+0.038
Neg logit contributions
 Electricity-0.027
Shipping-0.026
Initialized-0.026
-0.025
Electric-0.025
Token we
Token ID356
Feature activation-6.26e-02

Pos logit contributions
++)+0.051
ound+0.050
show+0.047
amara+0.047
ady+0.047
Neg logit contributions
 Electricity-0.046
Initialized-0.045
Shipping-0.045
-0.044
Electric-0.044
Token
Token ID564
Feature activation+2.40e-01

Pos logit contributions
++)+0.192
ound+0.188
show+0.177
 Stanley+0.176
amara+0.176
Neg logit contributions
 Electricity-0.185
Initialized-0.181
Shipping-0.180
-0.177
Electric-0.176
Token
Token ID250
Feature activation+6.54e-02

Pos logit contributions
++)+0.416
ound+0.408
show+0.384
 Stanley+0.382
amara+0.381
Neg logit contributions
 Electricity-0.412
Shipping-0.403
Initialized-0.403
-0.396
Electric-0.393
TokenY
Token ID56
Feature activation+5.39e-02

Pos logit contributions
++)+0.119
ound+0.116
show+0.110
amara+0.109
 Stanley+0.109
Neg logit contributions
 Electricity-0.107
Initialized-0.105
Shipping-0.105
-0.103
Electric-0.102
Tokenalk
Token ID971
Feature activation+1.52e-01

Pos logit contributions
++)+0.085
ound+0.082
show+0.077
 Stanley+0.077
amara+0.077
Neg logit contributions
 Electricity-0.101
Shipping-0.099
Initialized-0.099
-0.098
Electric-0.097
Tokenut
Token ID315
Feature activation-1.12e-01

Pos logit contributions
++)+0.215
ound+0.208
show+0.194
 Stanley+0.193
amara+0.192
Neg logit contributions
 Electricity-0.309
Shipping-0.302
Initialized-0.302
-0.298
Electric-0.297
Token Tal
Token ID7193
Feature activation+6.94e-01

Pos logit contributions
 Electricity+0.189
Initialized+0.184
Shipping+0.184
+0.181
Electric+0.179
Neg logit contributions
++)-0.198
ound-0.194
show-0.183
amara-0.182
 Stanley-0.182
Tokenmud
Token ID41650
Feature activation+5.31e-02

Pos logit contributions
++)+1.179
ound+1.160
show+1.092
 Stanley+1.087
amara+1.081
Neg logit contributions
 Electricity-1.212
Shipping-1.186
Initialized-1.185
-1.166
Electric-1.158
Token Torah
Token ID33366
Feature activation+2.34e-01

Pos logit contributions
++)+0.095
ound+0.093
show+0.088
amara+0.087
 Stanley+0.087
Neg logit contributions
 Electricity-0.089
Shipping-0.086
Initialized-0.086
-0.085
Electric-0.084
Token,
Token ID11
Feature activation-8.15e-04

Pos logit contributions
++)+0.428
ound+0.419
show+0.396
amara+0.394
 Stanley+0.394
Neg logit contributions
 Electricity-0.380
Shipping-0.369
Initialized-0.369
-0.363
Electric-0.360
Token
Token ID447
Feature activation-1.22e-02

Pos logit contributions
 Electricity+0.001
Initialized+0.001
Shipping+0.001
+0.001
Electric+0.001
Neg logit contributions
++)-0.001
ound-0.001
show-0.001
 Stanley-0.001
amara-0.001
Token
Token ID251
Feature activation+5.46e-02

Pos logit contributions
 Electricity+0.020
Initialized+0.020
Shipping+0.020
+0.019
Electric+0.019
Neg logit contributions
++)-0.022
ound-0.022
show-0.020
amara-0.020
 Stanley-0.020
Token Barack
Token ID8732
Feature activation-2.18e-01

Pos logit contributions
 Electricity+0.294
Initialized+0.283
Shipping+0.282
+0.279
Electric+0.276
Neg logit contributions
++)-0.328
ound-0.323
amara-0.305
show-0.303
okia-0.302
Token Obama
Token ID2486
Feature activation-1.03e-01

Pos logit contributions
 Electricity+0.431
Shipping+0.420
Initialized+0.419
+0.416
Electric+0.412
Neg logit contributions
++)-0.319
ound-0.313
amara-0.288
show-0.287
ady-0.286
Token,
Token ID11
Feature activation+2.31e-02

Pos logit contributions
 Electricity+0.179
Shipping+0.175
Initialized+0.173
+0.172
Electric+0.170
Neg logit contributions
++)-0.176
ound-0.174
show-0.162
amara-0.162
 Stanley-0.161
Token they
Token ID484
Feature activation+1.29e-02

Pos logit contributions
++)+0.046
ound+0.046
show+0.043
amara+0.043
ady+0.043
Neg logit contributions
 Electricity-0.034
Shipping-0.032
Initialized-0.032
-0.032
Electric-0.032
Token in
Token ID287
Feature activation+1.05e-02

Pos logit contributions
++)+0.022
ound+0.021
amara+0.020
show+0.020
 Stanley+0.020
Neg logit contributions
 Electricity-0.022
Shipping-0.022
Initialized-0.022
-0.022
Electric-0.021
Token­
Token ID3907
Feature activation+5.56e-01

Pos logit contributions
++)+0.010
ound+0.010
amara+0.009
okia+0.009
 Stanley+0.009
Neg logit contributions
 Electricity-0.026
Initialized-0.025
Shipping-0.025
-0.025
Electric-0.025
Tokenv
Token ID85
Feature activation-9.47e-02

Pos logit contributions
++)+0.927
ound+0.909
show+0.857
 Stanley+0.849
amara+0.847
Neg logit contributions
 Electricity-0.994
Initialized-0.972
Shipping-0.972
-0.956
Electric-0.949
Tokenoke
Token ID2088
Feature activation-1.14e-01

Pos logit contributions
 Electricity+0.165
Initialized+0.164
Shipping+0.162
Electric+0.160
+0.159
Neg logit contributions
++)-0.157
ound-0.152
 Stanley-0.146
amara-0.145
show-0.145
Token him
Token ID683
Feature activation-2.07e-02

Pos logit contributions
 Electricity+0.183
Initialized+0.178
Shipping+0.177
+0.176
Electric+0.174
Neg logit contributions
++)-0.209
ound-0.204
amara-0.193
show-0.193
ady-0.191
Token.
Token ID13
Feature activation+3.74e-02

Pos logit contributions
 Electricity+0.033
Shipping+0.032
Initialized+0.032
+0.031
Electric+0.031
Neg logit contributions
++)-0.039
ound-0.038
show-0.036
amara-0.036
 Stanley-0.036
Token
Token ID564
Feature activation+5.27e-02

