TOP ACTIVATIONS
MAX = 2.924

Russia . Image copyright AFP Image caption The Kurds
. <|endoftext|> Image copyright publicity Image caption The Greeks
ported License . <|endoftext|> Image copyright AP Image caption Peace talks
. <|endoftext|> Image copyright Deadline Police have
Serve hot ! <|endoftext|> Image copyright ESA Image caption Go ce
million years . <|endoftext|> Image copyright AFP The Bank
... Flag Flag Reply 14 Recommend
Bird sey e view of Brigham City , Utah Date :
arsenal of the Ban u Qur ay za which consisted of
said : Le icester have an excellent home record
? Flag Flag Reply 27 Recommend
. Flag Flag Reply 55 Recommend
in betting with a particular reputation as in - play football
, with this map of Brigham City , Utah [ g
. Flag Flag Reply 19 Recommend
surface . Media playback is unsupported on your device
energy goals . <|endoftext|> Media playback is unsupported on your device
on Twitter . <|endoftext|> Media playback is unsupported on your device
especially for the legacy and reputation of President Barack Obama and
language . - Katherine d ' Ent rem ont , commissioner

MIN ACTIVATIONS
MIN = -2.505

In 1973 , Beth une was induct ed into
said Sen . Kay Bailey Hutch ison ( R
The FCC accused California - based Total Call Mobile of fraud
slavery . The 18 76 Freed men s Memorial
: The Ride . The ride includes a rotating platform that
OUNT ( * ) AS count FROM ( SELECT SPL IT
sell its RF ID - based products throughout its global customer
, this week Kirk Herb stre it , Lee Cor so
T iki Tw irl thrill ride at California 's Great America
{ Center { $ s Format . Al ignment = [
The first proposal , Mandatory In clusion ary Housing ,
[ white ] se [ t ] { options } :[
but if it was a pie [ chart ], it would
for def raud ing its Lif eline program , which subsid
writing a D MA - based USB stack and libraries that
reached the original border .[ 19 ] At that
former St . Louis Rams kicker Brett Ba er who
. <|endoftext|> The Bengals signed kicker Jonathan Brown , far right
, Wells Fargo , and Ally Bank the nation
. # atl weather # Snow ed Out Atlanta pic .

INTERVAL 1.567 - 2.924
CONTAINS 0.146%

people . Its exports to Saudi Arabia total $ 1 .
2016 ( Photo : Wayne McG a hee III / Dem
for his fourth ACC Rookie of the Week Award and first
a block be a first class parameter and can you pass
/ W 8 v X Ds 4 j 0 o

INTERVAL 0.210 - 1.567
CONTAINS 30.707%

( W CR P ), European Commission Joint Research Centre (
Another common name suggested for Pet rog ale wil kins i
Exception . Message )" break } } End { Try {
s something you don t want to happen .
Forum , which will meet on a quarterly basis from September

INTERVAL -1.147 - 0.210
CONTAINS 68.153%

first by a hydra ul ics issue with the rocket
who could land a Supporting Actor nomination for Joe Wright
ading framework needed for the regional system to work .
's war chest is significantly bigger now . Mozilla , which
timed 45 - minute programming challenge on Interview Street as a

INTERVAL -2.505 - -1.147
CONTAINS 0.995%

the same thing . The news feed , a staple of
factor " number that is greater than 0 , and then
was once seemed like a summer memory from the ancient past
] optional white space { options } a list of option
F - 150 Eco Boost Tort ure Test truck in the
Token Russia
Token ID3284
Feature activation+3.17e-01

Pos logit contributions
ities+0.638
 fins+0.638
isite+0.606
 Advantage+0.603
ity+0.592
Neg logit contributions
hell-0.661
undo-0.661
dash-0.659
boro-0.630
 ALEC-0.625
Token.
Token ID13
Feature activation+4.48e-02

Pos logit contributions
 fins+1.004
ities+1.003
 Advantage+0.954
isite+0.950
ity+0.946
Neg logit contributions
dash-0.846
hell-0.838
undo-0.829
 ALEC-0.804
boro-0.787
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
ities+0.143
 fins+0.142
 Advantage+0.139
isite+0.137
ity+0.134
Neg logit contributions
hell-0.117
dash-0.117
undo-0.117
boro-0.111
 ALEC-0.111
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
hell+0.317
dash+0.315
undo+0.307
 ALEC+0.298
boro+0.293
Neg logit contributions
 fins-0.536
ities-0.525
isite-0.520
 Advantage-0.512
iaz-0.508
TokenImage
Token ID5159
Feature activation+1.05e+00

Pos logit contributions
ities+0.407
 fins+0.396
isite+0.385
ity+0.379
 Advantage+0.375
Neg logit contributions
undo-0.461
hell-0.459
dash-0.459
 ALEC-0.455
boro-0.446
Token copyright
Token ID6634
Feature activation+2.92e+00

Pos logit contributions
 fins+2.507
ities+2.438
 Advantage+2.338
isite+2.321
ity+2.246
Neg logit contributions
dash-3.610
hell-3.570
undo-3.526
boro-3.423
 ALEC-3.388
Token AFP
Token ID8916
Feature activation+1.24e+00

Pos logit contributions
 fins+6.576
ities+6.575
 Advantage+6.366
ity+6.223
 Flames+6.012
Neg logit contributions
dash-9.254
hell-9.104
undo-9.029
boro-8.919
robe-8.743
Token Image
Token ID7412
Feature activation+6.39e-01

Pos logit contributions
ities+2.373
 fins+2.305
 Advantage+2.190
ity+2.124
isite+2.102
Neg logit contributions
dash-4.819
hell-4.752
undo-4.651
 ALEC-4.619
boro-4.592
Token caption
Token ID8305
Feature activation+2.00e+00

Pos logit contributions
 fins+1.290
ities+1.262
isite+1.212
 Advantage+1.197
iaz+1.171
Neg logit contributions
dash-2.429
hell-2.429
undo-2.409
 ALEC-2.362
boro-2.327
Token The
Token ID383
Feature activation+8.80e-01

Pos logit contributions
ities+4.942
 Advantage+4.845
 fins+4.709
ity+4.644
 Flames+4.549
Neg logit contributions
undo-6.464
hell-6.426
dash-6.397
boro-6.092
acus-6.090
Token Kurds
Token ID23880
Feature activation+3.53e-01

Pos logit contributions
 fins+2.168
ities+2.164
 Advantage+2.044
isite+2.029
ity+2.003
Neg logit contributions
hell-2.917
dash-2.916
undo-2.913
boro-2.820
 ALEC-2.793
Token.
Token ID13
Feature activation-8.51e-02

Pos logit contributions
dash+1.828
hell+1.828
undo+1.808
 ALEC+1.750
boro+1.720
Neg logit contributions
 fins-2.395
ities-2.385
isite-2.303
 Advantage-2.292
iaz-2.256
Token
Token ID447
Feature activation+1.18e-01

Pos logit contributions
undo+0.278
hell+0.277
dash+0.277
boro+0.267
 ALEC+0.265
Neg logit contributions
ities-0.216
 fins-0.214
 Advantage-0.208
isite-0.203
ity-0.200
Token
Token ID251
Feature activation-9.95e-03

Pos logit contributions
 fins+0.309
ities+0.307
 Advantage+0.293
isite+0.291
pta+0.286
Neg logit contributions
hell-0.378
dash-0.377
undo-0.373
 ALEC-0.364
boro-0.360
Token<|endoftext|>
Token ID50256
Feature activation-3.90e-01

Pos logit contributions
undo+0.028
dash+0.028
hell+0.028
boro+0.027
 ALEC+0.027
Neg logit contributions
ities-0.030
 fins-0.030
 Advantage-0.029
isite-0.028
ity-0.028
TokenImage
Token ID5159
Feature activation+4.48e-01

Pos logit contributions
dash+1.144
hell+1.142
undo+1.139
 ALEC+1.122
boro+1.095
Neg logit contributions
ities-1.112
 fins-1.105
isite-1.063
 Advantage-1.050
iaz-1.041
Token copyright
Token ID6634
Feature activation+2.84e+00

Pos logit contributions
 fins+1.104
ities+1.082
 Advantage+1.041
isite+1.027
iaz+1.004
Neg logit contributions
dash-1.520
hell-1.500
undo-1.498
 ALEC-1.452
boro-1.447
Token publicity
Token ID19403
Feature activation+1.02e+00

Pos logit contributions
 Advantage+7.080
 fins+7.062
ities+7.034
ity+6.683
 Flames+6.549
Neg logit contributions
dash-8.267
undo-8.071
hell-8.046
boro-7.918
FTWARE-7.678
Token Image
Token ID7412
Feature activation+1.10e+00

Pos logit contributions
ities+2.947
 fins+2.916
 Advantage+2.804
ity+2.793
pta+2.744
Neg logit contributions
dash-2.913
hell-2.862
undo-2.855
 ALEC-2.796
FTWARE-2.780
Token caption
Token ID8305
Feature activation+2.16e+00

Pos logit contributions
 fins+2.056
ities+2.046
isite+1.912
 Advantage+1.896
iaz+1.841
Neg logit contributions
dash-4.344
hell-4.344
undo-4.314
 ALEC-4.223
boro-4.186
Token The
Token ID383
Feature activation+8.20e-01

Pos logit contributions
 Advantage+5.999
ities+5.993
 fins+5.953
ity+5.674
 Flames+5.650
Neg logit contributions
undo-6.101
dash-6.028
hell-5.943
acus-5.645
boro-5.628
Token Greeks
Token ID25059
Feature activation+1.83e-01

Pos logit contributions
 fins+2.251
ities+2.212
 Advantage+2.118
isite+2.094
ity+2.057
Neg logit contributions
hell-2.521
dash-2.519
undo-2.504
boro-2.405
 ALEC-2.391
Tokenported
Token ID9213
Feature activation-3.13e-01

Pos logit contributions
ities+1.526
 fins+1.470
isite+1.440
 Advantage+1.400
ity+1.398
Neg logit contributions
hell-2.977
dash-2.972
undo-2.885
 ALEC-2.874
boro-2.809
Token License
Token ID13789
Feature activation+7.89e-01

Pos logit contributions
hell+0.960
dash+0.960
undo+0.952
 ALEC+0.920
boro+0.909
Neg logit contributions
ities-0.866
 fins-0.864
 Advantage-0.828
isite-0.828
iaz-0.805
Token.
Token ID13
Feature activation-2.92e-01

Pos logit contributions
ities+2.399
 fins+2.389
 Advantage+2.338
ity+2.263
isite+2.262
Neg logit contributions
dash-2.143
hell-2.142
undo-2.118
boro-2.051
 ALEC-2.046
Token<|endoftext|>
Token ID50256
Feature activation-3.95e-01

Pos logit contributions
dash+0.911
hell+0.911
undo+0.900
 ALEC+0.876
boro+0.868
Neg logit contributions
 fins-0.787
ities-0.784
 Advantage-0.750
isite-0.749
iaz-0.733
TokenImage
Token ID5159
Feature activation+4.17e-01

Pos logit contributions
dash+1.161
hell+1.159
undo+1.156
 ALEC+1.138
boro+1.111
Neg logit contributions
ities-1.121
 fins-1.114
isite-1.071
 Advantage-1.058
iaz-1.049
Token copyright
Token ID6634
Feature activation+2.80e+00

Pos logit contributions
 fins+1.026
ities+1.006
 Advantage+0.966
isite+0.954
iaz+0.934
Neg logit contributions
dash-1.414
hell-1.398
undo-1.394
 ALEC-1.354
boro-1.347
Token AP
Token ID3486
Feature activation+1.06e+00

Pos logit contributions
 Advantage+7.005
 fins+7.000
ities+6.958
ity+6.597
 Flames+6.455
Neg logit contributions
dash-8.158
undo-7.949
hell-7.934
boro-7.807
FTWARE-7.569
Token Image
Token ID7412
Feature activation+8.78e-01

Pos logit contributions
ities+2.027
 fins+1.980
 Advantage+1.916
ity+1.838
isite+1.832
Neg logit contributions
dash-4.071
hell-4.011
undo-3.959
 ALEC-3.905
boro-3.885
Token caption
Token ID8305
Feature activation+1.98e+00

Pos logit contributions
 fins+1.699
ities+1.681
isite+1.592
 Advantage+1.574
iaz+1.533
Neg logit contributions
hell-3.405
dash-3.405
undo-3.380
 ALEC-3.312
boro-3.272
Token Peace
Token ID12689
Feature activation-1.11e+00

Pos logit contributions
ities+5.301
 Advantage+5.239
 fins+5.171
ity+4.959
 Flames+4.951
Neg logit contributions
undo-5.952
dash-5.927
hell-5.855
acus-5.550
boro-5.529
Token talks
Token ID6130
Feature activation+1.58e-02

Pos logit contributions
hell+3.312
dash+3.297
undo+3.269
 ALEC+3.185
boro+3.147
Neg logit contributions
 fins-3.112
ities-3.095
isite-2.982
 Advantage-2.952
iaz-2.906
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
 fins+1.241
ities+1.234
ity+1.179
 Advantage+1.174
isite+1.170
Neg logit contributions
undo-1.094
hell-1.089
dash-1.085
 ALEC-1.050
boro-1.038
Token
Token ID447
Feature activation-2.21e-02

Pos logit contributions
dash+0.340
hell+0.340
undo+0.338
 ALEC+0.328
boro+0.325
Neg logit contributions
 fins-0.277
ities-0.276
 Advantage-0.264
isite-0.263
iaz-0.257
Token
Token ID251
Feature activation+2.58e-01

Pos logit contributions
dash+0.072
hell+0.072
undo+0.071
 ALEC+0.070
boro+0.069
Neg logit contributions
 fins-0.057
ities-0.057
 Advantage-0.054
isite-0.053
pta-0.053
Token<|endoftext|>
Token ID50256
Feature activation-3.10e-01

Pos logit contributions
 fins+0.758
ities+0.757
 Advantage+0.726
isite+0.717
iaz+0.708
Neg logit contributions
dash-0.738
undo-0.735
hell-0.733
 ALEC-0.708
boro-0.702
TokenImage
Token ID5159
Feature activation+4.27e-01

Pos logit contributions
dash+0.909
hell+0.907
undo+0.906
 ALEC+0.894
boro+0.871
Neg logit contributions
ities-0.881
 fins-0.874
isite-0.842
 Advantage-0.830
iaz-0.825
Token copyright
Token ID6634
Feature activation+2.79e+00

Pos logit contributions
 fins+1.053
ities+1.032
 Advantage+0.993
isite+0.980
iaz+0.957
Neg logit contributions
dash-1.444
hell-1.425
undo-1.422
 ALEC-1.380
boro-1.374
Token Deadline
Token ID35954
Feature activation+1.70e-01

Pos logit contributions
 Advantage+7.000
 fins+6.995
ities+6.952
ity+6.605
 Flames+6.467
Neg logit contributions
dash-8.083
undo-7.885
hell-7.870
boro-7.728
FTWARE-7.510
Token
Token ID198
Feature activation+6.50e-02

Pos logit contributions
ities+0.427
 fins+0.422
isite+0.407
 Advantage+0.407
ity+0.394
Neg logit contributions
dash-0.568
hell-0.559
undo-0.554
 ALEC-0.545
boro-0.534
Token
Token ID198
Feature activation+9.56e-02

Pos logit contributions
 fins+0.234
ities+0.231
isite+0.227
 Advantage+0.223
iaz+0.222
Neg logit contributions
hell-0.146
dash-0.145
undo-0.142
 ALEC-0.138
boro-0.135
TokenPolice
Token ID9039
Feature activation-1.13e+00

Pos logit contributions
ities+0.264
 fins+0.258
isite+0.249
 Advantage+0.246
ity+0.245
Neg logit contributions
dash-0.287
undo-0.286
hell-0.285
 ALEC-0.283
boro-0.276
Token have
Token ID423
Feature activation+5.73e-02

Pos logit contributions
hell+3.405
undo+3.356
dash+3.349
 ALEC+3.268
boro+3.237
Neg logit contributions
 fins-3.089
ities-3.081
isite-3.055
pta-2.969
iaz-2.964
Token Serve
Token ID35557
Feature activation+3.50e-01

Pos logit contributions
 fins+0.545
ities+0.538
isite+0.520
 Advantage+0.512
iaz+0.508
Neg logit contributions
hell-0.656
dash-0.656
undo-0.648
 ALEC-0.635
boro-0.625
Token hot
Token ID3024
Feature activation-6.25e-01

Pos logit contributions
 fins+0.860
ities+0.854
isite+0.817
 Advantage+0.810
iaz+0.793
Neg logit contributions
dash-1.174
hell-1.174
undo-1.164
 ALEC-1.137
boro-1.122
Token!
Token ID0
Feature activation-2.24e-01

Pos logit contributions
dash+1.037
hell+1.035
undo+1.004
 ALEC+0.977
boro+0.934
Neg logit contributions
 fins-2.598
ities-2.562
isite-2.550
 Advantage-2.512
iaz-2.509
Token<|endoftext|>
Token ID50256
Feature activation-3.14e-01

Pos logit contributions
hell+0.643
undo+0.640
dash+0.639
 ALEC+0.619
boro+0.611
Neg logit contributions
 fins-0.656
ities-0.652
 Advantage-0.629
isite-0.628
iaz-0.614
TokenImage
Token ID5159
Feature activation+4.75e-01

Pos logit contributions
dash+0.922
hell+0.920
undo+0.919
 ALEC+0.908
boro+0.885
Neg logit contributions
ities-0.890
 fins-0.882
isite-0.850
 Advantage-0.837
iaz-0.832
Token copyright
Token ID6634
Feature activation+2.78e+00

Pos logit contributions
 fins+1.170
ities+1.144
 Advantage+1.103
isite+1.087
iaz+1.063
Neg logit contributions
dash-1.608
hell-1.589
undo-1.585
 ALEC-1.538
boro-1.534
Token ESA
Token ID42212
Feature activation+8.24e-02

Pos logit contributions
 Advantage+6.944
 fins+6.943
ities+6.876
ity+6.531
 Flames+6.405
Neg logit contributions
dash-8.110
undo-7.916
hell-7.900
boro-7.795
FTWARE-7.534
Token Image
Token ID7412
Feature activation+7.15e-01

Pos logit contributions
 fins+0.204
ities+0.202
 Advantage+0.194
isite+0.191
pta+0.187
Neg logit contributions
dash-0.278
hell-0.275
undo-0.274
 ALEC-0.268
boro-0.264
Token caption
Token ID8305
Feature activation+2.10e+00

Pos logit contributions
 fins+1.401
ities+1.386
isite+1.315
 Advantage+1.301
iaz+1.270
Neg logit contributions
hell-2.754
dash-2.753
undo-2.733
 ALEC-2.676
boro-2.642
Token Go
Token ID1514
Feature activation+3.66e-01

Pos logit contributions
 fins+5.296
 Advantage+5.214
ities+5.214
 Flames+4.916
ity+4.855
Neg logit contributions
undo-6.576
dash-6.506
hell-6.422
boro-6.220
acus-6.134
Tokence
Token ID344
Feature activation-8.25e-01

Pos logit contributions
 fins+1.041
ities+1.039
isite+0.973
 Advantage+0.970
pta+0.966
Neg logit contributions
dash-1.093
undo-1.089
hell-1.075
 ALEC-1.068
boro-1.037
Token million
Token ID1510
Feature activation+8.42e-01

Pos logit contributions
 fins+3.195
ities+3.159
 Advantage+2.990
isite+2.966
pta+2.963
Neg logit contributions
undo-3.708
dash-3.657
hell-3.602
 ALEC-3.527
boro-3.484
Token years
Token ID812
Feature activation+8.29e-01

Pos logit contributions
 fins+1.867
ities+1.863
isite+1.739
ity+1.715
arily+1.699
Neg logit contributions
undo-3.002
dash-3.001
hell-2.964
boro-2.893
 ALEC-2.883
Token.
Token ID13
Feature activation+4.61e-03

Pos logit contributions
ities+2.641
 fins+2.635
 Advantage+2.518
isite+2.497
iaz+2.478
Neg logit contributions
dash-2.147
hell-2.116
undo-2.100
 ALEC-2.038
boro-2.016
Token<|endoftext|>
Token ID50256
Feature activation-4.11e-01

Pos logit contributions
 fins+0.014
ities+0.014
 Advantage+0.013
isite+0.013
pta+0.013
Neg logit contributions
dash-0.013
hell-0.013
undo-0.013
 ALEC-0.012
boro-0.012
TokenImage
Token ID5159
Feature activation+4.14e-01

Pos logit contributions
dash+1.210
hell+1.208
undo+1.205
 ALEC+1.188
boro+1.159
Neg logit contributions
ities-1.164
 fins-1.157
isite-1.113
 Advantage-1.098
iaz-1.089
Token copyright
Token ID6634
Feature activation+2.77e+00

Pos logit contributions
 fins+1.020
ities+0.999
 Advantage+0.961
isite+0.950
iaz+0.929
Neg logit contributions
dash-1.402
hell-1.386
undo-1.382
 ALEC-1.341
boro-1.334
Token AFP
Token ID8916
Feature activation+1.24e+00

Pos logit contributions
 Advantage+6.893
 fins+6.879
ities+6.832
ity+6.481
 Flames+6.354
Neg logit contributions
dash-8.135
undo-7.923
hell-7.905
boro-7.777
FTWARE-7.534
Token
Token ID198
Feature activation-1.66e-01

Pos logit contributions
ities+2.458
 fins+2.409
 Advantage+2.318
ity+2.224
pta+2.184
Neg logit contributions
dash-4.713
hell-4.610
undo-4.523
 ALEC-4.492
boro-4.483
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
hell+0.358
dash+0.355
undo+0.346
 ALEC+0.338
boro+0.331
Neg logit contributions
 fins-0.618
ities-0.604
isite-0.599
 Advantage-0.587
iaz-0.587
TokenThe
Token ID464
Feature activation-3.51e-01

Pos logit contributions
ities+0.382
 fins+0.375
isite+0.361
 Advantage+0.356
ity+0.355
Neg logit contributions
dash-0.421
hell-0.420
undo-0.419
 ALEC-0.414
boro-0.404
Token Bank
Token ID5018
Feature activation-8.00e-01

Pos logit contributions
hell+1.189
dash+1.188
undo+1.178
 ALEC+1.153
boro+1.135
Neg logit contributions
 fins-0.847
ities-0.841
isite-0.806
 Advantage-0.798
iaz-0.783
Token...
Token ID986
Feature activation+6.27e-01

Pos logit contributions
dash+0.185
undo+0.185
hell+0.183
 ALEC+0.179
boro+0.176
Neg logit contributions
ities-0.166
 fins-0.164
 Advantage-0.158
isite-0.156
ity-0.156
Token Flag
Token ID19762
Feature activation-1.37e-01

Pos logit contributions
ities+1.753
 fins+1.737
 Advantage+1.705
isite+1.688
ity+1.654
Neg logit contributions
dash-1.845
undo-1.831
hell-1.807
 ALEC-1.761
boro-1.748
Token
Token ID198
Feature activation+5.69e-01

Pos logit contributions
dash+0.335
hell+0.335
undo+0.331
 ALEC+0.320
boro+0.315
Neg logit contributions
 fins-0.463
ities-0.461
isite-0.446
 Advantage-0.443
iaz-0.437
Token
Token ID198
Feature activation+7.01e-01

Pos logit contributions
ities+1.895
 fins+1.879
 Advantage+1.815
isite+1.810
ity+1.791
Neg logit contributions
dash-1.385
undo-1.382
hell-1.376
 ALEC-1.336
boro-1.304
TokenFlag
Token ID34227
Feature activation-5.94e-01

Pos logit contributions
ities+1.780
 fins+1.747
iaz+1.708
pta+1.700
isite+1.687
Neg logit contributions
 ALEC-2.185
hell-2.148
dash-2.146
undo-2.145
FTWARE-2.107
Token Reply
Token ID14883
Feature activation+2.70e+00

Pos logit contributions
hell+1.945
dash+1.939
undo+1.938
 ALEC+1.908
boro+1.860
Neg logit contributions
 fins-1.488
ities-1.482
isite-1.428
 Advantage-1.390
iaz-1.379
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
 fins+7.201
 Advantage+7.051
ities+7.046
isite+6.679
 Flames+6.582
Neg logit contributions
hell-7.718
undo-7.602
FTWARE-7.524
dash-7.443
acus-7.396
Token
Token ID198
Feature activation+4.87e-01

Pos logit contributions
 fins+0.741
ities+0.737
isite+0.715
 Advantage+0.710
iaz+0.701
Neg logit contributions
hell-0.487
dash-0.487
undo-0.481
 ALEC-0.464
boro-0.456
Token14
Token ID1415
Feature activation-1.43e-01

Pos logit contributions
ities+1.289
 fins+1.270
isite+1.225
 Advantage+1.218
pta+1.213
Neg logit contributions
undo-1.512
hell-1.508
dash-1.503
 ALEC-1.476
boro-1.447
Token Recommend
Token ID30361
Feature activation+8.13e-01

Pos logit contributions
dash+0.465
hell+0.465
undo+0.462
 ALEC+0.448
boro+0.445
Neg logit contributions
 fins-0.367
ities-0.365
isite-0.348
 Advantage-0.347
pta-0.339
Token
Token ID198
Feature activation+6.06e-01

Pos logit contributions
ities+2.738
 fins+2.718
 Advantage+2.621
isite+2.619
ity+2.584
Neg logit contributions
dash-1.983
hell-1.976
undo-1.956
 ALEC-1.891
boro-1.852
TokenBird
Token ID42562
Feature activation-8.96e-01

Pos logit contributions
ities+1.026
 fins+1.000
isite+0.968
ity+0.958
 Advantage+0.945
Neg logit contributions
dash-1.101
 ALEC-1.097
hell-1.094
undo-1.090
boro-1.051
Tokensey
Token ID4397
Feature activation-2.21e-02

Pos logit contributions
dash+2.533
hell+2.533
undo+2.509
 ALEC+2.438
boro+2.400
Neg logit contributions
 fins-2.675
ities-2.661
isite-2.564
 Advantage-2.548
iaz-2.504
Tokene
Token ID68
Feature activation+1.66e-01

Pos logit contributions
dash+0.069
hell+0.069
undo+0.069
 ALEC+0.068
boro+0.066
Neg logit contributions
ities-0.060
 fins-0.059
isite-0.057
 Advantage-0.056
ity-0.055
Token view
Token ID1570
Feature activation+6.07e-01

Pos logit contributions
 fins+0.487
ities+0.481
 Advantage+0.461
isite+0.456
ity+0.449
Neg logit contributions
dash-0.486
hell-0.483
undo-0.479
 ALEC-0.465
boro-0.459
Token of
Token ID286
Feature activation+7.96e-01

Pos logit contributions
 fins+1.691
ities+1.671
 Advantage+1.578
isite+1.569
ity+1.544
Neg logit contributions
hell-1.836
dash-1.825
undo-1.795
 ALEC-1.777
boro-1.749
Token Brigham
Token ID37434
Feature activation+2.62e+00

Pos logit contributions
ities+2.012
 fins+2.008
 Advantage+1.908
isite+1.883
ity+1.855
Neg logit contributions
dash-2.632
hell-2.598
undo-2.597
 ALEC-2.475
boro-2.434
Token City
Token ID2254
Feature activation+5.08e-01

Pos logit contributions
ities+5.261
ity+4.900
 Advantage+4.872
 fins+4.626
isite+4.474
Neg logit contributions
undo-9.357
FTWARE-9.310
dash-9.237
hell-9.203
acus-8.941
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
ities+1.612
 fins+1.609
 Advantage+1.551
isite+1.532
ity+1.511
Neg logit contributions
dash-1.340
undo-1.337
hell-1.332
 ALEC-1.269
FTWARE-1.237
Token Utah
Token ID10202
Feature activation+1.18e+00

Pos logit contributions
ities+3.111
 fins+3.096
 Advantage+2.974
isite+2.905
ity+2.894
Neg logit contributions
hell-3.168
dash-3.136
undo-3.081
 ALEC-2.946
boro-2.927
Token Date
Token ID7536
Feature activation+7.43e-01

Pos logit contributions
ities+3.465
 fins+3.431
 Advantage+3.325
isite+3.269
ity+3.227
Neg logit contributions
dash-3.337
undo-3.298
hell-3.294
FTWARE-3.129
 ALEC-3.127
Token:
Token ID25
Feature activation+1.17e-01

Pos logit contributions
ities+2.154
 fins+2.135
 Advantage+2.073
isite+2.047
ity+2.013
Neg logit contributions
hell-2.157
dash-2.132
undo-2.094
 ALEC-2.054
boro-1.998
Token arsenal
Token ID24375
Feature activation+2.14e-01

Pos logit contributions
ities+0.689
 fins+0.688
 Advantage+0.653
isite+0.652
ity+0.641
Neg logit contributions
dash-0.703
hell-0.702
undo-0.692
 ALEC-0.675
boro-0.671
Token of
Token ID286
Feature activation+3.02e-01

Pos logit contributions
ities+0.584
 fins+0.583
isite+0.549
 Advantage+0.547
ity+0.541
Neg logit contributions
dash-0.661
undo-0.650
hell-0.643
boro-0.632
 ALEC-0.632
Token the
Token ID262
Feature activation+5.45e-01

Pos logit contributions
 fins+0.697
ities+0.686
 Advantage+0.645
isite+0.644
iaz+0.626
Neg logit contributions
dash-1.068
hell-1.062
undo-1.059
 ALEC-1.032
boro-1.027
Token Ban
Token ID10274
Feature activation+6.56e-01

Pos logit contributions
 fins+1.382
ities+1.373
 Advantage+1.296
isite+1.295
iaz+1.271
Neg logit contributions
dash-1.794
undo-1.775
hell-1.774
 ALEC-1.741
boro-1.715
Tokenu
Token ID84
Feature activation+1.98e+00

Pos logit contributions
ities+2.290
 fins+2.253
isite+2.182
ity+2.137
iaz+2.128
Neg logit contributions
 ALEC-1.525
dash-1.497
hell-1.472
boro-1.453
undo-1.443
Token Qur
Token ID17599
Feature activation+2.62e+00

Pos logit contributions
ities+3.010
 fins+2.966
 Advantage+2.607
iaz+2.556
ity+2.551
Neg logit contributions
undo-8.088
dash-8.009
 ALEC-7.997
hell-7.952
FTWARE-7.864
Tokenay
Token ID323
Feature activation+4.13e-01

Pos logit contributions
ities+6.661
iaz+6.277
isite+6.198
ity+6.149
 fins+6.119
Neg logit contributions
 ALEC-7.978
FTWARE-7.809
dash-7.670
undo-7.575
boro-7.434
Tokenza
Token ID4496
Feature activation+6.82e-01

Pos logit contributions
ities+1.553
 fins+1.545
isite+1.497
 Advantage+1.487
iaz+1.485
Neg logit contributions
hell-0.841
dash-0.832
undo-0.830
 ALEC-0.816
boro-0.787
Token which
Token ID543
Feature activation-1.39e-01

Pos logit contributions
ities+1.957
 fins+1.953
 Advantage+1.852
isite+1.829
ity+1.808
Neg logit contributions
dash-2.010
undo-1.991
hell-1.982
 ALEC-1.945
boro-1.899
Token consisted
Token ID19954
Feature activation-4.08e-01

Pos logit contributions
dash+0.413
hell+0.411
undo+0.408
 ALEC+0.396
boro+0.391
Neg logit contributions
 fins-0.397
ities-0.396
isite-0.378
 Advantage-0.377
pta-0.370
Token of
Token ID286
Feature activation-2.02e-01

Pos logit contributions
dash+1.216
hell+1.209
undo+1.200
 ALEC+1.168
boro+1.154
Neg logit contributions
 fins-1.160
ities-1.155
isite-1.109
 Advantage-1.100
iaz-1.081
Token said
Token ID531
Feature activation-6.65e-04

Pos logit contributions
ities+0.389
 fins+0.389
 Advantage+0.368
isite+0.364
iaz+0.362
Neg logit contributions
dash-0.400
hell-0.394
undo-0.393
 ALEC-0.382
boro-0.376
Token:
Token ID25
Feature activation+1.04e+00

Pos logit contributions
dash+0.002
hell+0.002
undo+0.002
 ALEC+0.002
boro+0.002
Neg logit contributions
 fins-0.002
ities-0.002
 Advantage-0.002
isite-0.002
ity-0.002
Token
Token ID564
Feature activation+5.84e-01

Pos logit contributions
ities+2.800
 fins+2.759
 Advantage+2.654
isite+2.641
ity+2.618
Neg logit contributions
dash-3.167
hell-3.123
undo-3.114
 ALEC-3.026
boro-3.007
Token
Token ID250
Feature activation+2.16e-01

Pos logit contributions
 fins+1.279
ities+1.219
 Advantage+1.196
isite+1.166
pta+1.140
Neg logit contributions
dash-2.131
hell-2.103
undo-2.084
 ALEC-2.072
boro-2.045
TokenLe
Token ID3123
Feature activation+3.18e-01

Pos logit contributions
ities+0.633
 fins+0.632
 Advantage+0.606
isite+0.598
ity+0.596
Neg logit contributions
dash-0.619
undo-0.610
hell-0.609
 ALEC-0.599
boro-0.584
Tokenicester
Token ID26382
Feature activation+2.62e+00

Pos logit contributions
ities+0.859
 fins+0.848
isite+0.807
 Advantage+0.806
ity+0.798
Neg logit contributions
dash-1.003
undo-0.989
hell-0.977
 ALEC-0.975
boro-0.940
Token have
Token ID423
Feature activation+6.94e-01

Pos logit contributions
 fins+6.488
ities+6.475
 Advantage+6.440
ity+6.064
iaz+5.984
Neg logit contributions
undo-7.973
dash-7.911
hell-7.854
 ALEC-7.654
FTWARE-7.543
Token an
Token ID281
Feature activation+1.80e-01

Pos logit contributions
 fins+2.007
ities+1.960
 Advantage+1.891
isite+1.836
ity+1.835
Neg logit contributions
dash-2.077
hell-2.044
undo-2.036
 ALEC-1.964
boro-1.939
Token excellent
Token ID6275
Feature activation+5.51e-01

Pos logit contributions
ities+0.439
 fins+0.437
 Advantage+0.422
isite+0.412
iaz+0.405
Neg logit contributions
dash-0.613
hell-0.609
undo-0.601
 ALEC-0.587
boro-0.586
Token home
Token ID1363
Feature activation+1.20e+00

Pos logit contributions
 fins+1.404
ities+1.397
 Advantage+1.340
ity+1.314
iaz+1.309
Neg logit contributions
hell-1.798
dash-1.789
undo-1.772
 ALEC-1.734
boro-1.705
Token record
Token ID1700
Feature activation+5.99e-01

Pos logit contributions
ities+3.354
 fins+3.285
 Advantage+3.269
ity+3.238
iaz+3.142
Neg logit contributions
hell-3.497
undo-3.489
dash-3.448
 ALEC-3.392
boro-3.303
Token?
Token ID30
Feature activation+2.34e-01

Pos logit contributions
dash+0.464
hell+0.463
undo+0.462
 ALEC+0.443
boro+0.441
Neg logit contributions
ities-0.521
 fins-0.519
 Advantage-0.497
isite-0.495
iaz-0.486
Token Flag
Token ID19762
Feature activation+8.51e-02

Pos logit contributions
ities+0.640
 fins+0.639
 Advantage+0.622
isite+0.612
ity+0.598
Neg logit contributions
dash-0.716
undo-0.713
hell-0.711
boro-0.677
 ALEC-0.675
Token
Token ID198
Feature activation+5.17e-01

Pos logit contributions
 fins+0.291
ities+0.290
 Advantage+0.281
isite+0.281
iaz+0.276
Neg logit contributions
dash-0.203
hell-0.203
undo-0.200
 ALEC-0.193
boro-0.190
Token
Token ID198
Feature activation+8.53e-01

Pos logit contributions
ities+1.759
 fins+1.754
 Advantage+1.686
isite+1.686
ity+1.657
Neg logit contributions
dash-1.237
hell-1.234
undo-1.227
 ALEC-1.184
boro-1.161
TokenFlag
Token ID34227
Feature activation-1.20e-01

Pos logit contributions
ities+2.110
 fins+2.064
isite+1.984
ity+1.962
 Advantage+1.953
Neg logit contributions
hell-2.781
undo-2.773
dash-2.769
 ALEC-2.749
boro-2.672
Token Reply
Token ID14883
Feature activation+2.60e+00

Pos logit contributions
hell+0.393
dash+0.393
undo+0.392
 ALEC+0.384
boro+0.378
Neg logit contributions
 fins-0.303
ities-0.299
isite-0.294
iaz-0.283
pta-0.283
Token
Token ID198
Feature activation+8.31e-01

Pos logit contributions
ities+7.118
ity+6.820
 fins+6.771
 Advantage+6.615
arily+6.348
Neg logit contributions
undo-7.224
dash-7.193
hell-7.169
acus-7.144
FTWARE-7.034
Token
Token ID198
Feature activation+1.18e+00

Pos logit contributions
ities+2.744
 fins+2.713
 Advantage+2.613
isite+2.598
ity+2.592
Neg logit contributions
dash-2.062
undo-2.056
hell-2.048
 ALEC-1.980
boro-1.941
Token27
Token ID1983
Feature activation+2.29e-01

Pos logit contributions
ities+3.008
 fins+2.915
ity+2.850
 Advantage+2.832
isite+2.803
Neg logit contributions
undo-3.709
dash-3.692
hell-3.664
 ALEC-3.628
acus-3.545
Token Recommend
Token ID30361
Feature activation+8.97e-01

Pos logit contributions
 fins+0.607
ities+0.603
isite+0.579
 Advantage+0.574
iaz+0.564
Neg logit contributions
dash-0.727
hell-0.727
undo-0.721
 ALEC-0.703
boro-0.693
Token
Token ID198
Feature activation+5.03e-01

Pos logit contributions
ities+2.986
 fins+2.958
 Advantage+2.852
isite+2.841
ity+2.824
Neg logit contributions
dash-2.213
hell-2.203
undo-2.188
 ALEC-2.113
boro-2.069
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
dash+0.837
hell+0.834
undo+0.829
 ALEC+0.800
boro+0.784
Neg logit contributions
 fins-1.109
ities-1.107
isite-1.061
 Advantage-1.059
iaz-1.040
Token Flag
Token ID19762
Feature activation-1.68e-02

Pos logit contributions
dash+0.524
hell+0.524
undo+0.520
 ALEC+0.505
boro+0.498
Neg logit contributions
 fins-0.499
ities-0.497
isite-0.477
 Advantage-0.475
iaz-0.466
Token
Token ID198
Feature activation+4.72e-01

Pos logit contributions
dash+0.041
hell+0.041
undo+0.040
 ALEC+0.039
boro+0.038
Neg logit contributions
 fins-0.057
ities-0.057
 Advantage-0.055
isite-0.055
iaz-0.054
Token
Token ID198
Feature activation+8.51e-01

Pos logit contributions
ities+1.615
 fins+1.614
isite+1.552
 Advantage+1.551
iaz+1.525
Neg logit contributions
dash-1.121
hell-1.120
undo-1.112
 ALEC-1.072
boro-1.052
TokenFlag
Token ID34227
Feature activation-3.65e-01

Pos logit contributions
ities+2.105
 fins+2.067
isite+1.986
 Advantage+1.962
ity+1.954
Neg logit contributions
hell-2.780
dash-2.773
undo-2.763
 ALEC-2.735
boro-2.669
Token Reply
Token ID14883
Feature activation+2.60e+00

Pos logit contributions
undo+1.174
hell+1.172
dash+1.169
 ALEC+1.156
boro+1.130
Neg logit contributions
 fins-0.936
ities-0.926
isite-0.903
iaz-0.874
 Advantage-0.868
Token
Token ID198
Feature activation+6.86e-01

Pos logit contributions
ities+7.166
 fins+6.940
 Advantage+6.879
ity+6.797
 Flames+6.471
Neg logit contributions
hell-7.144
undo-7.132
dash-7.119
acus-7.014
FTWARE-6.912
Token
Token ID198
Feature activation+9.85e-01

Pos logit contributions
ities+2.297
 fins+2.281
 Advantage+2.196
isite+2.190
ity+2.167
Neg logit contributions
dash-1.675
undo-1.668
hell-1.667
 ALEC-1.606
boro-1.574
Token55
Token ID2816
Feature activation+8.36e-01

Pos logit contributions
ities+2.498
 fins+2.443
 Advantage+2.370
ity+2.365
isite+2.360
Neg logit contributions
undo-3.111
dash-3.083
hell-3.079
 ALEC-3.036
boro-2.955
Token Recommend
Token ID30361
Feature activation+1.15e+00

Pos logit contributions
ities+2.047
 fins+2.041
 Advantage+1.944
isite+1.940
ity+1.893
Neg logit contributions
dash-2.805
hell-2.788
undo-2.761
 ALEC-2.682
boro-2.658
Token
Token ID198
Feature activation+5.99e-01

Pos logit contributions
ities+3.747
 fins+3.681
 Advantage+3.555
ity+3.552
isite+3.535
Neg logit contributions
dash-2.890
hell-2.875
undo-2.859
 ALEC-2.760
boro-2.697
Token in
Token ID287
Feature activation+3.68e-01

Pos logit contributions
 fins+1.213
ities+1.204
 Advantage+1.129
ity+1.116
iaz+1.116
Neg logit contributions
undo-1.457
dash-1.456
hell-1.456
 ALEC-1.415
boro-1.387
Token betting
Token ID22908
Feature activation-1.21e+00

Pos logit contributions
 fins+1.079
ities+1.064
 Advantage+1.019
ity+1.008
isite+0.995
Neg logit contributions
undo-1.073
hell-1.071
dash-1.069
 ALEC-1.025
boro-1.020
Token with
Token ID351
Feature activation+1.69e-01

Pos logit contributions
dash+3.261
hell+3.259
undo+3.219
 ALEC+3.136
boro+3.076
Neg logit contributions
ities-3.724
 fins-3.719
isite-3.640
 Advantage-3.583
pta-3.560
Token a
Token ID257
Feature activation+3.98e-01

Pos logit contributions
 fins+0.462
ities+0.458
 Advantage+0.437
isite+0.432
ity+0.425
Neg logit contributions
hell-0.527
dash-0.523
undo-0.521
 ALEC-0.503
boro-0.500
Token particular
Token ID1948
Feature activation+9.38e-01

Pos logit contributions
 fins+1.100
ities+1.094
isite+1.043
 Advantage+1.037
ity+1.020
Neg logit contributions
hell-1.229
dash-1.212
undo-1.208
 ALEC-1.168
boro-1.156
Token reputation
Token ID8507
Feature activation+2.50e+00

Pos logit contributions
ities+1.974
 fins+1.918
ity+1.855
 Advantage+1.814
isite+1.793
Neg logit contributions
hell-3.585
dash-3.498
undo-3.482
boro-3.365
 ALEC-3.349
Token as
Token ID355
Feature activation+4.47e-01

Pos logit contributions
ities+6.198
 fins+6.110
ity+5.878
arily+5.736
 Advantage+5.550
Neg logit contributions
dash-7.695
undo-7.650
hell-7.650
acus-7.494
FTWARE-7.475
Token in
Token ID287
Feature activation+6.09e-01