Pos logit contributions
++)+0.076
ound+0.075
show+0.071
amara+0.071
ady+0.071
Neg logit contributions
 Electricity-0.053
Shipping-0.051
Initialized-0.051
-0.050
Electric-0.050
Token always
Token ID1464
Feature activation+2.80e-01

Pos logit contributions
++)+0.283
ound+0.277
show+0.261
 Stanley+0.260
amara+0.260
Neg logit contributions
 Electricity-0.268
Initialized-0.261
Shipping-0.261
-0.257
Electric-0.255
Token be
Token ID307
Feature activation+1.14e-01

Pos logit contributions
++)+0.475
ound+0.465
show+0.438
 Stanley+0.437
amara+0.435
Neg logit contributions
 Electricity-0.492
Initialized-0.480
Shipping-0.480
-0.473
Electric-0.469
Token the
Token ID262
Feature activation+1.22e-01

Pos logit contributions
++)+0.196
ound+0.192
show+0.181
amara+0.179
 Stanley+0.179
Neg logit contributions
 Electricity-0.195
Shipping-0.191
Initialized-0.190
-0.188
Electric-0.186
Token price
Token ID2756
Feature activation+2.80e-02

Pos logit contributions
++)+0.226
ound+0.222
show+0.210
 Stanley+0.209
amara+0.208
Neg logit contributions
 Electricity-0.194
Shipping-0.189
Initialized-0.189
-0.186
Electric-0.184
Token of
Token ID286
Feature activation+1.31e-01

Pos logit contributions
++)+0.051
ound+0.049
show+0.047
amara+0.046
ady+0.046
Neg logit contributions
 Electricity-0.046
Shipping-0.045
Initialized-0.044
-0.044
Electric-0.044
Token inflation
Token ID10610
Feature activation+3.23e-01

Pos logit contributions
++)+0.222
ound+0.217
show+0.204
amara+0.202
 Stanley+0.202
Neg logit contributions
 Electricity-0.230
Initialized-0.224
Shipping-0.224
-0.221
Electric-0.219
Token."
Token ID526
Feature activation-1.45e-02

Pos logit contributions
++)+0.614
ound+0.605
show+0.573
 Stanley+0.571
amara+0.568
Neg logit contributions
 Electricity-0.499
Initialized-0.487
Shipping-0.487
-0.477
Electric-0.475
TokenHe
Token ID1544
Feature activation+1.26e-01

Pos logit contributions
 Electricity+0.020
Shipping+0.020
Initialized+0.020
+0.019
Electric+0.019
Neg logit contributions
++)-0.029
ound-0.029
show-0.028
 Stanley-0.027
amara-0.027
Token correctly
Token ID9380
Feature activation-1.68e-01

Pos logit contributions
++)+0.232
ound+0.228
show+0.216
 Stanley+0.215
ady+0.215
Neg logit contributions
 Electricity-0.203
Initialized-0.198
Shipping-0.197
-0.194
Electric-0.193
Token predicted
Token ID11001
Feature activation-1.10e-01

Pos logit contributions
 Electricity+0.297
Shipping+0.290
Initialized+0.290
+0.285
Electric+0.283
Neg logit contributions
++)-0.282
ound-0.277
show-0.260
 Stanley-0.258
amara-0.258
Token the
Token ID262
Feature activation+1.47e-01

Pos logit contributions
 Electricity+0.150
Shipping+0.145
Initialized+0.145
+0.142
Electric+0.141
Neg logit contributions
++)-0.230
ound-0.224
show-0.214
amara-0.214
ady-0.212
TokenThe
Token ID464
Feature activation+1.41e-01

Pos logit contributions
++)+0.151
ound+0.149
show+0.141
 Stanley+0.141
amara+0.140
Neg logit contributions
 Electricity-0.117
Shipping-0.115
Initialized-0.115
-0.113
Electric-0.112
Token integrated
Token ID11521
Feature activation-8.88e-02

Pos logit contributions
++)+0.245
ound+0.240
show+0.227
 Stanley+0.226
amara+0.225
Neg logit contributions
 Electricity-0.242
Initialized-0.236
Shipping-0.236
-0.232
Electric-0.231
Token Lean
Token ID45661
Feature activation-4.58e-02

Pos logit contributions
 Electricity+0.135
Shipping+0.131
Initialized+0.131
+0.128
Electric+0.127
Neg logit contributions
++)-0.172
ound-0.169
show-0.161
amara-0.159
 Stanley-0.159
Token Six
Token ID9699
Feature activation-1.94e-02

Pos logit contributions
 Electricity+0.069
Shipping+0.068
Initialized+0.068
+0.066
Electric+0.066
Neg logit contributions
++)-0.089
ound-0.087
show-0.083
 Stanley-0.082
amara-0.082
Token Sigma
Token ID31669
Feature activation+2.44e-01

Pos logit contributions
 Electricity+0.046
Shipping+0.045
Initialized+0.045
+0.044
Electric+0.044
Neg logit contributions
++)-0.021
ound-0.021
show-0.019
amara-0.019
 Stanley-0.018
Token management
Token ID4542
Feature activation+2.14e-01

Pos logit contributions
++)+0.468
ound+0.460
show+0.436
 Stanley+0.435
amara+0.433
Neg logit contributions
 Electricity-0.374
Initialized-0.364
Shipping-0.364
-0.357
Electric-0.355
Token approach
Token ID3164
Feature activation-1.74e-01

Pos logit contributions
++)+0.458
ound+0.450
show+0.430
 Stanley+0.428
amara+0.427
Neg logit contributions
 Electricity-0.282
Shipping-0.273
Initialized-0.273
-0.267
Electric-0.265
Token is
Token ID318
Feature activation+1.71e-01

Pos logit contributions
 Electricity+0.274
Shipping+0.266
Initialized+0.266
+0.261
Electric+0.259
Neg logit contributions
++)-0.328
ound-0.322
show-0.306
amara-0.304
 Stanley-0.304
Token being
Token ID852
Feature activation+1.42e-01

Pos logit contributions
++)+0.317
ound+0.310
show+0.294
 Stanley+0.293
amara+0.292
Neg logit contributions
 Electricity-0.274
Shipping-0.267
Initialized-0.266
-0.262
Electric-0.260
Token used
Token ID973
Feature activation-4.68e-03

Pos logit contributions
++)+0.262
ound+0.256
show+0.243
 Stanley+0.242
amara+0.241
Neg logit contributions
 Electricity-0.228
Shipping-0.222
Initialized-0.222
-0.218
Electric-0.216
Token across
Token ID1973
Feature activation+7.26e-02

Pos logit contributions
 Electricity+0.007
Shipping+0.007
Initialized+0.007
+0.007
Electric+0.007
Neg logit contributions
++)-0.009
ound-0.009
show-0.008
 Stanley-0.008
amara-0.008
Token
Token ID447
Feature activation+8.44e-02

Pos logit contributions
 Electricity+0.081
Shipping+0.078
Initialized+0.078
+0.077
Electric+0.077
Neg logit contributions
++)-0.095
ound-0.093
show-0.088
amara-0.088
ady-0.087
Token
Token ID247
Feature activation+5.12e-03

Pos logit contributions
++)+0.128
ound+0.125
show+0.117
 Stanley+0.116
amara+0.116
Neg logit contributions
 Electricity-0.164
Initialized-0.160
Shipping-0.160
-0.158
Electric-0.157
Tokens
Token ID82
Feature activation+1.35e-01

Pos logit contributions
++)+0.009
ound+0.009
amara+0.008
show+0.008
 Stanley+0.008
Neg logit contributions
 Electricity-0.009
Shipping-0.009
Initialized-0.009
-0.009
Electric-0.009
Token
Token ID564
Feature activation+8.37e-02

Pos logit contributions
++)+0.234
ound+0.230
show+0.217
amara+0.216
 Stanley+0.215
Neg logit contributions
 Electricity-0.232
Initialized-0.225
Shipping-0.225
-0.222
Electric-0.221
Token
Token ID250
Feature activation-8.33e-02

Pos logit contributions
++)+0.138
ound+0.135
show+0.127
amara+0.126
 Stanley+0.125
Neg logit contributions
 Electricity-0.151
Initialized-0.148
Shipping-0.148
-0.146
Electric-0.144
TokenR
Token ID49
Feature activation+1.77e-01

Pos logit contributions
 Electricity+0.141
Shipping+0.137
Initialized+0.137
+0.136
Electric+0.135
Neg logit contributions
++)-0.146
ound-0.143
show-0.135
amara-0.135
 Stanley-0.134
Tokenhaps
Token ID2772
Feature activation+6.09e-01

Pos logit contributions
++)+0.297
ound+0.290
show+0.275
 Stanley+0.273
amara+0.272
Neg logit contributions
 Electricity-0.310
Shipping-0.303
Initialized-0.302
-0.298
Electric-0.297
Tokenody
Token ID1118
Feature activation-1.64e-02

Pos logit contributions
++)+0.339
ound+0.317
show+0.262
 Stanley+0.256
amara+0.254
Neg logit contributions
 Electricity-1.761
Shipping-1.734
Initialized-1.732
-1.716
Electric-1.712
Token In
Token ID554
Feature activation-1.44e-01

Pos logit contributions
 Electricity+0.026
Initialized+0.025
Shipping+0.025
+0.024
Electric+0.024
Neg logit contributions
++)-0.031
ound-0.030
show-0.029
amara-0.029
ady-0.029
Token Blue
Token ID4518
Feature activation+3.12e-02

Pos logit contributions
 Electricity+0.245
Electric+0.229
Shipping+0.225
Initialized+0.223
+0.222
Neg logit contributions
++)-0.262
ound-0.255
amara-0.243
show-0.242
ourke-0.238
Token
Token ID447
Feature activation-2.68e-02

Pos logit contributions
++)+0.057
ound+0.056
show+0.053
amara+0.053
 Stanley+0.053
Neg logit contributions
 Electricity-0.050
Shipping-0.049
Initialized-0.049
-0.048
Electric-0.048
Token reserves
Token ID14072
Feature activation+3.44e-03

Pos logit contributions
 Electricity+0.140
Shipping+0.136
Initialized+0.136
+0.133
Electric+0.133
Neg logit contributions
++)-0.175
ound-0.172
show-0.163
amara-0.162
 Stanley-0.162
Token its
Token ID663
Feature activation-1.52e-02

Pos logit contributions
++)+0.006
ound+0.006
show+0.006
amara+0.006
ourke+0.006
Neg logit contributions
 Electricity-0.006
Shipping-0.006
Initialized-0.005
Electric-0.005
-0.005
Token toughest
Token ID28212
Feature activation+5.02e-02

Pos logit contributions
 Electricity+0.025
Initialized+0.024
Shipping+0.024
+0.024
Electric+0.024
Neg logit contributions
++)-0.027
ound-0.027
show-0.025
 Stanley-0.025
amara-0.025
Token penalties
Token ID12970
Feature activation+1.18e-01

Pos logit contributions
++)+0.096
ound+0.095
amara+0.090
show+0.089
ourke+0.088
Neg logit contributions
 Electricity-0.077
Shipping-0.075
Initialized-0.074
Electric-0.073
-0.073
Token for
Token ID329
Feature activation+4.90e-02

Pos logit contributions
++)+0.243
ound+0.239
show+0.227
 Stanley+0.226
amara+0.226
Neg logit contributions
 Electricity-0.165
Shipping-0.160
Initialized-0.160
-0.157
Electric-0.156
Token those
Token ID883
Feature activation+1.51e-01

Pos logit contributions
++)+0.084
ound+0.082
show+0.077
 Stanley+0.077
ady+0.077
Neg logit contributions
 Electricity-0.085
Initialized-0.084
Shipping-0.084
-0.082
Electric-0.081
Token who
Token ID508
Feature activation+7.56e-02

Pos logit contributions
++)+0.269
ound+0.264
show+0.249
 Stanley+0.248
amara+0.247
Neg logit contributions
 Electricity-0.253
Initialized-0.247
Shipping-0.247
-0.242
Electric-0.241
Token "
Token ID366
Feature activation-1.11e-01

Pos logit contributions
++)+0.133
ound+0.131
show+0.123
 Stanley+0.123
amara+0.122
Neg logit contributions
 Electricity-0.128
Initialized-0.125
Shipping-0.125
-0.123
Electric-0.122
Tokendef
Token ID4299
Feature activation+6.88e-02

Pos logit contributions
 Electricity+0.203
Shipping+0.200
Initialized+0.200
+0.197
Electric+0.196
Neg logit contributions
++)-0.179
ound-0.175
 Stanley-0.165
amara-0.163
show-0.162
Tokenraud
Token ID22863
Feature activation+4.29e-02

Pos logit contributions
++)+0.092
ound+0.089
show+0.083
 Stanley+0.082
amara+0.082
Neg logit contributions
 Electricity-0.146
Initialized-0.143
Shipping-0.143
-0.141
Electric-0.141
Token or
Token ID393
Feature activation-1.46e-02