Pos logit contributions
 fins+1.335
ities+1.299
 Advantage+1.263
isite+1.230
ity+1.227
Neg logit contributions
undo-1.288
hell-1.286
dash-1.278
boro-1.222
 ALEC-1.214
Token-
Token ID12
Feature activation-3.97e-01

Pos logit contributions
 fins+1.636
ities+1.609
 Advantage+1.549
isite+1.527
ity+1.521
Neg logit contributions
undo-1.910
hell-1.888
dash-1.876
 ALEC-1.826
boro-1.811
Tokenplay
Token ID1759
Feature activation-2.20e-02

Pos logit contributions
undo+0.858
hell+0.847
 ALEC+0.838
dash+0.837
boro+0.798
Neg logit contributions
 fins-1.441
ities-1.441
 Advantage-1.386
isite-1.385
ity-1.370
Token football
Token ID4346
Feature activation+8.05e-01

Pos logit contributions
dash+0.054
undo+0.054
hell+0.054
 ALEC+0.052
boro+0.051
Neg logit contributions
 fins-0.075
ities-0.074
 Advantage-0.071
isite-0.071
iaz-0.070
Token,
Token ID11
Feature activation+4.87e-03

Pos logit contributions
ities+0.530
 fins+0.529
 Advantage+0.498
isite+0.495
ity+0.493
Neg logit contributions
dash-0.503
hell-0.500
undo-0.498
 ALEC-0.481
boro-0.473
Token with
Token ID351
Feature activation+3.92e-01

Pos logit contributions
 fins+0.014
ities+0.014
isite+0.013
 Advantage+0.013
ity+0.013
Neg logit contributions
dash-0.014
hell-0.014
undo-0.014
 ALEC-0.014
boro-0.014
Token this
Token ID428
Feature activation+5.90e-01

Pos logit contributions
 fins+1.176
ities+1.167
 Advantage+1.115
isite+1.112
ity+1.091
Neg logit contributions
hell-1.121
dash-1.119
undo-1.109
 ALEC-1.066
boro-1.053
Token map
Token ID3975
Feature activation-6.57e-01

Pos logit contributions
 fins+1.682
ities+1.680
 Advantage+1.600
isite+1.599
ity+1.580
Neg logit contributions
hell-1.744
dash-1.740
undo-1.712
 ALEC-1.650
boro-1.650
Token of
Token ID286
Feature activation+6.48e-01

Pos logit contributions
dash+1.784
hell+1.779
undo+1.764
 ALEC+1.709
boro+1.683
Neg logit contributions
 fins-2.041
ities-2.035
isite-1.958
 Advantage-1.948
iaz-1.913
Token Brigham
Token ID37434
Feature activation+2.48e+00

Pos logit contributions
ities+1.705
 fins+1.689
 Advantage+1.618
isite+1.600
ity+1.585
Neg logit contributions
dash-2.101
undo-2.059
hell-2.050
 ALEC-1.956
boro-1.931
Token City
Token ID2254
Feature activation+3.55e-01

Pos logit contributions
ities+5.202
 Advantage+4.877
ity+4.839
 fins+4.721
isite+4.510
Neg logit contributions
undo-8.791
dash-8.689
hell-8.598
FTWARE-8.562
 ALEC-8.400
Token,
Token ID11
Feature activation+9.06e-01

Pos logit contributions
ities+1.134
 fins+1.124
 Advantage+1.086
isite+1.078
ity+1.067
Neg logit contributions
dash-0.932
undo-0.924
hell-0.923
 ALEC-0.879
boro-0.860
Token Utah
Token ID10202
Feature activation+1.33e+00

Pos logit contributions
ities+2.615
 fins+2.615
 Advantage+2.503
isite+2.449
ity+2.445
Neg logit contributions
hell-2.621
dash-2.615
undo-2.579
boro-2.448
 ALEC-2.447
Token [
Token ID685
Feature activation-2.22e-01

Pos logit contributions
ities+4.006
 fins+3.922
 Advantage+3.833
ity+3.803
isite+3.793
Neg logit contributions
dash-3.605
undo-3.546
hell-3.518
 ALEC-3.361
FTWARE-3.345
Tokeng
Token ID70
Feature activation-4.56e-01

Pos logit contributions
dash+0.643
hell+0.642
undo+0.635
 ALEC+0.625
boro+0.613
Neg logit contributions
 fins-0.642
ities-0.641
isite-0.615
 Advantage-0.612
pta-0.601
Token.
Token ID13
Feature activation-6.32e-02

Pos logit contributions
ities+2.873
 fins+2.815
 Advantage+2.691
ity+2.651
isite+2.597
Neg logit contributions
undo-2.497
hell-2.484
dash-2.468
 ALEC-2.350
boro-2.341
Token Flag
Token ID19762
Feature activation-1.59e-01

Pos logit contributions
dash+0.189
hell+0.189
undo+0.188
 ALEC+0.181
boro+0.180
Neg logit contributions
 fins-0.177
ities-0.177
 Advantage-0.170
isite-0.169
iaz-0.165
Token
Token ID198
Feature activation+4.78e-01

Pos logit contributions
hell+0.362
dash+0.361
undo+0.359
 ALEC+0.347
boro+0.339
Neg logit contributions
 fins-0.564
ities-0.561
isite-0.546
 Advantage-0.539
pta-0.534
Token
Token ID198
Feature activation+9.26e-01

Pos logit contributions
ities+1.633
 fins+1.630
isite+1.568
 Advantage+1.566
iaz+1.540
Neg logit contributions
dash-1.137
hell-1.136
undo-1.128
 ALEC-1.088
boro-1.067
TokenFlag
Token ID34227
Feature activation-2.54e-01

Pos logit contributions
ities+2.260
 fins+2.199
isite+2.116
ity+2.104
 Advantage+2.083
Neg logit contributions
hell-3.045
undo-3.037
dash-3.029
 ALEC-3.018
boro-2.926
Token Reply
Token ID14883
Feature activation+2.45e+00

Pos logit contributions
dash+0.824
hell+0.823
undo+0.820
 ALEC+0.806
boro+0.792
Neg logit contributions
 fins-0.652
ities-0.642
isite-0.633
iaz-0.611
pta-0.609
Token
Token ID198
Feature activation+7.18e-01

Pos logit contributions
ities+6.846
 fins+6.548
ity+6.547
 Advantage+6.387
arily+6.124
Neg logit contributions
undo-6.744
dash-6.712
hell-6.703
acus-6.629
FTWARE-6.552
Token
Token ID198
Feature activation+1.05e+00

Pos logit contributions
ities+2.396
 fins+2.375
 Advantage+2.286
isite+2.278
ity+2.260
Neg logit contributions
dash-1.760
undo-1.753
hell-1.751
 ALEC-1.688
boro-1.655
Token19
Token ID1129
Feature activation-3.30e-01

Pos logit contributions
ities+2.720
 fins+2.646
ity+2.569
 Advantage+2.557
isite+2.543
Neg logit contributions
undo-3.304
dash-3.288
hell-3.268
 ALEC-3.231
boro-3.146
Token Recommend
Token ID30361
Feature activation+6.88e-01

Pos logit contributions
hell+1.016
dash+1.013
undo+1.009
 ALEC+0.984
boro+0.970
Neg logit contributions
 fins-0.899
ities-0.893
isite-0.858
 Advantage-0.846
iaz-0.842
Token
Token ID198
Feature activation+4.98e-01

Pos logit contributions
ities+2.333
 fins+2.321
 Advantage+2.234
isite+2.233
ity+2.200
Neg logit contributions
dash-1.661
hell-1.656
undo-1.643
 ALEC-1.586
boro-1.553
Token surface
Token ID4417
Feature activation-2.27e-01

Pos logit contributions
 fins+0.590
ities+0.586
isite+0.555
 Advantage+0.553
pta+0.542
Neg logit contributions
dash-0.693
hell-0.692
undo-0.689
 ALEC-0.669
boro-0.664
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
dash+0.590
hell+0.589
undo+0.584
 ALEC+0.565
boro+0.556
Neg logit contributions
 fins-0.732
ities-0.728
isite-0.702
 Advantage-0.699
iaz-0.687
Token
Token ID198
Feature activation+1.36e-01

Pos logit contributions
ities+0.042
 fins+0.042
 Advantage+0.040
isite+0.040
ity+0.039
Neg logit contributions
dash-0.032
hell-0.032
undo-0.032
 ALEC-0.030
boro-0.030
Token
Token ID198
Feature activation+4.82e-01

Pos logit contributions
 fins+0.487
ities+0.481
isite+0.471
 Advantage+0.466
iaz+0.461
Neg logit contributions
hell-0.306
dash-0.305
undo-0.300
 ALEC-0.290
boro-0.284
TokenMedia
Token ID13152
Feature activation+5.62e-01

Pos logit contributions
ities+1.302
 fins+1.257
ity+1.214
isite+1.203
pta+1.177
Neg logit contributions
 ALEC-1.484
dash-1.468
undo-1.467
hell-1.451
boro-1.439
Token playback
Token ID16388
Feature activation+2.45e+00

Pos logit contributions
 fins+1.132
ities+1.119
 Advantage+1.046
isite+1.020
ity+0.998
Neg logit contributions
dash-2.147
undo-2.133
hell-2.129
 ALEC-2.074
boro-2.061
Token is
Token ID318
Feature activation+2.83e-01

Pos logit contributions
ities+5.968
 fins+5.854
 Advantage+5.594
ity+5.538
isite+5.518
Neg logit contributions
undo-7.887
dash-7.857
hell-7.824
FTWARE-7.477
 ALEC-7.437
Token unsupported
Token ID24222
Feature activation+2.70e-01

Pos logit contributions
 fins+0.703
ities+0.698
isite+0.677
 Advantage+0.661
iaz+0.654
Neg logit contributions
dash-0.943
hell-0.937
undo-0.934
 ALEC-0.915
boro-0.895
Token on
Token ID319
Feature activation-5.50e-02

Pos logit contributions
 fins+0.810
ities+0.806
isite+0.777
 Advantage+0.772
iaz+0.759
Neg logit contributions
dash-0.759
hell-0.759
undo-0.751
 ALEC-0.730
boro-0.719
Token your
Token ID534
Feature activation+4.67e-01

Pos logit contributions
dash+0.106
hell+0.104
undo+0.103
 ALEC+0.099
boro+0.095
Neg logit contributions
 fins-0.214
ities-0.213
isite-0.210
 Advantage-0.207
iaz-0.206
Token device
Token ID3335
Feature activation+1.03e+00

Pos logit contributions
 fins+1.008
ities+0.997
isite+0.960
 Advantage+0.942
iaz+0.928
Neg logit contributions
dash-1.705
hell-1.694
undo-1.685
 ALEC-1.655
boro-1.629
Token energy
Token ID2568
Feature activation+8.11e-02

Pos logit contributions
 fins+0.420
ities+0.419
 Advantage+0.401
isite+0.396
ity+0.394
Neg logit contributions
dash-0.333
hell-0.332
undo-0.328
 ALEC-0.316
boro-0.315
Token goals
Token ID4661
Feature activation+3.81e-01

Pos logit contributions
 fins+0.187
ities+0.187
 Advantage+0.177
isite+0.173
ity+0.170
Neg logit contributions
hell-0.287
dash-0.285
undo-0.284
 ALEC-0.278
boro-0.275
Token.
Token ID13
Feature activation+2.22e-02

Pos logit contributions
ities+1.232
 fins+1.221
 Advantage+1.168
isite+1.164
iaz+1.161
Neg logit contributions
dash-0.981
hell-0.972
undo-0.970
 ALEC-0.936
boro-0.934
Token<|endoftext|>
Token ID50256
Feature activation-4.01e-01

Pos logit contributions
ities+0.069
 fins+0.069
 Advantage+0.067
isite+0.066
pta+0.065
Neg logit contributions
hell-0.060
dash-0.060
undo-0.060
 ALEC-0.057
boro-0.057
TokenMedia
Token ID13152
Feature activation-2.98e-01

Pos logit contributions
dash+1.180
hell+1.178
undo+1.175
 ALEC+1.159
boro+1.130
Neg logit contributions
ities-1.137
 fins-1.129
isite-1.087
 Advantage-1.072
iaz-1.064
Token playback
Token ID16388
Feature activation+2.43e+00

Pos logit contributions
dash+1.099
hell+1.095
undo+1.093
 ALEC+1.067
boro+1.054
Neg logit contributions
 fins-0.634
ities-0.631
isite-0.594
 Advantage-0.592
iaz-0.577
Token is
Token ID318
Feature activation+1.19e-01

Pos logit contributions
ities+5.656
 fins+5.473
isite+5.303
 Advantage+5.262
ity+5.257
Neg logit contributions
dash-8.165
undo-8.094
hell-7.991
FTWARE-7.648
 ALEC-7.568
Token unsupported
Token ID24222
Feature activation+2.18e-01

Pos logit contributions
 fins+0.258
ities+0.258
 Advantage+0.243
isite+0.242
pta+0.235
Neg logit contributions
dash-0.430
hell-0.430
undo-0.427
 ALEC-0.415
boro-0.413
Token on
Token ID319
Feature activation-2.35e-01

Pos logit contributions
 fins+0.659
ities+0.654
isite+0.633
 Advantage+0.628
iaz+0.618
Neg logit contributions
hell-0.609
dash-0.609
undo-0.601
 ALEC-0.585
boro-0.576
Token your
Token ID534
Feature activation+2.95e-01

Pos logit contributions
dash+0.440
hell+0.429
undo+0.424
 ALEC+0.410
boro+0.389
Neg logit contributions
 fins-0.929
ities-0.923
isite-0.910
 Advantage-0.902
iaz-0.896
Token device
Token ID3335
Feature activation+1.09e+00

Pos logit contributions
 fins+0.646
ities+0.638
isite+0.616
 Advantage+0.604
pta+0.597
Neg logit contributions
dash-1.071
hell-1.061
undo-1.057
 ALEC-1.041
boro-1.023
Token on
Token ID319
Feature activation+1.34e-01

Pos logit contributions
hell+1.631
dash+1.631
undo+1.602
 ALEC+1.566
boro+1.540
Neg logit contributions
 fins-1.687
ities-1.675
isite-1.624
 Advantage-1.617
iaz-1.592
Token Twitter
Token ID3009
Feature activation+5.75e-01

Pos logit contributions
 fins+0.284
ities+0.283
 Advantage+0.265
isite+0.265
iaz+0.257
Neg logit contributions
hell-0.491
undo-0.491
dash-0.491
 ALEC-0.478
boro-0.474
Token.
Token ID13
Feature activation-2.21e-01

Pos logit contributions
ities+1.664
 fins+1.647
 Advantage+1.569
isite+1.555
ity+1.543
Neg logit contributions
undo-1.666
dash-1.658
hell-1.654
 ALEC-1.606
boro-1.592
Token<|endoftext|>
Token ID50256
Feature activation-4.07e-01

Pos logit contributions
dash+0.764
hell+0.763
undo+0.761
 ALEC+0.740
boro+0.731
Neg logit contributions
 fins-0.514
ities-0.514
 Advantage-0.488
isite-0.486
iaz-0.474
TokenMedia
Token ID13152
Feature activation-2.43e-01

Pos logit contributions
dash+1.200
hell+1.197
undo+1.195
 ALEC+1.181
boro+1.149
Neg logit contributions
ities-1.149
 fins-1.141
isite-1.098
 Advantage-1.081
iaz-1.075
Token playback
Token ID16388
Feature activation+2.39e+00

Pos logit contributions
dash+0.905
undo+0.900
hell+0.900
 ALEC+0.879
boro+0.867
Neg logit contributions
 fins-0.511
ities-0.509
 Advantage-0.477
isite-0.476
iaz-0.463
Token is
Token ID318
Feature activation+3.85e-02

Pos logit contributions
ities+5.666
 fins+5.511
isite+5.318
 Advantage+5.302
ity+5.261
Neg logit contributions
dash-7.917
undo-7.833
hell-7.792
FTWARE-7.410
boro-7.350
Token unsupported
Token ID24222
Feature activation+1.97e-01

Pos logit contributions
 fins+0.084
ities+0.084
 Advantage+0.079
isite+0.079
iaz+0.077
Neg logit contributions
dash-0.139
hell-0.139
undo-0.138
 ALEC-0.134
boro-0.133
Token on
Token ID319
Feature activation-2.33e-01

Pos logit contributions
 fins+0.598
ities+0.593
isite+0.574
 Advantage+0.570
iaz+0.561
Neg logit contributions
dash-0.551
hell-0.550
undo-0.544
 ALEC-0.529
boro-0.520
Token your
Token ID534
Feature activation+1.83e-01

Pos logit contributions
dash+0.441
hell+0.431
undo+0.426
 ALEC+0.411
boro+0.392
Neg logit contributions
 fins-0.913
ities-0.907
isite-0.892
 Advantage-0.884
iaz-0.879
Token device
Token ID3335
Feature activation+1.06e+00

Pos logit contributions
 fins+0.408
ities+0.401
isite+0.390
 Advantage+0.381
pta+0.379
Neg logit contributions
dash-0.655
hell-0.646
undo-0.644
 ALEC-0.636
boro-0.623
Token especially
Token ID2592
Feature activation+2.22e-01

Pos logit contributions
 fins+1.180
ities+1.177
 Advantage+1.120
isite+1.112
ity+1.089
Neg logit contributions
dash-1.345
hell-1.335
undo-1.329
boro-1.293
 ALEC-1.282
Token for
Token ID329
Feature activation+5.16e-01

Pos logit contributions
 fins+0.629
ities+0.628
 Advantage+0.597
isite+0.591
ity+0.585
Neg logit contributions
dash-0.663
undo-0.661
hell-0.660
 ALEC-0.634
boro-0.632
Token the
Token ID262
Feature activation+4.43e-01

Pos logit contributions
 fins+1.479
ities+1.471
 Advantage+1.406
isite+1.389
ity+1.372
Neg logit contributions
undo-1.522
dash-1.519
hell-1.517
boro-1.459
 ALEC-1.428
Token legacy
Token ID10655
Feature activation+1.10e+00

Pos logit contributions
 fins+1.037
ities+1.029
 Advantage+0.974
isite+0.969
iaz+0.949
Neg logit contributions
dash-1.539
undo-1.538
hell-1.537
 ALEC-1.481
boro-1.481
Token and
Token ID290
Feature activation+5.72e-01

Pos logit contributions
ities+2.876
 fins+2.819
arily+2.715
 Advantage+2.706
ity+2.683
Neg logit contributions
undo-3.494
dash-3.491
hell-3.464
boro-3.389
acus-3.348
Token reputation
Token ID8507
Feature activation+2.37e+00

Pos logit contributions
ities+1.466
 fins+1.462
 Advantage+1.381
ity+1.366
isite+1.355
Neg logit contributions
dash-1.872
hell-1.863
undo-1.855
boro-1.789
 ALEC-1.774
Token of
Token ID286
Feature activation+1.06e+00

Pos logit contributions
ities+5.668
 fins+5.390
ity+5.229
arily+5.195
 Advantage+5.145
Neg logit contributions
dash-7.923
undo-7.860
hell-7.602
boro-7.597
acus-7.584
Token President
Token ID1992
Feature activation-4.98e-02

Pos logit contributions
 fins+2.998
ities+2.974
 Advantage+2.851
ity+2.802
isite+2.798
Neg logit contributions
hell-3.065
dash-3.055
undo-3.055
boro-2.957
FTWARE-2.876
Token Barack
Token ID8732
Feature activation+7.39e-01

Pos logit contributions
dash+0.134
hell+0.134
undo+0.133
 ALEC+0.128
boro+0.127
Neg logit contributions
 fins-0.155
ities-0.155
 Advantage-0.149
isite-0.149
iaz-0.146
Token Obama
Token ID2486
Feature activation+5.53e-01

Pos logit contributions
ities+2.457
 fins+2.438
 Advantage+2.372
isite+2.339
ity+2.313
Neg logit contributions
dash-1.840
hell-1.823
undo-1.815
 ALEC-1.730
boro-1.719
Token and
Token ID290
Feature activation-2.91e-01

Pos logit contributions
ities+1.719
 fins+1.693
 Advantage+1.642
ity+1.623
iaz+1.618
Neg logit contributions
dash-1.485
hell-1.477
undo-1.466
 ALEC-1.418
boro-1.393
Token language
Token ID3303
Feature activation+2.87e-01

Pos logit contributions
hell+0.422
dash+0.421
undo+0.417
 ALEC+0.407
boro+0.402
Neg logit contributions
 fins-0.295
ities-0.289
isite-0.285
 Advantage-0.279
pta-0.278
Token.
Token ID13
Feature activation+2.12e-01

Pos logit contributions
ities+0.873
 fins+0.871
isite+0.842
 Advantage+0.839
iaz+0.825
Neg logit contributions
dash-0.788
hell-0.787
undo-0.777
 ALEC-0.747
boro-0.741
Token -
Token ID532
Feature activation+5.63e-01

Pos logit contributions
ities+0.652
 fins+0.650
 Advantage+0.632
isite+0.620
pta+0.612
Neg logit contributions
dash-0.575
hell-0.573
undo-0.570
 ALEC-0.546
boro-0.541
Token Katherine
Token ID32719
Feature activation-1.31e-01

Pos logit contributions
ities+2.052
 fins+2.029
 Advantage+1.981
isite+1.944
ity+1.935
Neg logit contributions
dash-1.208
hell-1.208
undo-1.205
boro-1.135
 ALEC-1.134
Token d
Token ID288
Feature activation+1.61e+00