Pos logit contributions
++)+0.076
ound+0.074
show+0.070
 Stanley+0.070
amara+0.070
Neg logit contributions
 Electricity-0.072
Shipping-0.070
Initialized-0.070
-0.069
Electric-0.069
Token.
Token ID13
Feature activation-4.52e-02

Pos logit contributions
 Electricity+0.149
Shipping+0.145
Initialized+0.145
+0.142
Electric+0.141
Neg logit contributions
++)-0.176
ound-0.173
show-0.164
 Stanley-0.163
amara-0.163
Token Her
Token ID2332
Feature activation-1.85e-01

Pos logit contributions
 Electricity+0.063
Initialized+0.062
Shipping+0.062
+0.061
Electric+0.060
Neg logit contributions
++)-0.092
ound-0.090
 Stanley-0.086
show-0.086
amara-0.085
Token body
Token ID1767
Feature activation+2.83e-01

Pos logit contributions
 Electricity+0.340
Initialized+0.331
Shipping+0.331
+0.326
Electric+0.325
Neg logit contributions
++)-0.301
ound-0.294
show-0.277
amara-0.275
 Stanley-0.274
Token was
Token ID373
Feature activation+5.76e-02

Pos logit contributions
++)+0.512
ound+0.501
show+0.474
 Stanley+0.472
amara+0.470
Neg logit contributions
 Electricity-0.464
Shipping-0.454
Initialized-0.454
-0.445
Electric-0.443
Token still
Token ID991
Feature activation-1.42e-02

Pos logit contributions
++)+0.107
ound+0.105
show+0.100
 Stanley+0.100
amara+0.099
Neg logit contributions
 Electricity-0.091
Initialized-0.089
Shipping-0.089
-0.087
Electric-0.087
Token strong
Token ID1913
Feature activation+5.34e-02

Pos logit contributions
 Electricity+0.023
Initialized+0.022
Shipping+0.022
+0.022
Electric+0.022
Neg logit contributions
++)-0.026
ound-0.026
show-0.024
 Stanley-0.024
amara-0.024
Token enough
Token ID1576
Feature activation-3.47e-02

Pos logit contributions
++)+0.109
ound+0.107
show+0.102
 Stanley+0.102
amara+0.101
Neg logit contributions
 Electricity-0.075
Initialized-0.073
Shipping-0.073
-0.072
Electric-0.071
Token to
Token ID284
Feature activation-3.39e-03

Pos logit contributions
 Electricity+0.053
Initialized+0.051
Shipping+0.051
+0.050
Electric+0.050
Neg logit contributions
++)-0.067
ound-0.066
show-0.063
 Stanley-0.063
ady-0.062
Token fight
Token ID1907
Feature activation+1.18e-01

Pos logit contributions
 Electricity+0.005
Initialized+0.005
Shipping+0.005
+0.005
Electric+0.005
Neg logit contributions
++)-0.006
ound-0.006
show-0.006
 Stanley-0.006
ady-0.006
Token the
Token ID262
Feature activation-1.35e-02

Pos logit contributions
++)+0.226
ound+0.222
 Stanley+0.211
show+0.210
ady+0.208
Neg logit contributions
 Electricity-0.180
Initialized-0.177
Shipping-0.177
-0.174
Electric-0.172
Token illness
Token ID8526
Feature activation-5.43e-02

Pos logit contributions
 Electricity+0.021
Initialized+0.021
Shipping+0.021
+0.021
Electric+0.020
Neg logit contributions
++)-0.025
ound-0.025
show-0.023
 Stanley-0.023
amara-0.023
Token lawyers
Token ID9326
Feature activation-1.07e-01

Pos logit contributions
++)+0.619
ound+0.608
show+0.574
 Stanley+0.573
amara+0.570
Neg logit contributions
 Electricity-0.577
Initialized-0.564
Shipping-0.564
-0.555
Electric-0.551
Token in
Token ID287
Feature activation-4.20e-02

Pos logit contributions
 Electricity+0.160
Initialized+0.156
Shipping+0.155
+0.152
Electric+0.151
Neg logit contributions
++)-0.210
ound-0.206
show-0.196
 Stanley-0.195
amara-0.194
Token the
Token ID262
Feature activation-2.44e-02

Pos logit contributions
 Electricity+0.078
Initialized+0.076
Shipping+0.075
+0.075
Electric+0.074
Neg logit contributions
++)-0.068
ound-0.066
show-0.062
amara-0.062
 Stanley-0.061
Token Ecuador
Token ID25794
Feature activation-4.33e-01

Pos logit contributions
 Electricity+0.035
Initialized+0.034
Shipping+0.034
+0.033
Electric+0.033
Neg logit contributions
++)-0.050
ound-0.049
show-0.046
amara-0.046
 Stanley-0.046
Tokenian
Token ID666
Feature activation-1.35e-01

Pos logit contributions
 Electricity+0.935
Shipping+0.916
Initialized+0.916
+0.904
Electric+0.899
Neg logit contributions
++)-0.561
ound-0.546
show-0.504
 Stanley-0.501
amara-0.499
Token capital
Token ID3139
Feature activation-4.29e-01

Pos logit contributions
 Electricity+0.207
Shipping+0.200
Initialized+0.200
+0.197
Electric+0.195
Neg logit contributions
++)-0.260
ound-0.255
show-0.242
amara-0.241
 Stanley-0.241
Token Qu
Token ID2264
Feature activation+3.91e-01

Pos logit contributions
 Electricity+0.661
Shipping+0.639
Initialized+0.634
+0.627
Electric+0.620
Neg logit contributions
++)-0.826
ound-0.809
show-0.763
amara-0.761
ady-0.754
Tokenito
Token ID10094
Feature activation+4.70e-02

Pos logit contributions
++)+0.549
ound+0.527
 Stanley+0.491
show+0.486
cum+0.478
Neg logit contributions
 Electricity-0.800
Shipping-0.781
Initialized-0.770
Electric-0.770
_-_-0.766
Token to
Token ID284
Feature activation+1.02e-02

Pos logit contributions
++)+0.093
ound+0.091
show+0.086
 Stanley+0.086
amara+0.086
Neg logit contributions
 Electricity-0.070
Shipping-0.068
Initialized-0.068
-0.066
Electric-0.066
Token fight
Token ID1907
Feature activation+1.97e-01

Pos logit contributions
++)+0.018
ound+0.017
show+0.016
 Stanley+0.016
ady+0.016
Neg logit contributions
 Electricity-0.018
Initialized-0.017
Shipping-0.017
-0.017
Electric-0.017
Token his
Token ID465
Feature activation+5.50e-02

Pos logit contributions
++)+0.367
ound+0.362
 Stanley+0.344
show+0.343
ady+0.340
Neg logit contributions
 Electricity-0.307
Shipping-0.303
Initialized-0.301
-0.297
Electric-0.295
Token what
Token ID644
Feature activation-7.62e-02

Pos logit contributions
++)+0.136
ound+0.134
show+0.127
 Stanley+0.127
amara+0.126
Neg logit contributions
 Electricity-0.109
Shipping-0.106
Initialized-0.106
-0.104
Electric-0.104
Token usually
Token ID3221
Feature activation-2.47e-01

Pos logit contributions
 Electricity+0.113
Initialized+0.110
Shipping+0.109
+0.108
Electric+0.107
Neg logit contributions
++)-0.150
ound-0.147
show-0.140
amara-0.139
 Stanley-0.139
Token happens
Token ID4325
Feature activation+1.22e-01

Pos logit contributions
 Electricity+0.357
Shipping+0.347
Initialized+0.347
+0.340
Electric+0.337
Neg logit contributions
++)-0.497
ound-0.488
show-0.465
 Stanley-0.463
amara-0.461
Token at
Token ID379
Feature activation+4.51e-02

Pos logit contributions
++)+0.234
ound+0.230
show+0.219
 Stanley+0.219
amara+0.217
Neg logit contributions
 Electricity-0.185
Initialized-0.181
Shipping-0.181
-0.177
Electric-0.176
Token an
Token ID281
Feature activation+1.09e-01

Pos logit contributions
++)+0.077
ound+0.075
amara+0.071
show+0.070
ady+0.070
Neg logit contributions
 Electricity-0.079
Initialized-0.077
Shipping-0.076
-0.076
Electric-0.075
Token event
Token ID1785
Feature activation-8.40e-02

Pos logit contributions
++)+0.183
ound+0.179
show+0.168
 Stanley+0.167
amara+0.167
Neg logit contributions
 Electricity-0.195
Initialized-0.191
Shipping-0.190
-0.187
Electric-0.186
Token filled
Token ID5901
Feature activation+4.60e-02

Pos logit contributions
 Electricity+0.131
Shipping+0.127
Initialized+0.127
+0.125
Electric+0.124
Neg logit contributions
++)-0.159
ound-0.157
show-0.149
 Stanley-0.148
amara-0.147
Token with
Token ID351
Feature activation+4.28e-02

Pos logit contributions
++)+0.091
ound+0.089
show+0.084
 Stanley+0.084
amara+0.084
Neg logit contributions
 Electricity-0.068
Shipping-0.066
Initialized-0.066
-0.065
Electric-0.065
Token Tor
Token ID4022
Feature activation+2.44e-01

Pos logit contributions
++)+0.072
ound+0.070
show+0.066
amara+0.066
 Stanley+0.066
Neg logit contributions
 Electricity-0.076
Initialized-0.074
Shipping-0.074
-0.073
Electric-0.072
Tokenont
Token ID756
Feature activation-3.50e-01

Pos logit contributions
++)+0.377
ound+0.367
show+0.343
amara+0.342
 Stanley+0.341
Neg logit contributions
 Electricity-0.463
Initialized-0.454
Shipping-0.454
-0.448
Electric-0.444
Tokenon
Token ID261
Feature activation-1.61e-01

Pos logit contributions
 Electricity+0.768
Initialized+0.758
Shipping+0.757
+0.744
Electric+0.742
Neg logit contributions
++)-0.434
ound-0.419
show-0.386
 Stanley-0.383
amara-0.383
TokenAs
Token ID1722
Feature activation-4.88e-02

Pos logit contributions
 Electricity+0.059
Shipping+0.058
Initialized+0.058
+0.057
Electric+0.056
Neg logit contributions
++)-0.083
ound-0.082
show-0.077
 Stanley-0.077
amara-0.077
Token with
Token ID351
Feature activation-6.32e-02

Pos logit contributions
 Electricity+0.078
Initialized+0.076
Shipping+0.076
+0.075
Electric+0.074
Neg logit contributions
++)-0.090
ound-0.088
show-0.084
 Stanley-0.083
amara-0.083
Token many
Token ID867
Feature activation+1.32e-02

Pos logit contributions
 Electricity+0.103
Shipping+0.100
Initialized+0.100
+0.098
Electric+0.097
Neg logit contributions
++)-0.116
ound-0.113
show-0.107
amara-0.107
 Stanley-0.106
Token things
Token ID1243
Feature activation-1.67e-01

Pos logit contributions
++)+0.023
ound+0.023
show+0.021
amara+0.021
ady+0.021
Neg logit contributions
 Electricity-0.022
Initialized-0.022
Shipping-0.022
-0.021
Electric-0.021
Token Trump
Token ID1301
Feature activation-6.66e-02

Pos logit contributions
 Electricity+0.258
Shipping+0.251
Initialized+0.250
+0.246
Electric+0.244
Neg logit contributions
++)-0.321
ound-0.313
show-0.297
amara-0.295
 Stanley-0.294
Token,
Token ID11
Feature activation-1.07e-01

Pos logit contributions
 Electricity+0.096
Shipping+0.093
Initialized+0.093
+0.091
Electric+0.091
Neg logit contributions
++)-0.134
ound-0.132
show-0.125
 Stanley-0.125
amara-0.124
Token talk
Token ID1561
Feature activation-1.02e-01

Pos logit contributions
 Electricity+0.167
Shipping+0.162
Initialized+0.162
+0.159
Electric+0.158
Neg logit contributions
++)-0.202
ound-0.198
show-0.188
 Stanley-0.187
amara-0.186
Token of
Token ID286
Feature activation-1.76e-02

Pos logit contributions
 Electricity+0.161
Initialized+0.157
Shipping+0.157
+0.154
Electric+0.153
Neg logit contributions
++)-0.190
ound-0.186
show-0.176
 Stanley-0.175
amara-0.175
Token his
Token ID465
Feature activation-8.62e-03

Pos logit contributions
 Electricity+0.029
Shipping+0.029
Initialized+0.029
+0.028
Electric+0.028
Neg logit contributions
++)-0.031
ound-0.031
show-0.029
 Stanley-0.029
amara-0.029
Token competence
Token ID31450
Feature activation-6.02e-01

Pos logit contributions
 Electricity+0.015
Shipping+0.015
Initialized+0.015
+0.014
Electric+0.014
Neg logit contributions
++)-0.015
ound-0.014
show-0.014
amara-0.014
 Stanley-0.013
Token looks
Token ID3073
Feature activation+7.52e-02