Pos logit contributions
hell+0.437
dash+0.436
undo+0.435
 ALEC+0.419
boro+0.417
Neg logit contributions
 fins-0.326
ities-0.323
 Advantage-0.309
isite-0.305
iaz-0.301
Token'
Token ID6
Feature activation+2.36e+00

Pos logit contributions
ities+4.441
 fins+4.338
 Advantage+4.129
ity+4.128
iaz+4.119
Neg logit contributions
undo-4.803
hell-4.792
dash-4.734
 ALEC-4.612
boro-4.543
TokenEnt
Token ID14539
Feature activation+1.76e-01

Pos logit contributions
ities+4.484
 fins+4.160
ity+4.137
isite+4.065
 Advantage+3.989
Neg logit contributions
dash-8.546
undo-8.542
hell-8.391
 ALEC-8.290
boro-8.217
Tokenrem
Token ID2787
Feature activation+8.75e-01

Pos logit contributions
 fins+0.708
ities+0.698
 Advantage+0.684
isite+0.680
iaz+0.670
Neg logit contributions
dash-0.327
hell-0.326
undo-0.322
 ALEC-0.300
boro-0.298
Tokenont
Token ID756
Feature activation+8.67e-01

Pos logit contributions
ities+2.679
 fins+2.655
isite+2.599
pta+2.533
 Advantage+2.520
Neg logit contributions
dash-2.370
hell-2.343
undo-2.332
 ALEC-2.310
boro-2.224
Token,
Token ID11
Feature activation+4.87e-01

Pos logit contributions
ities+2.690
 fins+2.660
 Advantage+2.568
ity+2.525
isite+2.525
Neg logit contributions
dash-2.321
undo-2.321
hell-2.303
FTWARE-2.179
 ALEC-2.177
Token commissioner
Token ID16248
Feature activation+1.89e-01

Pos logit contributions
ities+1.377
 fins+1.371
 Advantage+1.333
isite+1.309
pta+1.278
Neg logit contributions
undo-1.444
dash-1.435
hell-1.432
boro-1.363
 ALEC-1.361
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
ities+1.662
 fins+1.623
 Advantage+1.623
isite+1.583
ity+1.577
Neg logit contributions
dash-1.565
undo-1.555
hell-1.537
 ALEC-1.431
acus-1.430
Token
Token ID198
Feature activation+3.07e-01

Pos logit contributions
hell+0.525
dash+0.523
undo+0.510
 ALEC+0.495
boro+0.486
Neg logit contributions
 fins-0.918
ities-0.898
isite-0.891
 Advantage-0.877
 mosqu-0.874
TokenIn
Token ID818
Feature activation+1.47e-01

Pos logit contributions
ities+0.844
 fins+0.813
isite+0.794
ity+0.789
iaz+0.774
Neg logit contributions
dash-0.930
undo-0.928
hell-0.925
 ALEC-0.920
boro-0.890
Token 1973
Token ID15674
Feature activation-6.95e-01

Pos logit contributions
ities+0.410
 fins+0.409
 Advantage+0.389
isite+0.388
iaz+0.379
Neg logit contributions
dash-0.445
undo-0.444
hell-0.442
 ALEC-0.427
boro-0.422
Token,
Token ID11
Feature activation-4.54e-01

Pos logit contributions
dash+1.822
hell+1.809
undo+1.803
 ALEC+1.724
boro+1.699
Neg logit contributions
ities-2.233
 fins-2.231
isite-2.151
 Advantage-2.142
pta-2.098
Token Beth
Token ID19223
Feature activation-2.50e+00

Pos logit contributions
dash+1.305
hell+1.294
undo+1.289
 ALEC+1.234
boro+1.222
Neg logit contributions
 fins-1.343
ities-1.340
isite-1.287
 Advantage-1.284
pta-1.254
Tokenune
Token ID1726
Feature activation-6.96e-01

Pos logit contributions
hell+3.155
undo+3.141
dash+2.969
boro+2.784
 ALEC+2.582
Neg logit contributions
 fins-11.097
 mosqu-10.914
ities-10.725
 inflamm-10.700
isite-10.687
Token was
Token ID373
Feature activation-4.24e-01

Pos logit contributions
hell+1.762
dash+1.762
undo+1.743
 ALEC+1.688
boro+1.659
Neg logit contributions
 fins-2.281
ities-2.269
isite-2.196
 Advantage-2.182
iaz-2.149
Token induct
Token ID28948
Feature activation+3.82e-01

Pos logit contributions
dash+1.106
hell+1.090
undo+1.083
boro+1.032
 ALEC+1.032
Neg logit contributions
 fins-1.378
ities-1.368
isite-1.311
 Advantage-1.311
ity-1.292
Tokened
Token ID276
Feature activation-4.08e-02

Pos logit contributions
ities+0.843
 fins+0.840
isite+0.795
 Advantage+0.781
iaz+0.774
Neg logit contributions
hell-1.373
dash-1.370
undo-1.363
 ALEC-1.331
boro-1.321
Token into
Token ID656
Feature activation+3.47e-02

Pos logit contributions
dash+0.115
undo+0.114
hell+0.114
 ALEC+0.108
boro+0.108
Neg logit contributions
ities-0.123
 fins-0.123
isite-0.117
 Advantage-0.117
ity-0.116
Token
Token ID447
Feature activation-3.69e-01

Pos logit contributions
dash+0.667
hell+0.667
undo+0.661
 ALEC+0.641
boro+0.634
Neg logit contributions
 fins-0.661
ities-0.657
isite-0.631
 Advantage-0.628
iaz-0.616
Token
Token ID251
Feature activation+1.75e-02

Pos logit contributions
hell+1.178
dash+1.177
undo+1.161
 ALEC+1.139
boro+1.123
Neg logit contributions
 fins-0.973
ities-0.962
 Advantage-0.922
isite-0.918
iaz-0.901
Token said
Token ID531
Feature activation-1.10e+00

Pos logit contributions
 fins+0.049
ities+0.049
 Advantage+0.047
isite+0.047
ity+0.046
Neg logit contributions
dash-0.052
hell-0.052
undo-0.052
 ALEC-0.051
boro-0.050
Token Sen
Token ID2311
Feature activation-1.18e+00

Pos logit contributions
hell+3.172
dash+3.166
undo+3.133
 ALEC+3.062
boro+3.004
Neg logit contributions
 fins-3.217
ities-3.193
isite-3.089
 Advantage-3.053
pta-3.003
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
hell+2.698
dash+2.692
undo+2.666
 ALEC+2.573
boro+2.520
Neg logit contributions
 fins-4.148
ities-4.117
isite-3.991
 Advantage-3.981
iaz-3.908
Token Kay
Token ID17356
Feature activation-2.41e+00

Pos logit contributions
hell+2.910
dash+2.903
undo+2.857
 ALEC+2.845
boro+2.766
Neg logit contributions
 fins-3.704
ities-3.662
isite-3.564
 Advantage-3.510
pta-3.486
Token Bailey
Token ID20330
Feature activation-2.86e-01

Pos logit contributions
undo+6.619
hell+6.564
dash+6.417
boro+6.407
 ALEC+6.373
Neg logit contributions
 fins-6.884
isite-6.721
ities-6.709
arily-6.556
pta-6.502
Token Hutch
Token ID30492
Feature activation+5.64e-01

Pos logit contributions
undo+1.144
dash+1.141
hell+1.137
 ALEC+1.106
boro+1.093
Neg logit contributions
 fins-0.519
ities-0.517
 Advantage-0.484
isite-0.473
iaz-0.468
Tokenison
Token ID1653
Feature activation-4.92e-01

Pos logit contributions
ities+1.346
 fins+1.258
ity+1.209
iaz+1.207
isite+1.186
Neg logit contributions
undo-2.037
dash-1.984
hell-1.975
boro-1.933
 ALEC-1.897
Token (
Token ID357
Feature activation-3.66e-01

Pos logit contributions
dash+1.323
hell+1.321
undo+1.312
 ALEC+1.265
boro+1.247
Neg logit contributions
 fins-1.532
ities-1.528
 Advantage-1.466
isite-1.465
iaz-1.446
TokenR
Token ID49
Feature activation-8.33e-01

Pos logit contributions
hell+1.242
dash+1.242
undo+1.239
 ALEC+1.204
boro+1.186
Neg logit contributions
ities-0.877
 fins-0.877
 Advantage-0.833
isite-0.828
iaz-0.815
TokenThe
Token ID464
Feature activation-1.60e-01

Pos logit contributions
dash+1.154
hell+1.150
undo+1.148
 ALEC+1.127
boro+1.110
Neg logit contributions
ities-0.998
 fins-0.985
isite-0.949
 Advantage-0.937
ity-0.924
Token FCC
Token ID15915
Feature activation+2.95e-02

Pos logit contributions
hell+0.489
dash+0.489
undo+0.485
 ALEC+0.471
boro+0.466
Neg logit contributions
 fins-0.439
ities-0.437
isite-0.419
 Advantage-0.417
iaz-0.408
Token accused
Token ID5371
Feature activation-7.19e-01

Pos logit contributions
 fins+0.091
ities+0.091
 Advantage+0.087
isite+0.087
ity+0.085
Neg logit contributions
dash-0.081
hell-0.081
undo-0.080
 ALEC-0.077
boro-0.076
Token California
Token ID3442
Feature activation-5.79e-01

Pos logit contributions
dash+1.974
hell+1.974
undo+1.953
 ALEC+1.901
boro+1.867
Neg logit contributions
 fins-2.205
ities-2.192
isite-2.118
 Advantage-2.098
iaz-2.070
Token-
Token ID12
Feature activation-1.24e+00

Pos logit contributions
dash+1.708
hell+1.707
undo+1.690
 ALEC+1.640
boro+1.618
Neg logit contributions
 fins-1.659
ities-1.652
isite-1.586
 Advantage-1.585
iaz-1.548
Tokenbased
Token ID3106
Feature activation-2.38e+00

Pos logit contributions
dash+3.443
hell+3.443
undo+3.391
 ALEC+3.289
boro+3.257
Neg logit contributions
 fins-3.764
ities-3.703
isite-3.579
 Advantage-3.550
iaz-3.512
Token Total
Token ID7472
Feature activation-6.90e-01

Pos logit contributions
 ALEC+6.743
dash+6.628
hell+6.601
undo+6.501
boro+6.317
Neg logit contributions
 fins-6.570
isite-6.520
ities-6.422
iaz-6.203
arily-6.083
Token Call
Token ID4889
Feature activation+7.07e-01

Pos logit contributions
hell+2.090
dash+2.089
undo+2.074
 ALEC+2.016
boro+1.986
Neg logit contributions
 fins-1.921
ities-1.905
isite-1.836
 Advantage-1.812
iaz-1.787
Token Mobile
Token ID12173
Feature activation+3.82e-01

Pos logit contributions
ities+1.901
 Advantage+1.876
 fins+1.863
iaz+1.779
isite+1.766
Neg logit contributions
dash-2.189
hell-2.165
 ALEC-2.102
undo-2.101
boro-2.075
Token of
Token ID286
Feature activation+8.62e-01

Pos logit contributions
ities+1.061
 fins+1.050
 Advantage+1.043
isite+0.989
ity+0.989
Neg logit contributions
dash-1.155
hell-1.136
undo-1.115
 ALEC-1.098
boro-1.087
Token fraud
Token ID7394
Feature activation+9.10e-02

Pos logit contributions
 fins+2.364
ities+2.362
 Advantage+2.292
ity+2.185
isite+2.163
Neg logit contributions
dash-2.652
hell-2.616
undo-2.601
boro-2.482
 ALEC-2.441
Token slavery
Token ID13503
Feature activation-4.56e-02

Pos logit contributions
 fins+0.729
ities+0.728
 Advantage+0.692
ity+0.683
isite+0.682
Neg logit contributions
dash-0.742
undo-0.737
hell-0.736
boro-0.701
 ALEC-0.692
Token.
Token ID13
Feature activation+3.75e-02

Pos logit contributions
dash+0.125
undo+0.123
hell+0.123
 ALEC+0.119
boro+0.117
Neg logit contributions
 fins-0.142
ities-0.141
 Advantage-0.135
isite-0.134
ity-0.132
Token The
Token ID383
Feature activation+5.98e-01

Pos logit contributions
ities+0.106
 fins+0.105
 Advantage+0.103
isite+0.100
ity+0.099
Neg logit contributions
dash-0.112
undo-0.112
hell-0.111
boro-0.106
 ALEC-0.106
Token 18
Token ID1248
Feature activation-7.51e-01

Pos logit contributions
ities+1.625
 fins+1.601
 Advantage+1.527
isite+1.515
ity+1.491
Neg logit contributions
dash-1.868
hell-1.847
undo-1.846
boro-1.766
 ALEC-1.764
Token76
Token ID4304
Feature activation-1.09e-01

Pos logit contributions
dash+2.121
hell+2.120
undo+2.102
 ALEC+2.042
boro+2.010
Neg logit contributions
 fins-2.242
ities-2.231
isite-2.147
 Advantage-2.135
iaz-2.097
Token Freed
Token ID38728
Feature activation-2.34e+00

Pos logit contributions
dash+0.330
hell+0.329
undo+0.326
 ALEC+0.314
boro+0.312
Neg logit contributions
ities-0.305
 fins-0.302
 Advantage-0.289
isite-0.289
ity-0.282
Tokenmen
Token ID3653
Feature activation-8.03e-01

Pos logit contributions
hell+5.906
dash+5.844
undo+5.834
 ALEC+5.621
boro+5.556
Neg logit contributions
 fins-7.601
ities-7.355
isite-7.329
pta-7.193
 Advantage-7.104
Token
Token ID447
Feature activation-8.93e-02

Pos logit contributions
hell+2.185
dash+2.184
undo+2.160
 ALEC+2.091
boro+2.053
Neg logit contributions
ities-2.486
 fins-2.478
isite-2.392
 Advantage-2.387
iaz-2.330
Token
Token ID247
Feature activation-3.51e-01

Pos logit contributions
dash+0.328
hell+0.326
undo+0.324
 ALEC+0.319
boro+0.314
Neg logit contributions
 fins-0.192
ities-0.189
 Advantage-0.181
isite-0.180
iaz-0.176
Tokens
Token ID82
Feature activation+4.06e-01

Pos logit contributions
dash+1.067
hell+1.066
undo+1.056
 ALEC+1.031
boro+1.014
Neg logit contributions
ities-0.970
 fins-0.969
isite-0.928
 Advantage-0.922
iaz-0.904
Token Memorial
Token ID14861
Feature activation-2.14e-01

Pos logit contributions
ities+1.162
 Advantage+1.117
 fins+1.112
isite+1.080
iaz+1.078
Neg logit contributions
dash-1.197
undo-1.191
hell-1.171
 ALEC-1.144
FTWARE-1.118
Token:
Token ID25
Feature activation+8.15e-01

Pos logit contributions
dash+0.308
hell+0.308
undo+0.305
 ALEC+0.296
boro+0.291
Neg logit contributions
 fins-0.340
ities-0.338
 Advantage-0.326
isite-0.325
ity-0.316
Token The
Token ID383
Feature activation+1.24e+00

Pos logit contributions
 fins+2.171
ities+2.157
 Advantage+2.141
isite+2.042
ity+2.027
Neg logit contributions
dash-2.554
undo-2.510
hell-2.483
 ALEC-2.397
boro-2.380
Token Ride
Token ID21640
Feature activation-1.71e+00

Pos logit contributions
 fins+3.262
 Advantage+3.221
ities+3.209
isite+3.044
ity+3.044
Neg logit contributions
dash-3.919
hell-3.825
undo-3.808
 ALEC-3.720
boro-3.664
Token.
Token ID13
Feature activation-2.77e-01

Pos logit contributions
dash+4.530
hell+4.497
undo+4.442
 ALEC+4.278
boro+4.246
Neg logit contributions
ities-5.289
 fins-5.253
isite-5.103
pta-5.025
iaz-5.009
Token The
Token ID383
Feature activation+7.87e-03

Pos logit contributions
dash+0.826
hell+0.825
undo+0.819
 ALEC+0.793
boro+0.784
Neg logit contributions
 fins-0.782
ities-0.778
 Advantage-0.748
isite-0.748
pta-0.727
Token ride
Token ID6594
Feature activation-2.27e+00

Pos logit contributions
 fins+0.026
ities+0.025
 Advantage+0.024
isite+0.024
ity+0.024
Neg logit contributions
hell-0.020
dash-0.020
undo-0.020
 ALEC-0.019
boro-0.019
Token includes
Token ID3407
Feature activation-5.10e-01

Pos logit contributions
dash+5.849
hell+5.772
undo+5.702
boro+5.585
 ALEC+5.559
Neg logit contributions
ities-6.743
isite-6.731
 fins-6.663
pta-6.646
iaz-6.640
Token a
Token ID257
Feature activation-3.23e-01

Pos logit contributions
hell+1.510
dash+1.509
undo+1.498
 ALEC+1.454
boro+1.435
Neg logit contributions
 fins-1.463
ities-1.450
isite-1.392
 Advantage-1.384
iaz-1.357
Token rotating
Token ID24012
Feature activation-1.27e+00

Pos logit contributions
hell+0.957
dash+0.956
undo+0.949
 ALEC+0.923
boro+0.910
Neg logit contributions
 fins-0.926
ities-0.917
isite-0.881
 Advantage-0.876
iaz-0.860
Token platform
Token ID3859
Feature activation-6.42e-01

Pos logit contributions
dash+3.845
hell+3.828
undo+3.810
 ALEC+3.727
boro+3.642
Neg logit contributions
ities-3.442
 fins-3.426
isite-3.343
pta-3.286
 Advantage-3.272
Token that
Token ID326
Feature activation-2.43e-01

Pos logit contributions
dash+1.824
hell+1.824
undo+1.807
 ALEC+1.756
boro+1.729
Neg logit contributions
 fins-1.906
ities-1.895
isite-1.826
 Advantage-1.814
iaz-1.783
TokenOUNT
Token ID28270
Feature activation-6.70e-01

Pos logit contributions
ities+0.172
 fins+0.170
isite+0.162
 Advantage+0.162
ity+0.160
Neg logit contributions
dash-0.143
hell-0.141
undo-0.140
 ALEC-0.136
boro-0.135
Token (
Token ID357
Feature activation+1.15e-01

Pos logit contributions
dash+1.876
hell+1.875
undo+1.857
 ALEC+1.805
boro+1.776
Neg logit contributions
 fins-2.014
ities-2.003
isite-1.932
 Advantage-1.919
iaz-1.888
Token *
Token ID1635
Feature activation-1.29e+00

Pos logit contributions
 fins+0.305
ities+0.302
isite+0.289
 Advantage+0.288
pta+0.280
Neg logit contributions
hell-0.368
dash-0.367
undo-0.361
 ALEC-0.353
boro-0.350
Token )
Token ID1267
Feature activation+3.32e-01

Pos logit contributions
dash+3.345
hell+3.333
undo+3.318
 ALEC+3.218
boro+3.153
Neg logit contributions
 fins-4.068
ities-4.054
isite-3.949
 Advantage-3.903
iaz-3.869
Token AS
Token ID7054
Feature activation+1.46e-01

Pos logit contributions
 fins+0.921
ities+0.907
 Advantage+0.875
isite+0.865
pta+0.846
Neg logit contributions
hell-1.016
dash-1.013
undo-1.002
boro-0.967
 ALEC-0.965
Token count
Token ID954
Feature activation-2.26e+00

Pos logit contributions
 fins+0.409
ities+0.406
isite+0.389
 Advantage+0.388
ity+0.378
Neg logit contributions
dash-0.443
hell-0.442
undo-0.437
 ALEC-0.423
boro-0.421
Token FROM
Token ID16034
Feature activation+2.92e-01

Pos logit contributions
dash+5.830
undo+5.819
hell+5.805
 ALEC+5.654
boro+5.461
Neg logit contributions
 fins-6.734
ities-6.685
isite-6.553
iaz-6.474
 Advantage-6.445
Token (
Token ID357
Feature activation-2.19e-01

Pos logit contributions
ities+0.667
 fins+0.663
isite+0.624
 Advantage+0.611
ity+0.605
Neg logit contributions
undo-1.034
dash-1.033
hell-1.023
 ALEC-0.995
boro-0.993
Token SELECT
Token ID33493
Feature activation+1.26e+00

Pos logit contributions
hell+0.695
dash+0.693
undo+0.687
 ALEC+0.670
boro+0.663
Neg logit contributions
 fins-0.579
ities-0.576
isite-0.552
 Advantage-0.546
pta-0.534
Token SPL
Token ID46341
Feature activation+7.24e-01

Pos logit contributions
ities+3.305
 fins+3.269
isite+3.165
 Advantage+3.113
ity+3.092
Neg logit contributions
dash-3.913
hell-3.877
undo-3.821
boro-3.695
acus-3.681
TokenIT
Token ID2043
Feature activation-5.90e-01

Pos logit contributions
ities+2.046
 fins+2.026
isite+1.947
ity+1.933
 Advantage+1.923
Neg logit contributions
dash-2.166
undo-2.118
hell-2.111
boro-2.094
 ALEC-2.060
Token sell
Token ID3677
Feature activation+3.66e-01

Pos logit contributions
dash+2.438
hell+2.437
undo+2.412
 ALEC+2.363
boro+2.320
Neg logit contributions
 fins-2.501
ities-2.467
isite-2.410
 Advantage-2.375
pta-2.336
Token its
Token ID663
Feature activation-7.05e-01

Pos logit contributions
 fins+1.053
ities+1.046
 Advantage+1.012
isite+1.005
ity+0.980
Neg logit contributions
hell-1.089
dash-1.081
undo-1.068
boro-1.023
 ALEC-1.020
Token RF
Token ID20445
Feature activation-6.59e-01

Pos logit contributions
dash+2.142
hell+2.136
undo+2.125
 ALEC+2.081
boro+2.039
Neg logit contributions
 fins-1.943
ities-1.925
isite-1.857
 Advantage-1.830
pta-1.812
TokenID
Token ID2389
Feature activation-5.29e-01

Pos logit contributions
dash+1.899
hell+1.894
undo+1.878
 ALEC+1.822
boro+1.795
Neg logit contributions
 fins-1.929
ities-1.916
isite-1.848
 Advantage-1.830
iaz-1.802
Token-
Token ID12
Feature activation-1.08e+00

Pos logit contributions
hell+1.715
dash+1.715
undo+1.700
 ALEC+1.658
boro+1.637
Neg logit contributions
 fins-1.360
ities-1.351
isite-1.294
 Advantage-1.285
iaz-1.259
Tokenbased
Token ID3106
Feature activation-2.25e+00

Pos logit contributions
dash+2.887
hell+2.877
undo+2.841
 ALEC+2.729
boro+2.710
Neg logit contributions
 fins-3.425
ities-3.392
isite-3.289
 Advantage-3.259
pta-3.212
Token products
Token ID3186
Feature activation-2.28e-01

Pos logit contributions
dash+6.940
undo+6.807
 ALEC+6.773
hell+6.716
boro+6.484
Neg logit contributions
 fins-5.608
isite-5.512
ities-5.464
pta-5.365
iaz-5.255
Token throughout
Token ID3690
Feature activation-4.98e-01

Pos logit contributions
hell+0.625
dash+0.624
undo+0.620
 ALEC+0.600
boro+0.592
Neg logit contributions
 fins-0.701
ities-0.699
 Advantage-0.671
isite-0.671
iaz-0.658
Token its
Token ID663
Feature activation-1.01e+00

Pos logit contributions
dash+1.416
hell+1.415
undo+1.405
 ALEC+1.359
boro+1.344
Neg logit contributions
 fins-1.482
ities-1.475
isite-1.419
 Advantage-1.413
iaz-1.386
Token global
Token ID3298
Feature activation-1.00e+00

Pos logit contributions
dash+2.991
hell+2.983
undo+2.937
 ALEC+2.918
boro+2.832
Neg logit contributions
 fins-2.787
ities-2.758
isite-2.683
pta-2.624
 Advantage-2.622
Token customer
Token ID6491
Feature activation+1.12e+00

Pos logit contributions
dash+2.825
hell+2.815
undo+2.784
 ALEC+2.741
boro+2.670
Neg logit contributions
 fins-2.938
ities-2.898
isite-2.834
pta-2.790
 Advantage-2.778
Token,
Token ID11
Feature activation-9.49e-01

Pos logit contributions
dash+2.896
hell+2.885
undo+2.860
 ALEC+2.788
boro+2.719
Neg logit contributions
 fins-4.594
ities-4.568
isite-4.414
 Advantage-4.398
iaz-4.356
Token this
Token ID428
Feature activation-3.00e-01

Pos logit contributions
hell+2.496
dash+2.491
undo+2.466
 ALEC+2.438
boro+2.376
Neg logit contributions
 fins-2.964
ities-2.957
isite-2.874
iaz-2.823
pta-2.819
Token week
Token ID1285
Feature activation-9.49e-01

Pos logit contributions
dash+0.933
hell+0.933
undo+0.925
 ALEC+0.903
boro+0.889
Neg logit contributions
 fins-0.810
ities-0.805
isite-0.773
 Advantage-0.767
iaz-0.754
Token Kirk
Token ID13855
Feature activation+8.47e-02

Pos logit contributions
dash+2.456
hell+2.451
undo+2.427
 ALEC+2.365
boro+2.319
Neg logit contributions
 fins-3.044
ities-3.024
isite-2.933
 Advantage-2.901
iaz-2.873
Token Herb
Token ID34858
Feature activation-1.16e-01

Pos logit contributions
ities+0.200
 fins+0.194
isite+0.183
 Advantage+0.183
ity+0.180
Neg logit contributions
undo-0.297
dash-0.296
hell-0.293
boro-0.285
 ALEC-0.284
Tokenstre
Token ID22853
Feature activation-2.25e+00

Pos logit contributions
hell+0.250
dash+0.248
undo+0.241
 ALEC+0.241
boro+0.233
Neg logit contributions
ities-0.424
 fins-0.419
 Advantage-0.410
isite-0.403
ity-0.402
Tokenit
Token ID270
Feature activation-5.05e-01

Pos logit contributions
hell+5.224
dash+5.075
undo+4.976
 ALEC+4.787
boro+4.694
Neg logit contributions
 fins-7.773
ities-7.695
isite-7.537
 Advantage-7.528
pta-7.277
Token,
Token ID11
Feature activation-4.16e-01

Pos logit contributions
dash+1.359
hell+1.358
undo+1.345
 ALEC+1.305
boro+1.283
Neg logit contributions
 fins-1.578
ities-1.571
isite-1.514
 Advantage-1.506
iaz-1.482
Token Lee
Token ID5741
Feature activation+1.25e-01

Pos logit contributions
hell+1.124
dash+1.124
undo+1.112
 ALEC+1.075
boro+1.060
Neg logit contributions
 fins-1.295
ities-1.287
isite-1.240
 Advantage-1.239
iaz-1.213
Token Cor
Token ID2744
Feature activation+9.61e-01

Pos logit contributions
ities+0.344
 fins+0.336
 Advantage+0.327
isite+0.323
pta+0.319
Neg logit contributions
dash-0.385
hell-0.377
undo-0.376
 ALEC-0.367
boro-0.360
Tokenso
Token ID568
Feature activation-2.87e-01

Pos logit contributions
ities+3.190
iaz+3.061
ity+3.036
isite+3.017
 fins+3.016
Neg logit contributions
dash-2.302
 ALEC-2.274
FTWARE-2.227
undo-2.225
hell-2.224
Token T
Token ID309
Feature activation-9.04e-01

Pos logit contributions
 fins+0.003
ities+0.003
 Advantage+0.003
isite+0.003
ity+0.003
Neg logit contributions
dash-0.003
hell-0.003
undo-0.003
 ALEC-0.003
boro-0.003
Tokeniki
Token ID5580
Feature activation-9.00e-03

Pos logit contributions
dash+2.656
hell+2.656
undo+2.631
 ALEC+2.560
boro+2.522
Neg logit contributions
 fins-2.598
ities-2.583
isite-2.486
 Advantage-2.469
iaz-2.426
Token Tw
Token ID1815
Feature activation+2.74e-01

Pos logit contributions
dash+0.027
hell+0.027
undo+0.027
 ALEC+0.027
boro+0.026
Neg logit contributions
 fins-0.025
ities-0.025
 Advantage-0.024
isite-0.024
ity-0.023
Tokenirl
Token ID1901
Feature activation-2.04e-02

Pos logit contributions
ities+0.507
 fins+0.495
isite+0.474
iaz+0.465
ity+0.454
Neg logit contributions
 ALEC-1.084
dash-1.080
hell-1.075
undo-1.063
FTWARE-1.050
Token thrill
Token ID28576
Feature activation-8.38e-01

Pos logit contributions
hell+0.059
undo+0.059
dash+0.059
 ALEC+0.057
boro+0.056
Neg logit contributions
 fins-0.060
ities-0.059
 Advantage-0.057
isite-0.057
ity-0.056
Token ride
Token ID6594
Feature activation-2.22e+00

Pos logit contributions
hell+1.806
dash+1.793
undo+1.791
 ALEC+1.740
boro+1.678
Neg logit contributions
 fins-3.096
ities-3.055
isite-2.982
 Advantage-2.958
iaz-2.927
Token at
Token ID379
Feature activation-2.53e-01

Pos logit contributions
dash+5.911
hell+5.879
undo+5.779
 ALEC+5.622
boro+5.585
Neg logit contributions
ities-6.551
 fins-6.445
isite-6.437
pta-6.402
iaz-6.295
Token California
Token ID3442
Feature activation-1.16e-01

Pos logit contributions
dash+0.734
hell+0.727
undo+0.725
 ALEC+0.700
boro+0.692
Neg logit contributions
 fins-0.743
ities-0.736
 Advantage-0.709
isite-0.708
iaz-0.688
Token's
Token ID338
Feature activation-7.09e-01

Pos logit contributions
hell+0.308
undo+0.308
dash+0.308
 ALEC+0.293
boro+0.289
Neg logit contributions
 fins-0.370
ities-0.369
 Advantage-0.356
isite-0.353
ity-0.347
Token Great
Token ID3878
Feature activation-4.19e-03

Pos logit contributions
dash+2.162
hell+2.161
undo+2.142
 ALEC+2.085
boro+2.056
Neg logit contributions
 fins-1.960
ities-1.948
isite-1.871
 Advantage-1.859
iaz-1.824
Token America
Token ID2253
Feature activation+4.01e-01

Pos logit contributions
undo+0.013
dash+0.013
hell+0.013
FTWARE+0.012
 ALEC+0.012
Neg logit contributions
ities-0.011
 fins-0.011
isite-0.011
 Advantage-0.011
ity-0.011
Token {
Token ID1391
Feature activation+6.90e-02

Pos logit contributions
dash+0.684
hell+0.684
undo+0.675
 ALEC+0.658
boro+0.649
Neg logit contributions
 fins-0.667
ities-0.664
 Advantage-0.637
isite-0.635
iaz-0.622
Token Center
Token ID3337
Feature activation-1.42e-01

Pos logit contributions
 fins+0.188
ities+0.186
 Advantage+0.181
isite+0.178
iaz+0.176
Neg logit contributions
hell-0.212
dash-0.212
undo-0.209
 ALEC-0.204
boro-0.201
Token {
Token ID1391
Feature activation+5.70e-01

Pos logit contributions
hell+0.400
dash+0.399
undo+0.396
 ALEC+0.386
boro+0.378
Neg logit contributions
 fins-0.425
ities-0.425
 Advantage-0.408
isite-0.404
ity-0.397
Token $
Token ID720
Feature activation-6.57e-02

Pos logit contributions
 fins+1.556
ities+1.547
 Advantage+1.500
isite+1.459
ity+1.442
Neg logit contributions
hell-1.735
dash-1.715
undo-1.710
 ALEC-1.676
boro-1.649
Tokens
Token ID82
Feature activation-4.22e-01

Pos logit contributions
hell+0.184
dash+0.184
undo+0.181
 ALEC+0.180
boro+0.176
Neg logit contributions
ities-0.197
 fins-0.195
isite-0.189
 Advantage-0.186
iaz-0.184
TokenFormat
Token ID26227
Feature activation-2.20e+00

Pos logit contributions
dash+1.284
hell+1.275
undo+1.263
 ALEC+1.250
boro+1.216
Neg logit contributions
ities-1.181
 fins-1.166
isite-1.118
 Advantage-1.109
ity-1.094
Token.
Token ID13
Feature activation-5.25e-01

Pos logit contributions
hell+5.869
dash+5.789
undo+5.774
 ALEC+5.589
boro+5.473
Neg logit contributions
 fins-6.680
ities-6.558
isite-6.393
 Advantage-6.325
iaz-6.287
TokenAl
Token ID2348
Feature activation-2.98e-01

Pos logit contributions
hell+1.454
dash+1.451
undo+1.439
 ALEC+1.412
boro+1.384
Neg logit contributions
 fins-1.591
ities-1.587
isite-1.525
 Advantage-1.515
iaz-1.491
Tokenignment
Token ID16747
Feature activation-1.67e-01

Pos logit contributions
dash+0.767
hell+0.757
undo+0.756
 ALEC+0.739
boro+0.718
Neg logit contributions
ities-0.971
 fins-0.958
isite-0.929
 Advantage-0.910
iaz-0.909
Token =
Token ID796
Feature activation-6.45e-01

Pos logit contributions
hell+0.436
dash+0.435
undo+0.431
 ALEC+0.417
boro+0.412
Neg logit contributions
ities-0.536
 fins-0.535
 Advantage-0.514
isite-0.513
iaz-0.503
Token [
Token ID685
Feature activation-7.91e-01

Pos logit contributions
dash+1.896
hell+1.896
undo+1.878
 ALEC+1.827
boro+1.800
Neg logit contributions
 fins-1.854
ities-1.843
isite-1.774
 Advantage-1.762
iaz-1.731
Token
Token ID198
Feature activation-6.19e-02

Pos logit contributions
hell+0.729
dash+0.728
undo+0.712
 ALEC+0.691
boro+0.676
Neg logit contributions
 fins-1.231
ities-1.209
isite-1.192
 Advantage-1.172
iaz-1.164
TokenThe
Token ID464
Feature activation-8.41e-02

Pos logit contributions
hell+0.185
dash+0.184
undo+0.184
 ALEC+0.181
boro+0.179
Neg logit contributions
ities-0.172
 fins-0.168
isite-0.162
 Advantage-0.161
ity-0.160
Token first
Token ID717
Feature activation+3.99e-01

Pos logit contributions
dash+0.258
hell+0.257
undo+0.255
 ALEC+0.248
boro+0.246
Neg logit contributions
 fins-0.231
ities-0.231
 Advantage-0.220
isite-0.220
iaz-0.215
Token proposal
Token ID6961
Feature activation+4.44e-01

Pos logit contributions
 fins+1.046
ities+1.041
 Advantage+0.989
isite+0.983
ity+0.968
Neg logit contributions
dash-1.271
hell-1.271
undo-1.266
boro-1.222
 ALEC-1.209
Token,
Token ID11
Feature activation+3.30e-01

Pos logit contributions
ities+1.318
 fins+1.299
 Advantage+1.242
ity+1.230
isite+1.217
Neg logit contributions
dash-1.276
undo-1.272
hell-1.263
boro-1.210
FTWARE-1.202
Token Mandatory
Token ID47018
Feature activation-2.19e+00

Pos logit contributions
 fins+0.977
ities+0.973
 Advantage+0.936
isite+0.930
iaz+0.910
Neg logit contributions
dash-0.939
hell-0.929
undo-0.927
boro-0.892
 ALEC-0.878
Token In
Token ID554
Feature activation+6.14e-01

Pos logit contributions
undo+6.088
dash+6.070
hell+5.958
 ALEC+5.912
boro+5.702
Neg logit contributions
 fins-6.201
ities-6.156
isite-5.995
iaz-5.942
pta-5.866
Tokenclusion
Token ID4717
Feature activation+1.04e-01

Pos logit contributions
ities+1.154
 fins+1.095
 Advantage+1.066
isite+1.043
ity+1.042
Neg logit contributions
undo-2.409
dash-2.401
hell-2.389
 ALEC-2.364
boro-2.321
Tokenary
Token ID560
Feature activation-4.50e-01

Pos logit contributions
ities+0.302
 fins+0.295
 Advantage+0.291
isite+0.285
ity+0.281
Neg logit contributions
hell-0.304
dash-0.302
undo-0.299
 ALEC-0.292
boro-0.289
Token Housing
Token ID16797
Feature activation+4.86e-01

Pos logit contributions
hell+1.321
dash+1.319
undo+1.308
 ALEC+1.269
boro+1.254
Neg logit contributions
ities-1.302
 fins-1.299
 Advantage-1.245
isite-1.240
iaz-1.215
Token,
Token ID11
Feature activation-1.71e-01

Pos logit contributions
ities+1.438
 Advantage+1.434
 fins+1.421
isite+1.370
ity+1.343
Neg logit contributions
hell-1.367
dash-1.357
undo-1.342
boro-1.296
FTWARE-1.293
Token[
Token ID58
Feature activation-5.40e-01

Pos logit contributions
ities+1.848
 fins+1.829
 Advantage+1.761
isite+1.736
pta+1.726
Neg logit contributions
hell-2.304
 ALEC-2.301
dash-2.300
undo-2.291
boro-2.226
Tokenwhite
Token ID11186
Feature activation-1.11e+00

Pos logit contributions
dash+1.577
hell+1.576
undo+1.560
 ALEC+1.532
boro+1.503
Neg logit contributions
 fins-1.554
ities-1.553
isite-1.492
 Advantage-1.480
pta-1.456
Token]
Token ID60
Feature activation+6.05e-02

Pos logit contributions
dash+2.375
hell+2.367
undo+2.337
 ALEC+2.238
boro+2.202
Neg logit contributions
 fins-4.099
ities-4.062
isite-3.949
 Advantage-3.932
iaz-3.879
Tokense
Token ID325
Feature activation-1.07e+00

Pos logit contributions
ities+0.190
 fins+0.190
isite+0.183
 Advantage+0.182
pta+0.179
Neg logit contributions
hell-0.161
dash-0.160
undo-0.159
 ALEC-0.157
boro-0.153
Token[
Token ID58
Feature activation-7.56e-01

Pos logit contributions
hell+3.081
dash+3.076
undo+3.050
 ALEC+2.954
boro+2.921
Neg logit contributions
 fins-3.111
ities-3.080
isite-2.978
 Advantage-2.961
iaz-2.908
Tokent
Token ID83
Feature activation-2.16e+00

Pos logit contributions
dash+2.151
hell+2.150
undo+2.130
 ALEC+2.070
boro+2.038
Neg logit contributions
 fins-2.242
ities-2.229
isite-2.148
 Advantage-2.134
iaz-2.098
Token]
Token ID60
Feature activation+4.27e-02

Pos logit contributions
hell+5.731
dash+5.694
undo+5.687
boro+5.386
zone+5.269
Neg logit contributions
 fins-6.719
ities-6.419
 Advantage-6.412
isite-6.357
iaz-6.156
Token {
Token ID1391
Feature activation+2.55e-01

Pos logit contributions
ities+0.129
 fins+0.128
isite+0.123
 Advantage+0.123
pta+0.121
Neg logit contributions
hell-0.118
dash-0.118
 ALEC-0.117
undo-0.117
boro-0.113
Tokenoptions
Token ID25811
Feature activation-1.03e+00

Pos logit contributions
ities+0.777
 fins+0.769
isite+0.743
 Advantage+0.740
pta+0.731
Neg logit contributions
hell-0.692
dash-0.688
 ALEC-0.687
undo-0.675
boro-0.669
Token}
Token ID92
Feature activation+1.83e-01

Pos logit contributions
dash+2.468
hell+2.468
undo+2.441
 ALEC+2.351
boro+2.311
Neg logit contributions
 fins-3.512
ities-3.488
isite-3.381
 Advantage-3.366
iaz-3.319
Token:[
Token ID33250
Feature activation-5.85e-01

Pos logit contributions
ities+0.503
 fins+0.502
 Advantage+0.481
isite+0.479
pta+0.469
Neg logit contributions
hell-0.555
dash-0.553
 ALEC-0.549
undo-0.548
boro-0.533
Token but
Token ID475
Feature activation+9.46e-02

Pos logit contributions
dash+0.514
hell+0.514
undo+0.509
 ALEC+0.497
boro+0.490
Neg logit contributions
 fins-0.423
ities-0.421
isite-0.403
 Advantage-0.400
iaz-0.392
Token if
Token ID611
Feature activation-1.10e-01

Pos logit contributions
 fins+0.266
ities+0.266
 Advantage+0.252
isite+0.252
ity+0.246
Neg logit contributions
dash-0.285
hell-0.284
undo-0.283
 ALEC-0.273
boro-0.271
Token it
Token ID340
Feature activation-6.82e-01

Pos logit contributions
undo+0.266
dash+0.266
hell+0.266
 ALEC+0.254
boro+0.252
Neg logit contributions
 fins-0.372
ities-0.371
isite-0.356
 Advantage-0.355
iaz-0.350
Token was
Token ID373
Feature activation-9.19e-01

Pos logit contributions
dash+2.047
hell+2.046
undo+2.028
 ALEC+1.974
boro+1.945
Neg logit contributions
 fins-1.915
ities-1.904
isite-1.830
 Advantage-1.818
iaz-1.785
Token a
Token ID257
Feature activation-5.55e-01

Pos logit contributions
hell+2.617
dash+2.610
undo+2.573
 ALEC+2.523
boro+2.467
Neg logit contributions
 fins-2.706
ities-2.688
isite-2.613
 Advantage-2.575
pta-2.545
Token pie
Token ID2508
Feature activation-2.16e+00

Pos logit contributions
hell+1.739
dash+1.738
undo+1.721
 ALEC+1.681
boro+1.656
Neg logit contributions
 fins-1.487
ities-1.475
isite-1.420
 Advantage-1.406
iaz-1.381
Token [
Token ID685
Feature activation-2.30e-01

Pos logit contributions
hell+6.300
dash+6.268
undo+6.127
 ALEC+5.968
boro+5.921
Neg logit contributions
 fins-6.209
ities-6.171
isite-5.924
 Advantage-5.846
pta-5.802
Tokenchart
Token ID40926
Feature activation-1.45e+00

Pos logit contributions
dash+0.646
hell+0.645
undo+0.644
 ALEC+0.636
boro+0.619
Neg logit contributions
ities-0.676
 fins-0.676
isite-0.649
 Advantage-0.643
iaz-0.637
Token],
Token ID4357
Feature activation+2.30e-01

Pos logit contributions
dash+3.750
hell+3.719
undo+3.691
 ALEC+3.570
boro+3.506
Neg logit contributions
 fins-4.627
ities-4.618
isite-4.480
 Advantage-4.443
pta-4.387
Token it
Token ID340
Feature activation-5.73e-02

Pos logit contributions
 fins+0.671
ities+0.671
 Advantage+0.638
isite+0.636
ity+0.625
Neg logit contributions
dash-0.657
undo-0.657
hell-0.653
 ALEC-0.632
boro-0.627
Token would
Token ID561
Feature activation-3.15e-01

Pos logit contributions
dash+0.170
hell+0.169
undo+0.169
 ALEC+0.165
boro+0.162
Neg logit contributions
 fins-0.163
ities-0.162
isite-0.155
 Advantage-0.154
pta-0.152
Token for
Token ID329
Feature activation+4.83e-02