Pos logit contributions
 Electricity+0.931
Shipping+0.906
Initialized+0.902
+0.893
Electric+0.875
Neg logit contributions
++)-1.135
ound-1.113
show-1.054
amara-1.053
 Stanley-1.048
Token been
Token ID587
Feature activation+1.62e-01

Pos logit contributions
++)+0.100
ound+0.097
show+0.092
amara+0.092
 Stanley+0.092
Neg logit contributions
 Electricity-0.094
Shipping-0.091
Initialized-0.091
-0.090
Electric-0.089
Token encouraging
Token ID12577
Feature activation-6.60e-02

Pos logit contributions
++)+0.278
ound+0.272
show+0.257
 Stanley+0.256
amara+0.255
Neg logit contributions
 Electricity-0.280
Initialized-0.273
Shipping-0.273
-0.269
Electric-0.267
Token.
Token ID13
Feature activation+2.84e-02

Pos logit contributions
 Electricity+0.121
Initialized+0.119
Shipping+0.118
+0.117
Electric+0.116
Neg logit contributions
++)-0.106
ound-0.103
show-0.097
amara-0.097
ady-0.096
Token
Token ID198
Feature activation+8.11e-02

Pos logit contributions
++)+0.055
ound+0.054
show+0.051
 Stanley+0.051
amara+0.051
Neg logit contributions
 Electricity-0.043
Initialized-0.042
Shipping-0.042
-0.041
Electric-0.041
Token
Token ID198
Feature activation+6.85e-02

Pos logit contributions
++)+0.143
ound+0.141
show+0.133
 Stanley+0.132
amara+0.132
Neg logit contributions
 Electricity-0.136
Initialized-0.133
Shipping-0.133
-0.131
Electric-0.130
TokenSy
Token ID13940
Feature activation-1.29e-01

Pos logit contributions
++)+0.140
ound+0.138
show+0.132
 Stanley+0.131
ady+0.130
Neg logit contributions
 Electricity-0.096
Initialized-0.093
Shipping-0.093
-0.091
Electric-0.090
Tokenfy
Token ID24928
Feature activation-3.23e-01

Pos logit contributions
 Electricity+0.148
Shipping+0.143
Initialized+0.143
+0.140
Electric+0.138
Neg logit contributions
++)-0.298
ound-0.293
show-0.281
 Stanley-0.281
amara-0.280
Token
Token ID447
Feature activation+4.59e-02

Pos logit contributions
 Electricity+0.505
Initialized+0.491
Shipping+0.491
+0.483
Electric+0.478
Neg logit contributions
++)-0.612
ound-0.600
show-0.568
amara-0.566
 Stanley-0.566
Token
Token ID247
Feature activation+7.79e-02

Pos logit contributions
++)+0.069
ound+0.067
show+0.063
 Stanley+0.063
amara+0.062
Neg logit contributions
 Electricity-0.089
Initialized-0.087
Shipping-0.087
-0.086
Electric-0.086
Tokens
Token ID82
Feature activation+4.00e-03

Pos logit contributions
++)+0.129
ound+0.126
show+0.119
 Stanley+0.118
amara+0.118
Neg logit contributions
 Electricity-0.140
Initialized-0.137
Shipping-0.137
-0.134
Electric-0.134
Token return
Token ID1441
Feature activation+5.33e-01

Pos logit contributions
++)+0.007
ound+0.007
show+0.006
 Stanley+0.006
amara+0.006
Neg logit contributions
 Electricity-0.007
Shipping-0.007
Initialized-0.007
-0.007
Electric-0.007
Tokengeneration
Token ID20158
Feature activation-1.39e-01

Pos logit contributions
 Electricity+0.181
Shipping+0.178
Initialized+0.177
Electric+0.175
+0.173
Neg logit contributions
++)-0.154
ound-0.150
 Stanley-0.141
amara-0.141
ourke-0.139
Token 3
Token ID513
Feature activation-1.07e-01

Pos logit contributions
 Electricity+0.238
Shipping+0.230
Initialized+0.230
Electric+0.226
+0.225
Neg logit contributions
++)-0.245
ound-0.240
show-0.227
amara-0.226
 Stanley-0.223
Token.
Token ID13
Feature activation+2.17e-02

Pos logit contributions
 Electricity+0.164
Shipping+0.160
Initialized+0.160
+0.157
Electric+0.156
Neg logit contributions
++)-0.206
ound-0.202
show-0.192
 Stanley-0.191
amara-0.190
Token5
Token ID20
Feature activation-1.68e-01

Pos logit contributions
++)+0.044
ound+0.043
show+0.041
 Stanley+0.041
amara+0.040
Neg logit contributions
 Electricity-0.031
Initialized-0.030
Shipping-0.030
-0.030
Electric-0.030
Token-
Token ID12
Feature activation-1.09e-01

Pos logit contributions
 Electricity+0.317
Shipping+0.309
Initialized+0.308
Electric+0.304
+0.302
Neg logit contributions
++)-0.263
ound-0.256
show-0.241
amara-0.240
ady-0.239
Tokenliter
Token ID17201
Feature activation-4.77e-01

Pos logit contributions
 Electricity+0.185
Initialized+0.181
Shipping+0.181
+0.178
Electric+0.177
Neg logit contributions
++)-0.189
ound-0.186
show-0.175
 Stanley-0.175
amara-0.174
Token Eco
Token ID38719
Feature activation-3.11e-01

Pos logit contributions
 Electricity+0.802
Initialized+0.774
Shipping+0.773
Electric+0.765
+0.760
Neg logit contributions
++)-0.843
ound-0.829
show-0.784
amara-0.780
okia-0.770
TokenBoost
Token ID45686
Feature activation-3.50e-01

Pos logit contributions
 Electricity+0.589
Shipping+0.578
Initialized+0.578
+0.568
Electric+0.568
Neg logit contributions
++)-0.480
ound-0.470
show-0.441
 Stanley-0.439
amara-0.438
Token proved
Token ID8302
Feature activation+2.19e-02

Pos logit contributions
 Electricity+0.612
Shipping+0.591
Initialized+0.590
Electric+0.585
+0.580
Neg logit contributions
++)-0.595
ound-0.586
show-0.555
amara-0.552
 Stanley-0.547
Token its
Token ID663
Feature activation-4.84e-02

Pos logit contributions
++)+0.041
ound+0.040
show+0.038
 Stanley+0.038
amara+0.038
Neg logit contributions
 Electricity-0.035
Shipping-0.034
Initialized-0.034
-0.033
Electric-0.033
Token met
Token ID1138
Feature activation-2.82e-01

Pos logit contributions
 Electricity+0.079
Initialized+0.077
Shipping+0.077
+0.076
Electric+0.075
Neg logit contributions
++)-0.088
ound-0.086
show-0.082
 Stanley-0.081
amara-0.081
Token the
Token ID262
Feature activation-5.47e-02

Pos logit contributions
 Electricity+0.016
Initialized+0.015
Shipping+0.015
+0.015
Electric+0.015
Neg logit contributions
++)-0.019
ound-0.019
show-0.018
 Stanley-0.018
amara-0.018
Token same
Token ID976
Feature activation-2.78e-01

Pos logit contributions
 Electricity+0.094
Initialized+0.092
Shipping+0.092
+0.091
Electric+0.090
Neg logit contributions
++)-0.094
ound-0.092
show-0.087
 Stanley-0.087
ady-0.086
Token with
Token ID351
Feature activation-5.66e-02

Pos logit contributions
 Electricity+0.433
Initialized+0.423
Shipping+0.422
+0.414
Electric+0.412
Neg logit contributions
++)-0.525
ound-0.515
show-0.489
 Stanley-0.487
amara-0.484
Token a
Token ID257
Feature activation-6.81e-02

Pos logit contributions
 Electricity+0.066
Shipping+0.064
Initialized+0.064
+0.062
Electric+0.062
Neg logit contributions
++)-0.129
ound-0.127
show-0.122
 Stanley-0.121
amara-0.121
Token Trap
Token ID21914
Feature activation-5.19e-01

Pos logit contributions
 Electricity+0.092
Initialized+0.089
Shipping+0.089
+0.087
Electric+0.087
Neg logit contributions
++)-0.143
ound-0.141
show-0.134
 Stanley-0.134
amara-0.133
Token Card
Token ID5172
Feature activation-5.42e-01

Pos logit contributions
 Electricity+0.832
Shipping+0.809
Initialized+0.807
+0.795
Electric+0.791
Neg logit contributions
++)-0.957
ound-0.939
show-0.890
 Stanley-0.887
amara-0.886
Token!
Token ID0
Feature activation+1.19e-01

Pos logit contributions
 Electricity+0.834
Initialized+0.812
Shipping+0.812
+0.797
Electric+0.791
Neg logit contributions
++)-1.036
ound-1.018
show-0.966
 Stanley-0.962
amara-0.958
Token The
Token ID383
Feature activation-1.04e-01

Pos logit contributions
++)+0.238
ound+0.234
 Stanley+0.224
show+0.224
ady+0.220
Neg logit contributions
 Electricity-0.171
Initialized-0.169
Shipping-0.168
-0.166
Electric-0.164
Token best
Token ID1266
Feature activation-6.26e-02

Pos logit contributions
 Electricity+0.167
Initialized+0.164
Shipping+0.164
+0.161
Electric+0.160
Neg logit contributions
++)-0.189
ound-0.186
show-0.176
 Stanley-0.176
ady-0.174
Token part
Token ID636
Feature activation-1.32e-01

Pos logit contributions
 Electricity+0.109
Initialized+0.107
Shipping+0.107
+0.105
Electric+0.105
Neg logit contributions
++)-0.107
ound-0.104
show-0.098
 Stanley-0.098
amara-0.098
Token is
Token ID318
Feature activation+1.33e-02

Pos logit contributions
 Electricity+0.193
Shipping+0.188
Initialized+0.187
+0.184
Electric+0.183
Neg logit contributions
++)-0.264
ound-0.259
show-0.246
amara-0.245
 Stanley-0.245
Token what
Token ID644
Feature activation+5.66e-02

Pos logit contributions
 Electricity+0.246
Shipping+0.238
+0.237
Initialized+0.237
Electric+0.233
Neg logit contributions
++)-0.277
ound-0.266
amara-0.253
show-0.252
okia-0.251
Token seem
Token ID1283
Feature activation-2.40e-01

Pos logit contributions
++)+0.099
ound+0.096
show+0.091
amara+0.091
ady+0.090
Neg logit contributions
 Electricity-0.096
Shipping-0.094
Initialized-0.094
-0.093
Electric-0.092
Token to
Token ID284
Feature activation-3.16e-02

Pos logit contributions
 Electricity+0.323
Shipping+0.319
+0.316
_(+0.310
Initialized+0.308
Neg logit contributions
++)-0.506
ound-0.489
amara-0.467
show-0.462
okia-0.461
Token be
Token ID307
Feature activation-1.94e-02

Pos logit contributions
 Electricity+0.055
Shipping+0.053
Initialized+0.053
+0.052
Electric+0.052
Neg logit contributions
++)-0.055
ound-0.053
amara-0.050
show-0.050
 Stanley-0.049
Token real
Token ID1103
Feature activation+2.19e-03

Pos logit contributions
 Electricity+0.033
Shipping+0.032
Initialized+0.032
+0.032
Electric+0.031
Neg logit contributions
++)-0.034
ound-0.033
show-0.031
amara-0.031
ady-0.031
Token disagreements
Token ID37990
Feature activation-5.18e-01

Pos logit contributions
++)+0.004
ound+0.004
show+0.004
amara+0.004
 Stanley+0.004
Neg logit contributions
 Electricity-0.004
Initialized-0.004
Shipping-0.004
-0.004
Electric-0.003
Token in
Token ID287
Feature activation-3.08e-02

Pos logit contributions
 Electricity+0.749
Shipping+0.728
Initialized+0.720
+0.714
_(+0.702
Neg logit contributions
++)-1.040
ound-1.009
show-0.964
amara-0.960
ady-0.957
Token judgments
Token ID24195
Feature activation-1.08e-01

Pos logit contributions
 Electricity+0.053
Initialized+0.051
Shipping+0.051
+0.051
Electric+0.050
Neg logit contributions
++)-0.054
ound-0.053
show-0.050
amara-0.050
ady-0.049
Token about
Token ID546
Feature activation-1.72e-01

Pos logit contributions
 Electricity+0.149
Shipping+0.144
Initialized+0.144
+0.142
Electric+0.140
Neg logit contributions
++)-0.223
ound-0.218
show-0.208
amara-0.207
 Stanley-0.207
Token the
Token ID262
Feature activation-2.34e-02

Pos logit contributions
 Electricity+0.284
Initialized+0.276
Shipping+0.276
+0.274
Electric+0.270
Neg logit contributions
++)-0.311
ound-0.303
show-0.287
amara-0.286
ady-0.284
Token performances
Token ID13289
Feature activation+2.37e-02

Pos logit contributions
 Electricity+0.044
Shipping+0.043
Initialized+0.043
+0.042
Electric+0.042
Neg logit contributions
++)-0.037
ound-0.036
show-0.034
amara-0.034
 Stanley-0.034
Token at
Token ID379
Feature activation-5.82e-03