Pos logit contributions
dash+0.782
hell+0.781
undo+0.775
 ALEC+0.752
boro+0.743
Neg logit contributions
 fins-0.696
ities-0.695
 Advantage-0.663
isite-0.661
iaz-0.647
Token def
Token ID825
Feature activation+3.29e-01

Pos logit contributions
 fins+0.138
ities+0.137
 Advantage+0.131
isite+0.129
ity+0.127
Neg logit contributions
hell-0.144
dash-0.143
undo-0.143
 ALEC-0.136
boro-0.136
Tokenraud
Token ID22863
Feature activation-1.72e-01

Pos logit contributions
ities+0.977
 fins+0.967
iaz+0.935
isite+0.934
 Advantage+0.922
Neg logit contributions
dash-0.923
hell-0.900
undo-0.892
 ALEC-0.889
FTWARE-0.870
Tokening
Token ID278
Feature activation-4.83e-01

Pos logit contributions
dash+0.616
hell+0.611
undo+0.608
 ALEC+0.591
boro+0.586
Neg logit contributions
 fins-0.388
ities-0.384
isite-0.365
 Advantage-0.362
iaz-0.354
Token its
Token ID663
Feature activation-9.07e-01

Pos logit contributions
hell+1.447
dash+1.443
undo+1.437
 ALEC+1.386
boro+1.377
Neg logit contributions
 fins-1.365
ities-1.355
 Advantage-1.302
isite-1.295
pta-1.264
Token Lif
Token ID21073
Feature activation-2.15e+00

Pos logit contributions
dash+2.678
hell+2.670
undo+2.655
 ALEC+2.601
boro+2.542
Neg logit contributions
 fins-2.565
ities-2.541
isite-2.480
 Advantage-2.411
iaz-2.405
Tokeneline
Token ID4470
Feature activation-3.57e-01

Pos logit contributions
undo+5.078
hell+4.997
dash+4.936
boro+4.662
 ALEC+4.633
Neg logit contributions
 fins-7.411
ities-7.223
isite-7.054
 Advantage-7.047
iaz-6.885
Token program
Token ID1430
Feature activation-3.30e-01

Pos logit contributions
hell+1.113
dash+1.110
undo+1.099
 ALEC+1.071
boro+1.056
Neg logit contributions
 fins-0.966
ities-0.959
 Advantage-0.925
isite-0.917
iaz-0.895
Token,
Token ID11
Feature activation-3.80e-01

Pos logit contributions
dash+0.932
hell+0.932
undo+0.922
 ALEC+0.895
boro+0.885
Neg logit contributions
 fins-0.986
ities-0.983
 Advantage-0.945
isite-0.942
iaz-0.925
Token which
Token ID543
Feature activation-1.38e-02

Pos logit contributions
dash+1.151
hell+1.150
undo+1.139
 ALEC+1.106
boro+1.094
Neg logit contributions
 fins-1.063
ities-1.054
isite-1.012
 Advantage-1.011
iaz-0.986
Token subsid
Token ID7905
Feature activation-9.88e-02

Pos logit contributions
dash+0.042
hell+0.042
undo+0.042
 ALEC+0.040
boro+0.040
Neg logit contributions
 fins-0.039
ities-0.038
 Advantage-0.037
isite-0.036
iaz-0.036
Token writing
Token ID3597
Feature activation-3.97e-01

Pos logit contributions
dash+1.598
hell+1.598
undo+1.583
 ALEC+1.538
boro+1.515
Neg logit contributions
 fins-1.676
ities-1.667
isite-1.606
 Advantage-1.596
iaz-1.569
Token a
Token ID257
Feature activation-4.83e-01

Pos logit contributions
dash+1.142
hell+1.142
undo+1.132
 ALEC+1.100
boro+1.088
Neg logit contributions
 fins-1.174
ities-1.165
 Advantage-1.115
isite-1.115
pta-1.091
Token D
Token ID360
Feature activation+3.29e-02

Pos logit contributions
dash+1.420
hell+1.419
undo+1.406
 ALEC+1.369
boro+1.351
Neg logit contributions
 fins-1.387
ities-1.378
isite-1.323
 Advantage-1.317
iaz-1.294
TokenMA
Token ID5673
Feature activation-2.16e-01

Pos logit contributions
ities+0.096
 fins+0.096
isite+0.091
 Advantage+0.091
iaz+0.091
Neg logit contributions
hell-0.095
undo-0.094
dash-0.094
 ALEC-0.092
boro-0.090
Token-
Token ID12
Feature activation-3.73e-01

Pos logit contributions
dash+0.618
hell+0.617
undo+0.617
 ALEC+0.599
boro+0.595
Neg logit contributions
 fins-0.633
ities-0.629
 Advantage-0.603
isite-0.602
iaz-0.591
Tokenbased
Token ID3106
Feature activation-2.13e+00

Pos logit contributions
undo+1.012
hell+1.010
dash+1.009
 ALEC+0.995
boro+0.977
Neg logit contributions
ities-1.139
 fins-1.137
isite-1.093
 Advantage-1.087
iaz-1.072
Token USB
Token ID8450
Feature activation-1.57e-01

Pos logit contributions
dash+6.207
hell+6.160
undo+6.089
 ALEC+5.944
boro+5.689
Neg logit contributions
 fins-5.839
isite-5.828
ities-5.774
pta-5.561
iaz-5.506
Token stack
Token ID8931
Feature activation-1.12e-01

Pos logit contributions
dash+0.478
hell+0.478
undo+0.478
 ALEC+0.465
boro+0.461
Neg logit contributions
ities-0.430
 fins-0.430
 Advantage-0.412
isite-0.407
iaz-0.401
Token and
Token ID290
Feature activation-4.49e-01

Pos logit contributions
dash+0.301
undo+0.301
hell+0.299
 ALEC+0.291
boro+0.287
Neg logit contributions
 fins-0.347
ities-0.343
 Advantage-0.330
isite-0.329
iaz-0.324
Token libraries
Token ID12782
Feature activation+3.90e-02

Pos logit contributions
hell+1.323
dash+1.322
undo+1.311
 ALEC+1.275
boro+1.258
Neg logit contributions
 fins-1.287
ities-1.278
isite-1.228
 Advantage-1.222
iaz-1.200
Token that
Token ID326
Feature activation-3.90e-01

Pos logit contributions
 fins+0.118
ities+0.118
 Advantage+0.112
isite+0.112
ity+0.110
Neg logit contributions
dash-0.109
undo-0.108
hell-0.106
 ALEC-0.104
boro-0.103
Token reached
Token ID4251
Feature activation-2.86e-01

Pos logit contributions
dash+0.349
hell+0.347
undo+0.344
 ALEC+0.334
boro+0.329
Neg logit contributions
ities-0.368
 fins-0.367
 Advantage-0.353
isite-0.351
ity-0.343
Token the
Token ID262
Feature activation-1.76e-01

Pos logit contributions
dash+0.840
hell+0.840
undo+0.833
 ALEC+0.806
boro+0.799
Neg logit contributions
 fins-0.827
ities-0.826
isite-0.791
 Advantage-0.790
pta-0.770
Token original
Token ID2656
Feature activation+2.28e-01

Pos logit contributions
dash+0.558
hell+0.558
undo+0.553
 ALEC+0.538
boro+0.532
Neg logit contributions
 fins-0.465
ities-0.463
isite-0.442
 Advantage-0.440
iaz-0.431
Token border
Token ID4865
Feature activation-1.28e-01

Pos logit contributions
ities+0.555
 fins+0.549
isite+0.517
 Advantage+0.517
ity+0.511
Neg logit contributions
dash-0.774
hell-0.774
undo-0.770
 ALEC-0.747
boro-0.744
Token.[
Token ID3693
Feature activation-5.80e-01

Pos logit contributions
hell+0.381
dash+0.379
undo+0.379
 ALEC+0.368
boro+0.363
Neg logit contributions
ities-0.368
 fins-0.366
isite-0.347
 Advantage-0.346
iaz-0.341
Token19
Token ID1129
Feature activation-2.13e+00

Pos logit contributions
dash+1.760
hell+1.759
undo+1.746
 ALEC+1.707
boro+1.675
Neg logit contributions
 fins-1.601
ities-1.601
isite-1.531
 Advantage-1.524
iaz-1.495
Token]
Token ID60
Feature activation-7.12e-02

Pos logit contributions
hell+3.961
dash+3.948
undo+3.858
 ALEC+3.652
boro+3.600
Neg logit contributions
 fins-8.136
ities-8.040
isite-7.879
iaz-7.827
 Advantage-7.795
Token
Token ID198
Feature activation-4.16e-01

Pos logit contributions
dash+0.203
hell+0.203
undo+0.202
 ALEC+0.195
boro+0.193
Neg logit contributions
ities-0.210
 fins-0.210
 Advantage-0.202
isite-0.201
pta-0.196
Token
Token ID198
Feature activation+1.03e-01

Pos logit contributions
hell+0.883
dash+0.876
undo+0.850
 ALEC+0.838
boro+0.815
Neg logit contributions
 fins-1.555
ities-1.516
isite-1.503
 mosqu-1.478
 Advantage-1.476
TokenAt
Token ID2953
Feature activation+2.37e-01

Pos logit contributions
ities+0.282
 fins+0.275
isite+0.267
ity+0.261
 Advantage+0.261
Neg logit contributions
dash-0.313
hell-0.313
undo-0.312
 ALEC-0.310
boro-0.302
Token that
Token ID326
Feature activation+8.20e-01

Pos logit contributions
ities+0.686
 fins+0.678
isite+0.650
 Advantage+0.649
iaz+0.641
Neg logit contributions
dash-0.694
undo-0.689
hell-0.686
 ALEC-0.664
boro-0.658
Token former
Token ID1966
Feature activation+1.88e-01

Pos logit contributions
undo+0.544
dash+0.543
hell+0.543
 ALEC+0.519
boro+0.512
Neg logit contributions
 fins-0.603
ities-0.597
 Advantage-0.574
isite-0.569
iaz-0.562
Token St
Token ID520
Feature activation-2.55e-01

Pos logit contributions
ities+0.518
 fins+0.517
 Advantage+0.496
isite+0.487
ity+0.480
Neg logit contributions
dash-0.576
hell-0.572
undo-0.572
 ALEC-0.550
boro-0.540
Token.
Token ID13
Feature activation+2.60e-01

Pos logit contributions
dash+0.598
hell+0.593
undo+0.591
 ALEC+0.572
boro+0.556
Neg logit contributions
ities-0.883
 fins-0.878
isite-0.849
 Advantage-0.848
iaz-0.840
Token Louis
Token ID5593
Feature activation+1.45e+00

Pos logit contributions
 fins+0.759
ities+0.758
 Advantage+0.736
isite+0.725
iaz+0.709
Neg logit contributions
dash-0.743
undo-0.739
hell-0.734
 ALEC-0.710
boro-0.694
Token Rams
Token ID16077
Feature activation+4.66e-01

Pos logit contributions
 fins+3.549
ities+3.543
 Advantage+3.404
iaz+3.282
ity+3.279
Neg logit contributions
undo-4.757
dash-4.714
hell-4.589
 ALEC-4.528
FTWARE-4.465
Token kicker
Token ID38297
Feature activation-2.12e+00

Pos logit contributions
ities+1.359
 fins+1.355
 Advantage+1.301
ity+1.277
isite+1.268
Neg logit contributions
dash-1.344
undo-1.328
hell-1.324
 ALEC-1.293
FTWARE-1.244
Token Brett
Token ID18726
Feature activation-8.42e-01

Pos logit contributions
dash+5.328
hell+5.295
undo+5.195
 ALEC+5.160
boro+5.043
Neg logit contributions
 fins-6.697
ities-6.644
isite-6.570
pta-6.410
 Advantage-6.385
Token Ba
Token ID8999
Feature activation+2.83e-01

Pos logit contributions
hell+2.526
dash+2.525
undo+2.502
 ALEC+2.435
boro+2.402
Neg logit contributions
 fins-2.366
ities-2.350
isite-2.263
 Advantage-2.242
iaz-2.204
Tokener
Token ID263
Feature activation-2.80e-01

Pos logit contributions
ities+0.773
 fins+0.750
ity+0.723
isite+0.722
iaz+0.720
Neg logit contributions
dash-0.889
undo-0.869
 ALEC-0.856
hell-0.855
boro-0.830
Token
Token ID784
Feature activation-2.94e-01

Pos logit contributions
dash+0.758
hell+0.755
undo+0.754
 ALEC+0.735
boro+0.713
Neg logit contributions
ities-0.864
 fins-0.863
 Advantage-0.821
isite-0.821
iaz-0.818
Token who
Token ID508
Feature activation-5.51e-01

Pos logit contributions
dash+0.926
hell+0.923
undo+0.917
 ALEC+0.893
boro+0.880
Neg logit contributions
 fins-0.784
ities-0.778
 Advantage-0.743
isite-0.740
iaz-0.726
Token.
Token ID13
Feature activation-2.18e-01

Pos logit contributions
dash+2.325
hell+2.318
undo+2.297
 ALEC+2.231
boro+2.193
Neg logit contributions
 fins-2.337
ities-2.334
isite-2.236
 Advantage-2.233
iaz-2.195
Token<|endoftext|>
Token ID50256
Feature activation-3.34e-01

Pos logit contributions
dash+0.641
hell+0.640
undo+0.638
boro+0.609
 ALEC+0.607
Neg logit contributions
ities-0.623
 fins-0.620
 Advantage-0.604
isite-0.592
ity-0.583
TokenThe
Token ID464
Feature activation-4.16e-01

Pos logit contributions
dash+0.980
hell+0.978
undo+0.976
 ALEC+0.963
boro+0.939
Neg logit contributions
ities-0.946
 fins-0.939
isite-0.904
 Advantage-0.892
iaz-0.885
Token Bengals
Token ID24037
Feature activation-1.37e-02

Pos logit contributions
dash+1.322
hell+1.320
undo+1.310
 ALEC+1.273
boro+1.259
Neg logit contributions
 fins-1.102
ities-1.095
isite-1.047
 Advantage-1.044
iaz-1.019
Token signed
Token ID4488
Feature activation-4.38e-01

Pos logit contributions
dash+0.041
hell+0.040
undo+0.040
 ALEC+0.039
boro+0.038
Neg logit contributions
 fins-0.039
ities-0.039
 Advantage-0.038
isite-0.036
ity-0.036
Token kicker
Token ID38297
Feature activation-2.12e+00

Pos logit contributions
hell+1.198
dash+1.196
undo+1.185
 ALEC+1.141
boro+1.128
Neg logit contributions
 fins-1.356
ities-1.351
 Advantage-1.300
isite-1.296
iaz-1.272
Token Jonathan
Token ID11232
Feature activation-6.75e-01

Pos logit contributions
hell+5.294
dash+5.265
 ALEC+5.205
undo+5.175
boro+5.048
Neg logit contributions
 fins-6.687
ities-6.590
isite-6.549
pta-6.430
 Advantage-6.317
Token Brown
Token ID4373
Feature activation+4.33e-01

Pos logit contributions
dash+1.895
hell+1.892
undo+1.875
 ALEC+1.818
boro+1.791
Neg logit contributions
 fins-2.027
ities-2.021
isite-1.944
 Advantage-1.937
iaz-1.902
Token,
Token ID11
Feature activation-3.54e-01

Pos logit contributions
 fins+1.273
ities+1.263
 Advantage+1.215
iaz+1.215
isite+1.195
Neg logit contributions
dash-1.231
undo-1.211
hell-1.193
 ALEC-1.185
FTWARE-1.133
Token far
Token ID1290
Feature activation+4.15e-01

Pos logit contributions
dash+1.067
hell+1.067
undo+1.054
 ALEC+1.023
boro+1.011
Neg logit contributions
 fins-1.000
ities-0.988
 Advantage-0.952
isite-0.946
iaz-0.926
Token right
Token ID826
Feature activation+1.27e-01

Pos logit contributions
ities+1.130
 fins+1.120
 Advantage+1.069
iaz+1.058
isite+1.057
Neg logit contributions
dash-1.272
hell-1.267
undo-1.252
boro-1.209
 ALEC-1.208
Token,
Token ID11
Feature activation-1.54e-01

Pos logit contributions
dash+0.195
hell+0.194
undo+0.190
 ALEC+0.185
boro+0.181
Neg logit contributions
ities-0.243
 fins-0.241
 Advantage-0.237
isite-0.232
pta-0.230
Token Wells
Token ID18292
Feature activation+7.12e-01

Pos logit contributions
dash+0.457
hell+0.456
undo+0.453
 ALEC+0.438
boro+0.434
Neg logit contributions
 fins-0.436
ities-0.436
 Advantage-0.418
isite-0.417
iaz-0.408
Token Fargo
Token ID28125
Feature activation+4.50e-02

Pos logit contributions
ities+1.997
 fins+1.993
 Advantage+1.932
isite+1.902
iaz+1.875
Neg logit contributions
dash-2.128
undo-2.109
hell-2.102
 ALEC-2.035
boro-1.956
Token,
Token ID11
Feature activation-6.75e-01

Pos logit contributions
ities+0.149
 fins+0.149
 Advantage+0.144
isite+0.143
iaz+0.141
Neg logit contributions
dash-0.113
hell-0.112
undo-0.111
 ALEC-0.107
boro-0.105
Token and
Token ID290
Feature activation-4.49e-01

Pos logit contributions
hell+1.961
dash+1.954
undo+1.934
 ALEC+1.900
boro+1.858
Neg logit contributions
 fins-1.958
ities-1.930
isite-1.878
 Advantage-1.833
pta-1.827
Token Ally
Token ID43039
Feature activation-2.12e+00

Pos logit contributions
dash+1.259
hell+1.259
undo+1.247
 ALEC+1.213
boro+1.193
Neg logit contributions
 fins-1.349
ities-1.340
isite-1.295
 Advantage-1.283
iaz-1.263
Token Bank
Token ID5018
Feature activation-6.67e-01

Pos logit contributions
hell+6.884
undo+6.865
dash+6.693
boro+6.683
 ALEC+6.523
Neg logit contributions
 fins-5.177
ities-5.097
isite-5.002
pta-4.726
arily-4.688
Token
Token ID960
Feature activation-6.88e-01

Pos logit contributions
hell+1.794
dash+1.784
undo+1.775
 ALEC+1.718
boro+1.694
Neg logit contributions
 fins-2.078
ities-2.058
isite-2.012
 Advantage-1.973
pta-1.952
Tokenthe
Token ID1169
Feature activation-2.43e-01

Pos logit contributions
hell+1.835
dash+1.831
undo+1.811
 ALEC+1.753
boro+1.728
Neg logit contributions
 fins-2.171
ities-2.155
isite-2.086
 Advantage-2.071
iaz-2.038
Token nation
Token ID3277
Feature activation-1.12e-01

Pos logit contributions
hell+0.797
dash+0.793
undo+0.787
 ALEC+0.773
boro+0.759
Neg logit contributions
 fins-0.611
ities-0.606
isite-0.585
 Advantage-0.577
iaz-0.570
Token
Token ID447
Feature activation-5.52e-01

Pos logit contributions
dash+0.298
hell+0.298
undo+0.295
 ALEC+0.285
boro+0.281
Neg logit contributions
 fins-0.351
ities-0.349
isite-0.336
 Advantage-0.335
iaz-0.329
Token.
Token ID13
Feature activation-2.18e-01

Pos logit contributions
ities+0.871
 fins+0.860
 Advantage+0.824
ity+0.818
isite+0.812
Neg logit contributions
undo-0.736
hell-0.720
dash-0.717
boro-0.695
 ALEC-0.683
Token #
Token ID1303
Feature activation+1.84e-01

Pos logit contributions
dash+0.633
hell+0.632
undo+0.628
 ALEC+0.608
boro+0.601
Neg logit contributions
 fins-0.633
ities-0.630
 Advantage-0.605
isite-0.603
iaz-0.590
Tokenatl
Token ID25864
Feature activation+5.52e-01

Pos logit contributions
ities+0.551
 fins+0.542
isite+0.522
 Advantage+0.517
iaz+0.517
Neg logit contributions
dash-0.509
hell-0.506
undo-0.506
 ALEC-0.504
boro-0.487
Tokenweather
Token ID23563
Feature activation-5.86e-01

Pos logit contributions
ities+1.692
 fins+1.670
isite+1.592
 Advantage+1.580
pta+1.575
Neg logit contributions
hell-1.507
 ALEC-1.501
dash-1.497
undo-1.492
FTWARE-1.437
Token #
Token ID1303
Feature activation+2.14e-01

Pos logit contributions
dash+1.878
hell+1.876
undo+1.865
 ALEC+1.821
boro+1.794
Neg logit contributions
 fins-1.525
ities-1.519
isite-1.449
 Advantage-1.443
iaz-1.413
TokenSnow
Token ID28974
Feature activation-2.11e+00

Pos logit contributions
ities+0.654
 fins+0.642
isite+0.622
iaz+0.615
pta+0.614
Neg logit contributions
dash-0.575
 ALEC-0.574
undo-0.573
hell-0.570
boro-0.553
Tokened
Token ID276
Feature activation-8.11e-01

Pos logit contributions
hell+6.333
dash+6.333
undo+6.164
boro+5.999
 ALEC+5.887
Neg logit contributions
 fins-5.759
ities-5.582
isite-5.537
 Advantage-5.452
pta-5.420
TokenOut
Token ID7975
Feature activation-8.26e-01

Pos logit contributions
hell+2.393
dash+2.393
undo+2.369
 ALEC+2.303
boro+2.272
Neg logit contributions
 fins-2.321
ities-2.304
isite-2.221
 Advantage-2.205
iaz-2.166
TokenAtlanta
Token ID43482
Feature activation-4.52e-01