Pos logit contributions
++)+0.053
ound+0.052
show+0.049
 Stanley+0.049
ady+0.049
Neg logit contributions
 Electricity-0.043
Initialized-0.042
Shipping-0.042
Electric-0.041
-0.041
Token all
Token ID477
Feature activation-4.53e-02

Pos logit contributions
 Electricity+0.008
Initialized+0.008
Shipping+0.008
+0.007
Electric+0.007
Neg logit contributions
++)-0.012
ound-0.012
show-0.011
 Stanley-0.011
amara-0.011
Token.
Token ID13
Feature activation-2.50e-02

Pos logit contributions
 Electricity+0.064
Initialized+0.063
Shipping+0.062
+0.061
Electric+0.061
Neg logit contributions
++)-0.092
ound-0.090
show-0.086
 Stanley-0.086
ady-0.085
Token
Token ID447
Feature activation-4.65e-02

Pos logit contributions
 Electricity+0.037
Initialized+0.036
Shipping+0.036
+0.035
Electric+0.035
Neg logit contributions
++)-0.049
ound-0.048
show-0.046
 Stanley-0.046
amara-0.045
Token
Token ID251
Feature activation+7.54e-02

Pos logit contributions
 Electricity+0.081
Shipping+0.079
Initialized+0.079
+0.078
Electric+0.077
Neg logit contributions
++)-0.079
ound-0.078
show-0.073
amara-0.073
 Stanley-0.073
Token Ichigo
Token ID44547
Feature activation-6.75e-01

Pos logit contributions
++)+0.155
ound+0.152
 Stanley+0.145
show+0.145
amara+0.143
Neg logit contributions
 Electricity-0.105
Shipping-0.103
Initialized-0.102
-0.100
Electric-0.100
Token
Token ID447
Feature activation-7.94e-02

Pos logit contributions
 Electricity+1.140
Shipping+1.108
Initialized+1.106
+1.092
Electric+1.082
Neg logit contributions
++)-1.178
ound-1.163
show-1.099
amara-1.090
 Stanley-1.083
Token
Token ID247
Feature activation+1.22e-02

Pos logit contributions
 Electricity+0.143
Shipping+0.140
Initialized+0.140
+0.138
Electric+0.137
Neg logit contributions
++)-0.130
ound-0.127
show-0.120
 Stanley-0.119
amara-0.119
Tokens
Token ID82
Feature activation-4.18e-02

Pos logit contributions
++)+0.021
ound+0.021
show+0.020
 Stanley+0.020
ady+0.019
Neg logit contributions
 Electricity-0.021
Initialized-0.020
Shipping-0.020
-0.020
Electric-0.020
Token next
Token ID1306
Feature activation+3.25e-01

Pos logit contributions
 Electricity+0.073
Shipping+0.072
Initialized+0.072
+0.071
Electric+0.070
Neg logit contributions
++)-0.071
ound-0.069
show-0.065
 Stanley-0.065
amara-0.065
Token sentence
Token ID6827
Feature activation+6.89e-02

Pos logit contributions
++)+0.503
ound+0.492
show+0.461
 Stanley+0.459
amara+0.456
Neg logit contributions
 Electricity-0.618
Initialized-0.605
Shipping-0.605
-0.595
Electric-0.592
Token,
Token ID11
Feature activation+6.24e-02

Pos logit contributions
++)+0.587
ound+0.577
show+0.547
 Stanley+0.546
amara+0.542
Neg logit contributions
 Electricity-0.499
Shipping-0.488
Initialized-0.487
-0.478
Electric-0.475
Token too
Token ID1165
Feature activation-9.54e-02

Pos logit contributions
++)+0.118
ound+0.115
show+0.109
 Stanley+0.109
amara+0.109
Neg logit contributions
 Electricity-0.098
Shipping-0.095
Initialized-0.095
-0.093
Electric-0.093
Token:
Token ID25
Feature activation+4.17e-02

Pos logit contributions
 Electricity+0.138
Shipping+0.134
Initialized+0.134
+0.132
Electric+0.130
Neg logit contributions
++)-0.190
ound-0.187
show-0.178
amara-0.177
ady-0.176
Token These
Token ID2312
Feature activation-9.26e-02

Pos logit contributions
++)+0.082
ound+0.080
show+0.076
 Stanley+0.076
amara+0.076
Neg logit contributions
 Electricity-0.062
Shipping-0.061
Initialized-0.060
-0.059
Electric-0.059
Token "
Token ID366
Feature activation+1.26e-02

Pos logit contributions
 Electricity+0.147
Shipping+0.142
Initialized+0.142
+0.140
Electric+0.139
Neg logit contributions
++)-0.173
ound-0.169
show-0.161
amara-0.160
 Stanley-0.159
Tokenlab
Token ID23912
Feature activation-4.84e-01

Pos logit contributions
++)+0.020
ound+0.019
 Stanley+0.018
show+0.018
amara+0.018
Neg logit contributions
 Electricity-0.024
Shipping-0.023
Initialized-0.023
-0.023
Electric-0.023
Tokenyrinth
Token ID21324
Feature activation+1.43e-01

Pos logit contributions
 Electricity+0.843
Shipping+0.826
Initialized+0.824
Electric+0.811
+0.811
Neg logit contributions
++)-0.816
ound-0.789
 Stanley-0.749
amara-0.747
show-0.745
Tokenine
Token ID500
Feature activation-5.56e-01

Pos logit contributions
++)+0.246
ound+0.241
show+0.227
 Stanley+0.226
amara+0.225
Neg logit contributions
 Electricity-0.247
Shipping-0.241
Initialized-0.241
-0.237
Electric-0.236
Token worlds
Token ID11621
Feature activation+2.89e-02

Pos logit contributions
 Electricity+0.876
Shipping+0.853
Initialized+0.853
+0.837
Electric+0.829
Neg logit contributions
++)-1.040
ound-1.020
show-0.967
amara-0.963
ady-0.959
Token filled
Token ID5901
Feature activation+9.75e-02

Pos logit contributions
++)+0.055
ound+0.053
show+0.051
 Stanley+0.051
amara+0.050
Neg logit contributions
 Electricity-0.045
Shipping-0.044
Initialized-0.044
-0.043
Electric-0.043
Token with
Token ID351
Feature activation+6.30e-02

Pos logit contributions
++)+0.191
ound+0.188
show+0.178
 Stanley+0.178
amara+0.177
Neg logit contributions
 Electricity-0.145
Shipping-0.141
Initialized-0.141
-0.139
Electric-0.137