Pos logit contributions
dash+2.795
hell+2.795
undo+2.773
 ALEC+2.707
boro+2.673
Neg logit contributions
 fins-2.007
ities-1.994
isite-1.905
 Advantage-1.890
iaz-1.850
Token pic
Token ID8301
Feature activation-3.75e-01

Pos logit contributions
dash+1.565
hell+1.561
undo+1.556
 ALEC+1.517
boro+1.497
Neg logit contributions
 fins-1.062
ities-1.061
isite-1.003
 Advantage-1.002
iaz-0.977
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
dash+0.776
hell+0.775
undo+0.760
 ALEC+0.734
boro+0.715
Neg logit contributions
 fins-1.411
ities-1.392
isite-1.375
 Advantage-1.355
pta-1.339
Token people
Token ID661
Feature activation+3.13e-01

Pos logit contributions
 fins+2.630
ities+2.594
iaz+2.393
 Advantage+2.388
ity+2.383
Neg logit contributions
hell-3.331
dash-3.303
undo-3.299
boro-3.245
 ALEC-3.206
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
ities+0.990
 fins+0.979
 Advantage+0.934
ity+0.933
iaz+0.927
Neg logit contributions
dash-0.828
undo-0.821
hell-0.812
 ALEC-0.789
boro-0.783
Token Its
Token ID6363
Feature activation-1.49e-01

Pos logit contributions
dash+0.442
hell+0.442
undo+0.440
 ALEC+0.425
boro+0.421
Neg logit contributions
 fins-0.411
ities-0.409
 Advantage-0.394
isite-0.392
iaz-0.383
Token exports
Token ID15319
Feature activation+8.81e-01

Pos logit contributions
dash+0.444
hell+0.444
undo+0.441
 ALEC+0.428
boro+0.422
Neg logit contributions
 fins-0.423
ities-0.420
isite-0.403
 Advantage-0.402
iaz-0.394
Token to
Token ID284
Feature activation+3.96e-01

Pos logit contributions
 fins+2.419
ities+2.413
 Advantage+2.268
ity+2.233
iaz+2.226
Neg logit contributions
dash-2.684
undo-2.668
hell-2.643
 ALEC-2.575
boro-2.557
Token Saudi
Token ID7420
Feature activation+1.69e+00

Pos logit contributions
 fins+1.051
ities+1.042
 Advantage+0.990
isite+0.979
ity+0.978
Neg logit contributions
dash-1.260
undo-1.257
hell-1.237
boro-1.210
 ALEC-1.184
Token Arabia
Token ID9671
Feature activation+9.42e-01

Pos logit contributions
 fins+1.902
ities+1.842
iaz+1.631
ity+1.618
 Advantage+1.553
Neg logit contributions
undo-7.809
dash-7.678
hell-7.643
boro-7.494
 ALEC-7.490
Token total
Token ID2472
Feature activation+7.19e-02

Pos logit contributions
ities+2.542
 fins+2.521
 Advantage+2.373
ity+2.353
isite+2.329
Neg logit contributions
dash-2.917
undo-2.906
hell-2.885
 ALEC-2.802
boro-2.765
Token $
Token ID720
Feature activation-2.31e-02

Pos logit contributions
 fins+0.205
ities+0.204
 Advantage+0.194
isite+0.194
iaz+0.190
Neg logit contributions
dash-0.214
hell-0.213
undo-0.212
 ALEC-0.205
boro-0.204
Token1
Token ID16
Feature activation-4.57e-01

Pos logit contributions
dash+0.069
hell+0.069
undo+0.069
 ALEC+0.067
boro+0.066
Neg logit contributions
ities-0.065
 fins-0.065
isite-0.062
 Advantage-0.062
iaz-0.061
Token.
Token ID13
Feature activation+3.39e-02

Pos logit contributions
undo+1.076
dash+1.074
hell+1.070
 ALEC+1.026
boro+1.005
Neg logit contributions
 fins-1.584
ities-1.571
isite-1.523
 Advantage-1.515
iaz-1.501
Token 2016
Token ID1584
Feature activation-7.73e-01

Pos logit contributions
ities+1.958
 fins+1.946
 Advantage+1.890
isite+1.848
ity+1.821
Neg logit contributions
dash-1.931
undo-1.907
hell-1.895
 ALEC-1.815
boro-1.800
Token (
Token ID357
Feature activation+3.93e-01

Pos logit contributions
dash+1.842
hell+1.840
undo+1.819
 ALEC+1.755
boro+1.723
Neg logit contributions
 fins-2.654
ities-2.643
isite-2.559
 Advantage-2.546
iaz-2.507
TokenPhoto
Token ID6191
Feature activation-2.29e-01

Pos logit contributions
ities+1.090
 fins+1.062
 Advantage+1.036
isite+1.033
pta+1.016
Neg logit contributions
dash-1.146
 ALEC-1.142
hell-1.140
undo-1.131
boro-1.107
Token:
Token ID25
Feature activation+6.74e-01

Pos logit contributions
hell+0.506
dash+0.505
undo+0.495
 ALEC+0.481
boro+0.475
Neg logit contributions
 fins-0.832
ities-0.822
isite-0.812
 Advantage-0.792
iaz-0.790
Token Wayne
Token ID13329
Feature activation-5.95e-01

Pos logit contributions
ities+2.104
 fins+2.079
 Advantage+2.068
isite+1.996
ity+1.972
Neg logit contributions
dash-1.787
hell-1.766
undo-1.744
boro-1.680
acus-1.662
Token McG
Token ID11130
Feature activation+1.73e+00

Pos logit contributions
hell+1.789
dash+1.786
undo+1.765
 ALEC+1.725
boro+1.699
Neg logit contributions
 fins-1.674
ities-1.658
isite-1.600
 Advantage-1.584
iaz-1.562
Tokena
Token ID64
Feature activation+5.15e-02

Pos logit contributions
ities+5.082
ity+4.789
isite+4.784
iaz+4.640
 fins+4.639
Neg logit contributions
dash-4.999
 ALEC-4.996
FTWARE-4.882
undo-4.675
hell-4.637
Tokenhee
Token ID21067
Feature activation-4.07e-01

Pos logit contributions
ities+0.186
 fins+0.185
isite+0.179
 Advantage+0.178
ity+0.176
Neg logit contributions
dash-0.114
undo-0.112
hell-0.112
 ALEC-0.110
boro-0.106
Token III
Token ID6711
Feature activation+5.35e-02

Pos logit contributions
hell+1.043
dash+1.041
undo+1.032
 ALEC+0.997
boro+0.983
Neg logit contributions
ities-1.316
 fins-1.314
 Advantage-1.269
isite-1.268
iaz-1.246
Token/
Token ID14
Feature activation-1.95e-01

Pos logit contributions
ities+0.164
 fins+0.164
 Advantage+0.160
isite+0.157
iaz+0.155
Neg logit contributions
hell-0.145
dash-0.144
undo-0.143
 ALEC-0.139
boro-0.137
TokenDem
Token ID11522
Feature activation-1.08e+00

Pos logit contributions
dash+0.588
hell+0.588
undo+0.582
 ALEC+0.572
boro+0.563
Neg logit contributions
ities-0.539
 fins-0.538
isite-0.516
 Advantage-0.515
iaz-0.501
Tokenfor
Token ID1640
Feature activation+1.88e-01

Pos logit contributions
 fins+0.706
ities+0.703
isite+0.679
 Advantage+0.675
iaz+0.665
Neg logit contributions
dash-0.561
hell-0.561
undo-0.555
 ALEC-0.538
boro-0.528
Token his
Token ID465
Feature activation+4.01e-02

Pos logit contributions
ities+0.577
 fins+0.576
 Advantage+0.559
isite+0.549
pta+0.541
Neg logit contributions
dash-0.522
hell-0.512
undo-0.508
 ALEC-0.487
boro-0.479
Token fourth
Token ID5544
Feature activation+4.13e-01

Pos logit contributions
 fins+0.126
ities+0.125
 Advantage+0.120
isite+0.119
ity+0.117
Neg logit contributions
dash-0.109
hell-0.108
undo-0.107
 ALEC-0.102
boro-0.102
Token ACC
Token ID15859
Feature activation+9.38e-01

Pos logit contributions
 fins+1.159
ities+1.156
 Advantage+1.116
isite+1.102
ity+1.081
Neg logit contributions
dash-1.253
hell-1.232
undo-1.221
 ALEC-1.169
boro-1.159
Token Rookie
Token ID36595
Feature activation-4.13e-01

Pos logit contributions
ities+2.130
 fins+2.125
 Advantage+2.079
ity+1.971
isite+1.935
Neg logit contributions
dash-3.279
hell-3.233
undo-3.193
FTWARE-3.114
 ALEC-3.105
Token of
Token ID286
Feature activation+1.67e+00

Pos logit contributions
dash+1.250
hell+1.246
undo+1.233
 ALEC+1.196
boro+1.182
Neg logit contributions
 fins-1.157
ities-1.157
 Advantage-1.111
isite-1.110
iaz-1.082
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
ities+4.915
 fins+4.773
 Advantage+4.744
ity+4.681
isite+4.554
Neg logit contributions
undo-4.677
dash-4.665
hell-4.574
boro-4.369
 ALEC-4.362
Token Week
Token ID6119
Feature activation-2.22e-01

Pos logit contributions
ities+2.751
 Advantage+2.733
ity+2.636
 fins+2.617
isite+2.523
Neg logit contributions
dash-4.794
hell-4.773
undo-4.750
FTWARE-4.607
acus-4.525
Token Award
Token ID11289
Feature activation+9.66e-01

Pos logit contributions
dash+0.665
hell+0.664
undo+0.655
 ALEC+0.637
boro+0.630
Neg logit contributions
 fins-0.632
ities-0.628
isite-0.603
 Advantage-0.601
iaz-0.589
Token and
Token ID290
Feature activation+2.16e-01

Pos logit contributions
ities+2.606
 fins+2.603
 Advantage+2.506
ity+2.468
isite+2.463
Neg logit contributions
dash-2.997
hell-2.948
undo-2.899
 ALEC-2.800
boro-2.799
Token first
Token ID717
Feature activation+4.41e-01

Pos logit contributions
 fins+0.652
ities+0.648
 Advantage+0.627
isite+0.612
ity+0.609
Neg logit contributions
dash-0.609
hell-0.607
undo-0.601
boro-0.568
 ALEC-0.567
Token a
Token ID257
Feature activation+1.05e-01

Pos logit contributions
ities+1.839
 fins+1.839
ity+1.727
 Advantage+1.716
arily+1.701
Neg logit contributions
dash-1.568
undo-1.559
hell-1.556
 ALEC-1.508
boro-1.496
Token block
Token ID2512
Feature activation-4.55e-01

Pos logit contributions
 fins+0.273
ities+0.272
 Advantage+0.257
isite+0.257
iaz+0.252
Neg logit contributions
dash-0.339
hell-0.338
undo-0.334
 ALEC-0.329
boro-0.324
Token be
Token ID307
Feature activation-3.81e-01

Pos logit contributions
hell+1.365
dash+1.365
undo+1.353
 ALEC+1.316
boro+1.298
Neg logit contributions
 fins-1.277
ities-1.270
isite-1.222
 Advantage-1.213
iaz-1.191
Token a
Token ID257
Feature activation+3.16e-01

Pos logit contributions
dash+1.096
hell+1.096
undo+1.086
 ALEC+1.056
boro+1.040
Neg logit contributions
 fins-1.116
ities-1.109
isite-1.067
 Advantage-1.062
iaz-1.043
Token first
Token ID717
Feature activation+3.75e-01

Pos logit contributions
 fins+0.868
ities+0.861
 Advantage+0.822
isite+0.816
pta+0.804
Neg logit contributions
hell-0.971
dash-0.959
undo-0.953
 ALEC-0.934
boro-0.928
Token class
Token ID1398
Feature activation+1.60e+00

Pos logit contributions
 fins+0.964
ities+0.960
 Advantage+0.919
isite+0.915
ity+0.897
Neg logit contributions
hell-1.213
dash-1.209
undo-1.208
 ALEC-1.175
boro-1.158
Token parameter
Token ID11507
Feature activation-3.71e-02

Pos logit contributions
ities+3.876
 fins+3.830
 Advantage+3.785
ity+3.699
isite+3.692
Neg logit contributions
dash-5.222
hell-5.179
undo-5.147
boro-5.025
FTWARE-4.927
Token and
Token ID290
Feature activation-2.85e-01

Pos logit contributions
dash+0.107
hell+0.107
undo+0.106
 ALEC+0.103
boro+0.102
Neg logit contributions
ities-0.109
 fins-0.108
isite-0.104
 Advantage-0.103
iaz-0.101
Token can
Token ID460
Feature activation+5.21e-01

Pos logit contributions
dash+0.830
hell+0.829
undo+0.822
 ALEC+0.799
boro+0.788
Neg logit contributions
 fins-0.829
ities-0.823
isite-0.790
 Advantage-0.787
iaz-0.772
Token you
Token ID345
Feature activation+9.81e-01

Pos logit contributions
 fins+1.617
ities+1.611
 Advantage+1.510
ity+1.509
isite+1.509
Neg logit contributions
dash-1.426
undo-1.420
hell-1.413
 ALEC-1.373
boro-1.355
Token pass
Token ID1208
Feature activation-1.39e-02

Pos logit contributions
 fins+2.566
ities+2.531
ity+2.344
 Advantage+2.329
pta+2.329
Neg logit contributions
dash-3.161
hell-3.125
undo-3.071
 ALEC-3.045
boro-3.036
Token/
Token ID14
Feature activation+8.71e-01

Pos logit contributions
ities+3.227
 fins+3.131
ity+3.066
 Advantage+3.017
isite+2.992
Neg logit contributions
undo-2.147
dash-2.100
hell-2.082
 ALEC-2.037
acus-1.972
TokenW
Token ID54
Feature activation+8.35e-01

Pos logit contributions
ities+2.514
 fins+2.467
iaz+2.397
pta+2.386
isite+2.381
Neg logit contributions
 ALEC-2.474
dash-2.444
undo-2.437
hell-2.430
boro-2.365
Token8
Token ID23
Feature activation+1.12e+00

Pos logit contributions
ities+2.481
 fins+2.425
iaz+2.365
isite+2.361
pta+2.350
Neg logit contributions
 ALEC-2.315
dash-2.286
hell-2.279
undo-2.278
boro-2.200
Tokenv
Token ID85
Feature activation+9.67e-01

Pos logit contributions
ities+3.289
 fins+3.212
iaz+3.131
pta+3.121
ity+3.115
Neg logit contributions
 ALEC-3.079
dash-3.043
undo-3.023
hell-3.002
boro-2.920
TokenX
Token ID55
Feature activation+1.92e+00

Pos logit contributions
ities+2.800
 fins+2.740
iaz+2.680
pta+2.668
isite+2.666
Neg logit contributions
 ALEC-2.723
dash-2.692
undo-2.680
hell-2.666
boro-2.582
TokenDs
Token ID30832
Feature activation+1.74e+00

Pos logit contributions
ities+5.534
iaz+5.346
 fins+5.337
pta+5.309
ity+5.305
Neg logit contributions
 ALEC-5.273
undo-5.041
dash-5.013
hell-4.977
FTWARE-4.896
Token4
Token ID19
Feature activation+1.09e+00

Pos logit contributions
ities+5.051
iaz+4.911
 fins+4.871
pta+4.825
ity+4.823
Neg logit contributions
 ALEC-4.734
undo-4.543
dash-4.528
hell-4.485
FTWARE-4.394
Tokenj
Token ID73
Feature activation+1.28e+00

Pos logit contributions
ities+3.211
 fins+3.141
iaz+3.062
pta+3.055
ity+3.045
Neg logit contributions
 ALEC-2.998
dash-2.960
undo-2.944
hell-2.921
boro-2.852
Token0
Token ID15
Feature activation+1.05e+00

Pos logit contributions
ities+3.699
 fins+3.612
iaz+3.568
pta+3.538
ity+3.516
Neg logit contributions
 ALEC-3.578
undo-3.481
dash-3.477
hell-3.468
boro-3.361
Tokeno
Token ID78
Feature activation+9.27e-01

Pos logit contributions
ities+3.057
 fins+3.001
iaz+2.916
pta+2.906
ity+2.895
Neg logit contributions
 ALEC-2.939
dash-2.920
undo-2.900
hell-2.884
boro-2.812
Token
Token ID851
Feature activation-1.28e-01

Pos logit contributions
ities+2.259
 fins+2.256
 Advantage+2.171
iaz+2.156
ity+2.129
Neg logit contributions
dash-3.053
undo-3.019
hell-2.981
 ALEC-2.953
boro-2.913
Token (
Token ID357
Feature activation-1.54e-01

Pos logit contributions
 fins+0.301
ities+0.300
 Advantage+0.287
isite+0.286
ity+0.281
Neg logit contributions
dash-0.279
hell-0.277
undo-0.277
boro-0.266
 ALEC-0.265
TokenW
Token ID54
Feature activation-4.66e-01

Pos logit contributions
dash+0.484
hell+0.480
undo+0.479
 ALEC+0.470
boro+0.460
Neg logit contributions
 fins-0.409
ities-0.407
isite-0.389
 Advantage-0.386
pta-0.379
TokenCR
Token ID9419
Feature activation-5.54e-01

Pos logit contributions
hell+1.187
dash+1.187
undo+1.176
 ALEC+1.143
boro+1.120
Neg logit contributions
 fins-1.518
ities-1.511
isite-1.462
 Advantage-1.447
pta-1.433
TokenP
Token ID47
Feature activation-1.02e+00

Pos logit contributions
dash+1.576
hell+1.575
undo+1.561
 ALEC+1.512
boro+1.494
Neg logit contributions
 fins-1.643
ities-1.635
isite-1.575
 Advantage-1.565
iaz-1.541
Token),
Token ID828
Feature activation-4.30e-01

Pos logit contributions
dash+2.169
hell+2.164
undo+2.134
 ALEC+2.054
boro+2.010
Neg logit contributions
 fins-3.726
ities-3.705
isite-3.594
 Advantage-3.576
iaz-3.529
Token European
Token ID3427
Feature activation+3.48e-01

Pos logit contributions
dash+1.249
hell+1.247
undo+1.238
 ALEC+1.200
boro+1.185
Neg logit contributions
 fins-1.254
ities-1.247
isite-1.199
 Advantage-1.193
iaz-1.171
Token Commission
Token ID4513
Feature activation-3.21e-01

Pos logit contributions
 fins+0.909
ities+0.907
 Advantage+0.865
isite+0.842
ity+0.839
Neg logit contributions
dash-1.118
undo-1.118
hell-1.104
 ALEC-1.070
boro-1.062
Token Joint
Token ID16798
Feature activation-8.46e-01

Pos logit contributions
dash+0.881
hell+0.877
undo+0.872
 ALEC+0.843
boro+0.833
Neg logit contributions
 fins-0.990
ities-0.986
isite-0.947
 Advantage-0.944
iaz-0.927
Token Research
Token ID4992
Feature activation+3.26e-01

Pos logit contributions
hell+2.662
dash+2.662
undo+2.607
 ALEC+2.583
boro+2.530
Neg logit contributions
 fins-2.230
ities-2.182
isite-2.121
pta-2.105
 Advantage-2.095
Token Centre
Token ID9072
Feature activation+4.36e-02

Pos logit contributions
ities+0.780
 fins+0.777
 Advantage+0.740
isite+0.736
ity+0.711
Neg logit contributions
dash-1.119
undo-1.118
hell-1.113
 ALEC-1.077
boro-1.067
Token (
Token ID357
Feature activation-1.07e-01

Pos logit contributions
 fins+0.132
ities+0.132
isite+0.126
 Advantage+0.126
iaz+0.123
Neg logit contributions
hell-0.122
dash-0.122
undo-0.121
 ALEC-0.116
boro-0.116
Token Another
Token ID6023
Feature activation+6.67e-01

Pos logit contributions
dash+0.096
hell+0.095
undo+0.095
 ALEC+0.091
boro+0.090
Neg logit contributions
 fins-0.120
ities-0.120
 Advantage-0.116
isite-0.115
pta-0.113
Token common
Token ID2219
Feature activation+6.09e-01

Pos logit contributions
 fins+1.737
ities+1.714
isite+1.630
 Advantage+1.619
ity+1.599
Neg logit contributions
dash-2.171
hell-2.139
undo-2.119
 ALEC-2.064
boro-2.041
Token name
Token ID1438
Feature activation+1.44e+00

Pos logit contributions
ities+1.429
 fins+1.402
isite+1.321
ity+1.317
 Advantage+1.295
Neg logit contributions
dash-2.153
undo-2.127
hell-2.124
 ALEC-2.054
boro-2.036
Token suggested
Token ID5220
Feature activation+9.12e-02

Pos logit contributions
ities+3.901
 fins+3.821
ity+3.697
arily+3.596
 Advantage+3.529
Neg logit contributions
dash-4.408
hell-4.320
undo-4.320
 ALEC-4.163
FTWARE-4.137
Token for
Token ID329
Feature activation+9.28e-01

Pos logit contributions
 fins+0.265
ities+0.263
isite+0.249
 Advantage+0.248
ity+0.245
Neg logit contributions
dash-0.271
undo-0.268
hell-0.266
 ALEC-0.258
boro-0.254
Token Pet
Token ID4767
Feature activation+3.19e-01

Pos logit contributions
 fins+2.682
ities+2.628
 Advantage+2.519
arily+2.503
ity+2.502
Neg logit contributions
dash-2.747
hell-2.676
undo-2.649
 ALEC-2.566
boro-2.520
Tokenrog
Token ID3828
Feature activation+6.63e-01

Pos logit contributions
 fins+1.337
ities+1.336
isite+1.298
 Advantage+1.292
iaz+1.279
Neg logit contributions
dash-0.511
hell-0.506
undo-0.499
 ALEC-0.479
boro-0.458
Tokenale
Token ID1000
Feature activation+6.39e-01

Pos logit contributions
ities+2.236
 fins+2.228
isite+2.158
 Advantage+2.140
iaz+2.121
Neg logit contributions
dash-1.605
hell-1.595
undo-1.582
 ALEC-1.536
boro-1.501
Token wil
Token ID39716
Feature activation+1.37e+00

Pos logit contributions
 fins+1.735
ities+1.700
isite+1.607
ity+1.592
 Advantage+1.591
Neg logit contributions
dash-2.015
hell-1.996
undo-1.989
 ALEC-1.919
boro-1.869
Tokenkins
Token ID5331
Feature activation+1.35e+00

Pos logit contributions
ities+5.173
 fins+5.131
isite+4.883
ity+4.883
pta+4.875
Neg logit contributions
 ALEC-2.679
undo-2.677
dash-2.661
hell-2.629
FTWARE-2.433
Tokeni
Token ID72
Feature activation+3.72e-01

Pos logit contributions
ities+2.842
 fins+2.834
ity+2.650
iaz+2.602
isite+2.594
Neg logit contributions
undo-4.881
dash-4.873
hell-4.805
 ALEC-4.789
FTWARE-4.666
TokenException
Token ID16922
Feature activation-4.36e-01

Pos logit contributions
ities+0.457
 fins+0.449
isite+0.438
 Advantage+0.435
ity+0.428
Neg logit contributions
dash-0.413
hell-0.409
undo-0.409
 ALEC-0.405
boro-0.395
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
hell+0.898
dash+0.894
undo+0.874
 ALEC+0.843
boro+0.827
Neg logit contributions
 fins-1.663
ities-1.626
isite-1.591
 Advantage-1.576
pta-1.565
TokenMessage
Token ID12837
Feature activation-7.35e-01

Pos logit contributions
ities+0.039
 fins+0.038
isite+0.037
 Advantage+0.037
ity+0.036
Neg logit contributions
dash-0.034
undo-0.034
hell-0.033
 ALEC-0.033
boro-0.032
Token)"
Token ID16725
Feature activation+2.13e-01

Pos logit contributions
hell+2.016
dash+2.016
undo+1.996
 ALEC+1.937
boro+1.907
Neg logit contributions
 fins-2.255
ities-2.243
isite-2.164
 Advantage-2.150
iaz-2.115
Token break
Token ID2270
Feature activation-4.58e-01

Pos logit contributions
 fins+0.669
ities+0.666
isite+0.650
 Advantage+0.639
iaz+0.634
Neg logit contributions
hell-0.567
dash-0.565
undo-0.563
 ALEC-0.546
boro-0.535
Token }
Token ID1782
Feature activation+4.10e-01

Pos logit contributions
hell+1.569
dash+1.557
undo+1.551
 ALEC+1.527
boro+1.496
Neg logit contributions
 fins-1.077
ities-1.069
isite-1.047
iaz-1.016
 Advantage-1.000
Token }
Token ID1782
Feature activation+6.35e-01

Pos logit contributions
 fins+0.788
ities+0.774
 Advantage+0.735
isite+0.714
pta+0.696
Neg logit contributions
dash-1.602
hell-1.590
undo-1.588
 ALEC-1.549
boro-1.545
Token End
Token ID5268
Feature activation+3.81e-01

Pos logit contributions
 fins+1.418
ities+1.386
 Advantage+1.337
isite+1.274
pta+1.257
Neg logit contributions
dash-2.287
undo-2.262
hell-2.261
 ALEC-2.201
boro-2.198
Token {
Token ID1391
Feature activation+2.60e-01

Pos logit contributions
 fins+1.055
ities+1.054
 Advantage+1.011
isite+1.005
iaz+0.983
Neg logit contributions
dash-1.164
undo-1.155
hell-1.145
 ALEC-1.124
boro-1.099
Token Try
Token ID9993
Feature activation-2.56e-01

Pos logit contributions
 fins+0.661
ities+0.653
 Advantage+0.629
isite+0.619
iaz+0.603
Neg logit contributions
dash-0.853
hell-0.846
undo-0.844
 ALEC-0.821
boro-0.818
Token {
Token ID1391
Feature activation-3.37e-02

Pos logit contributions
dash+0.779
hell+0.773
undo+0.771
 ALEC+0.747
boro+0.740
Neg logit contributions
 fins-0.712
ities-0.712
 Advantage-0.681
isite-0.680
iaz-0.662
Tokens
Token ID82
Feature activation+5.17e-02

Pos logit contributions
hell+0.180
dash+0.180
undo+0.179
 ALEC+0.176
boro+0.174
Neg logit contributions
ities-0.114
 fins-0.114
isite-0.107
 Advantage-0.106
ity-0.104
Token something
Token ID1223
Feature activation-4.55e-01

Pos logit contributions
 fins+0.152
ities+0.151
 Advantage+0.145
isite+0.144
iaz+0.142
Neg logit contributions
dash-0.150
hell-0.149
undo-0.149
 ALEC-0.143
boro-0.142
Token you
Token ID345
Feature activation+6.64e-01

Pos logit contributions
dash+1.228
undo+1.227
hell+1.223
 ALEC+1.174
boro+1.160
Neg logit contributions
 fins-1.421
ities-1.420
 Advantage-1.358
isite-1.352
iaz-1.334
Token don
Token ID836
Feature activation+1.24e+00

Pos logit contributions
 fins+1.810
ities+1.780
 Advantage+1.686
isite+1.668
iaz+1.661
Neg logit contributions
hell-2.057
dash-2.057
undo-2.040
 ALEC-1.980
boro-1.951
Token
Token ID447
Feature activation+1.46e-01

Pos logit contributions
ities+2.608
 fins+2.527
ity+2.405
 Advantage+2.351
iaz+2.334
Neg logit contributions
undo-4.513
hell-4.498
dash-4.478
 ALEC-4.400
boro-4.323
Token
Token ID247
Feature activation+2.40e-01

Pos logit contributions
 fins+0.401
ities+0.399
isite+0.383
 Advantage+0.381
iaz+0.373
Neg logit contributions
hell-0.449
dash-0.449
undo-0.445
 ALEC-0.434
boro-0.427
Tokent
Token ID83
Feature activation-8.77e-02

Pos logit contributions
 fins+0.827
ities+0.826
isite+0.792
 Advantage+0.788
ity+0.782
Neg logit contributions
hell-0.564
dash-0.560
undo-0.556
 ALEC-0.547
boro-0.532
Token want
Token ID765
Feature activation+3.71e-01

Pos logit contributions
dash+0.282
hell+0.282
undo+0.280
 ALEC+0.273
boro+0.269
Neg logit contributions
 fins-0.228
ities-0.226
isite-0.216
 Advantage-0.215
iaz-0.211
Token to
Token ID284
Feature activation-1.60e-01

Pos logit contributions
ities+1.132
 fins+1.132
isite+1.066
ity+1.065
 Advantage+1.065
Neg logit contributions
hell-1.014
undo-1.009
dash-1.005
 ALEC-0.976
boro-0.963
Token happen
Token ID1645
Feature activation-1.26e-01

Pos logit contributions
dash+0.483
hell+0.483
undo+0.478
 ALEC+0.466
boro+0.459
Neg logit contributions
 fins-0.448
ities-0.446
isite-0.429
 Advantage-0.426
iaz-0.418
Token.
Token ID13
Feature activation+7.23e-02

Pos logit contributions
dash+0.345
undo+0.343
hell+0.343
 ALEC+0.332
boro+0.324
Neg logit contributions
ities-0.391
 fins-0.389
isite-0.371
 Advantage-0.370
ity-0.366
Token Forum
Token ID14867
Feature activation+6.85e-01

Pos logit contributions
 fins+0.732
ities+0.722
 Advantage+0.688
isite+0.686
iaz+0.663
Neg logit contributions
hell-1.276
dash-1.272
undo-1.267
 ALEC-1.233
boro-1.220
Token,
Token ID11
Feature activation+4.42e-01

Pos logit contributions
 fins+1.948
ities+1.938
 Advantage+1.836
isite+1.821
ity+1.797
Neg logit contributions
dash-2.052
hell-2.052
undo-2.040
boro-1.938
 ALEC-1.937
Token which
Token ID543
Feature activation+6.83e-01

Pos logit contributions
 fins+1.074
ities+1.057
 Advantage+1.013
isite+1.001
iaz+0.985
Neg logit contributions
dash-1.500
undo-1.494
hell-1.494
boro-1.434
 ALEC-1.423
Token will
Token ID481
Feature activation+3.90e-01

Pos logit contributions
 fins+1.998
ities+1.988
 Advantage+1.894
isite+1.850
iaz+1.849
Neg logit contributions
undo-1.998
hell-1.988
dash-1.985
boro-1.857
 ALEC-1.856
Token meet
Token ID1826
Feature activation-4.30e-02

Pos logit contributions
 fins+1.076
ities+1.061
isite+1.010
 Advantage+1.000
iaz+0.996
Neg logit contributions
dash-1.208
hell-1.207
undo-1.188
 ALEC-1.160
boro-1.147
Token on
Token ID319
Feature activation+7.11e-01

Pos logit contributions
dash+0.123
hell+0.123
undo+0.122
 ALEC+0.118
boro+0.117
Neg logit contributions
 fins-0.127
ities-0.127
isite-0.122
 Advantage-0.121
iaz-0.119
Token a
Token ID257
Feature activation+1.82e-01

Pos logit contributions
 fins+1.939
ities+1.925
 Advantage+1.852
isite+1.828
ity+1.792
Neg logit contributions
undo-2.187
dash-2.175
hell-2.172
 ALEC-2.072
acus-2.050
Token quarterly
Token ID27868
Feature activation+1.11e-01

Pos logit contributions
 fins+0.559
ities+0.558
isite+0.539
 Advantage+0.534
iaz+0.525
Neg logit contributions
dash-0.498
hell-0.497
undo-0.493
 ALEC-0.477
boro-0.469
Token basis
Token ID4308
Feature activation-7.27e-02

Pos logit contributions
ities+0.239
 fins+0.239
isite+0.222
 Advantage+0.222
ity+0.218
Neg logit contributions
dash-0.412
hell-0.409
undo-0.409
 ALEC-0.394
boro-0.393
Token from
Token ID422
Feature activation-6.64e-01

Pos logit contributions
dash+0.203
hell+0.201
undo+0.201
 ALEC+0.194
boro+0.191
Neg logit contributions
 fins-0.221
ities-0.220
isite-0.211
 Advantage-0.210
iaz-0.207
Token September
Token ID2693
Feature activation-1.84e-01

Pos logit contributions
hell+1.899
dash+1.886
undo+1.872
 ALEC+1.845
boro+1.802
Neg logit contributions
 fins-1.938
ities-1.926
isite-1.885
 Advantage-1.841
pta-1.831
Token first
Token ID717
Feature activation+1.01e+00

Pos logit contributions
 fins+1.248
ities+1.224
 Advantage+1.166
isite+1.146
ity+1.130
Neg logit contributions
hell-1.461
dash-1.456
undo-1.443
 ALEC-1.401
boro-1.378
Token by
Token ID416
Feature activation+5.74e-01

Pos logit contributions
ities+2.720
 fins+2.687
ity+2.548
 Advantage+2.539
arily+2.538
Neg logit contributions
dash-3.184
undo-3.145
hell-3.138
 ALEC-3.039
boro-3.011
Token a
Token ID257
Feature activation+4.11e-01

Pos logit contributions
 fins+1.671
ities+1.649
 Advantage+1.559
isite+1.538
ity+1.538
Neg logit contributions
dash-1.702
hell-1.685
undo-1.680
boro-1.623
 ALEC-1.619
Token hydra
Token ID25039
Feature activation+1.67e-01

Pos logit contributions
 fins+1.057
ities+1.045
isite+0.988
 Advantage+0.985
ity+0.967
Neg logit contributions
dash-1.342
hell-1.341
undo-1.327
 ALEC-1.294
boro-1.284
Tokenul
Token ID377
Feature activation+2.62e-01

Pos logit contributions
 fins+0.599
ities+0.585
isite+0.571
iaz+0.563
 Advantage+0.561
Neg logit contributions
dash-0.373
hell-0.369
undo-0.365
 ALEC-0.362
boro-0.348
Tokenics
Token ID873
Feature activation+3.14e-02

Pos logit contributions
ities+0.621
 fins+0.620
isite+0.586
 Advantage+0.573
ity+0.572
Neg logit contributions
dash-0.906
hell-0.895
undo-0.895
 ALEC-0.887
boro-0.870
Token issue
Token ID2071
Feature activation+8.84e-01

Pos logit contributions
 fins+0.059
ities+0.058
isite+0.054
 Advantage+0.054
iaz+0.052
Neg logit contributions
dash-0.125
hell-0.124
undo-0.124
 ALEC-0.121
boro-0.120
Token with
Token ID351
Feature activation+6.26e-01

Pos logit contributions
ities+2.433
 fins+2.406
ity+2.280
 Advantage+2.270
arily+2.233
Neg logit contributions
dash-2.684
undo-2.644
hell-2.622
 ALEC-2.585
boro-2.544
Token the
Token ID262
Feature activation+6.42e-01

Pos logit contributions
 fins+1.928
ities+1.852
 Advantage+1.775
isite+1.771
ity+1.742
Neg logit contributions
dash-1.773
hell-1.760
undo-1.757
boro-1.686
 ALEC-1.681
Token rocket
Token ID10701
Feature activation+3.05e-01

Pos logit contributions
 fins+1.791
ities+1.737
 Advantage+1.663
isite+1.652
iaz+1.616
Neg logit contributions
dash-1.980
hell-1.962
undo-1.949
 ALEC-1.904
boro-1.886
Token
Token ID447
Feature activation+1.36e-01

Pos logit contributions
 fins+0.905
ities+0.888
isite+0.847
 Advantage+0.846
iaz+0.832
Neg logit contributions
dash-0.877
undo-0.873
hell-0.872
 ALEC-0.845
boro-0.834
Token who
Token ID508
Feature activation-2.61e-01

Pos logit contributions
 fins+0.111
ities+0.109
 Advantage+0.105
isite+0.103
iaz+0.102
Neg logit contributions
dash-0.122
hell-0.122
undo-0.122
 ALEC-0.117
boro-0.116
Token could
Token ID714
Feature activation+2.54e-01

Pos logit contributions
dash+0.787
hell+0.784
undo+0.782
 ALEC+0.755
boro+0.744
Neg logit contributions
 fins-0.738
ities-0.735
isite-0.698
 Advantage-0.697
iaz-0.684
Token land
Token ID1956
Feature activation-5.53e-01

Pos logit contributions
 fins+0.668
ities+0.663
isite+0.622
 Advantage+0.621
ity+0.612
Neg logit contributions
dash-0.814
hell-0.813
undo-0.801
 ALEC-0.787
boro-0.775
Token a
Token ID257
Feature activation+9.28e-02

Pos logit contributions
dash+1.547
hell+1.543
undo+1.534
 ALEC+1.484
boro+1.466
Neg logit contributions
 fins-1.672
ities-1.662
isite-1.597
 Advantage-1.592
iaz-1.561
Token Supporting
Token ID44188
Feature activation-9.66e-01

Pos logit contributions
 fins+0.264
ities+0.262
 Advantage+0.250
isite+0.249
ity+0.245
Neg logit contributions
dash-0.278
hell-0.275
undo-0.274
 ALEC-0.265
boro-0.264
Token Actor
Token ID27274
Feature activation+9.44e-02

Pos logit contributions
hell+2.777
dash+2.773
undo+2.751
 ALEC+2.678
boro+2.636
Neg logit contributions
 fins-2.831
ities-2.814
isite-2.713
 Advantage-2.681
pta-2.645
Token nomination
Token ID11872
Feature activation+4.21e-01

Pos logit contributions
ities+0.268
 fins+0.267
 Advantage+0.257
isite+0.255
ity+0.253
Neg logit contributions
dash-0.284
hell-0.281
undo-0.277
 ALEC-0.270
boro-0.267
Token for
Token ID329
Feature activation+3.57e-01

Pos logit contributions
ities+1.228
 fins+1.224
 Advantage+1.167
ity+1.154
isite+1.153
Neg logit contributions
dash-1.220
hell-1.201
undo-1.200
 ALEC-1.165
boro-1.146
Token Joe
Token ID5689
Feature activation-3.27e-01

Pos logit contributions
 fins+1.070
ities+1.058
 Advantage+1.034
isite+1.005
ity+1.000
Neg logit contributions
dash-1.012
undo-0.997
hell-0.990
 ALEC-0.948
boro-0.938
Token Wright
Token ID12206
Feature activation+1.37e-01

Pos logit contributions
dash+1.082
hell+1.078
undo+1.069
 ALEC+1.040
boro+1.024
Neg logit contributions
 fins-0.820
ities-0.814
 Advantage-0.783
isite-0.781
iaz-0.760
Token
Token ID447
Feature activation-7.16e-01

Pos logit contributions
 fins+0.406
ities+0.400
 Advantage+0.390
isite+0.383
iaz+0.380
Neg logit contributions
dash-0.387
undo-0.384
hell-0.384
 ALEC-0.374
boro-0.362
Tokenading
Token ID4980
Feature activation+6.82e-01

Pos logit contributions
ities+0.105
 fins+0.103
isite+0.099
iaz+0.098
ity+0.097
Neg logit contributions
hell-0.113
dash-0.112
undo-0.112
 ALEC-0.111
boro-0.107
Token framework
Token ID9355
Feature activation+1.18e-01

Pos logit contributions
 fins+1.846
ities+1.801
 Advantage+1.727
ity+1.672
isite+1.659
Neg logit contributions
undo-2.167
hell-2.137
dash-2.128
boro-2.048
 ALEC-2.035
Token needed
Token ID2622
Feature activation-4.31e-01

Pos logit contributions
ities+0.361
 fins+0.361
 Advantage+0.344
isite+0.341
ity+0.337
Neg logit contributions
dash-0.326
undo-0.323
hell-0.322
boro-0.309
 ALEC-0.306
Token for
Token ID329
Feature activation-1.89e-02

Pos logit contributions
dash+1.150
hell+1.149
undo+1.141
 ALEC+1.097
boro+1.086
Neg logit contributions
 fins-1.367
ities-1.361
isite-1.311
 Advantage-1.300
pta-1.280
Token the
Token ID262
Feature activation+2.90e-01

Pos logit contributions
hell+0.055
dash+0.055
undo+0.054
boro+0.052
 ALEC+0.052
Neg logit contributions
 fins-0.056
ities-0.056
 Advantage-0.053
isite-0.053
ity-0.052
Token regional
Token ID7915
Feature activation-2.94e-01

Pos logit contributions
 fins+0.813
ities+0.803
 Advantage+0.769
isite+0.762
iaz+0.748
Neg logit contributions
undo-0.878
hell-0.878
dash-0.878
boro-0.840
 ALEC-0.835
Token system
Token ID1080
Feature activation+2.41e-01

Pos logit contributions
dash+0.827
hell+0.827
undo+0.824
 ALEC+0.793
boro+0.785
Neg logit contributions
 fins-0.890
ities-0.889
 Advantage-0.847
isite-0.846
iaz-0.829
Token to
Token ID284
Feature activation+2.80e-02

Pos logit contributions
ities+0.753
 fins+0.748
 Advantage+0.716
isite+0.712
ity+0.707
Neg logit contributions
dash-0.650
undo-0.647
hell-0.644
 ALEC-0.618
boro-0.618
Token work
Token ID670
Feature activation+3.96e-01

Pos logit contributions
 fins+0.076
ities+0.075
isite+0.071
 Advantage+0.071
iaz+0.070
Neg logit contributions
dash-0.088
hell-0.088
undo-0.087
 ALEC-0.085
boro-0.084
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
ities+1.231
 fins+1.223
isite+1.160
 Advantage+1.159
ity+1.152
Neg logit contributions
dash-1.084
undo-1.082
hell-1.064
 ALEC-1.026
boro-1.022
Token
Token ID198
Feature activation-4.77e-01

Pos logit contributions
dash+0.561
hell+0.561
undo+0.558
 ALEC+0.534
boro+0.532
Neg logit contributions
ities-0.612
 fins-0.612
 Advantage-0.591
isite-0.587
pta-0.574
Token's
Token ID338
Feature activation-3.57e-01

Pos logit contributions
 fins+0.425
ities+0.424
 Advantage+0.402
isite+0.400
arily+0.393
Neg logit contributions
dash-0.401
hell-0.397
undo-0.395
 ALEC-0.383
boro-0.377
Token war
Token ID1175
Feature activation-4.93e-01

Pos logit contributions
dash+1.040
hell+1.040
undo+1.030
 ALEC+1.002
boro+0.987
Neg logit contributions
 fins-1.037
ities-1.031
isite-0.994
 Advantage-0.986
iaz-0.970
Token chest
Token ID7721
Feature activation+6.74e-01

Pos logit contributions
dash+1.084
undo+1.081
hell+1.071
 ALEC+1.039
boro+0.999
Neg logit contributions
 fins-1.812
ities-1.803
 Advantage-1.724
isite-1.723
iaz-1.698
Token is
Token ID318
Feature activation+2.26e-01

Pos logit contributions
 fins+1.939
ities+1.929
 Advantage+1.817
ity+1.786
isite+1.776
Neg logit contributions
dash-2.012
undo-1.988
hell-1.982
 ALEC-1.914
boro-1.903
Token significantly
Token ID5566
Feature activation-4.20e-01

Pos logit contributions
 fins+0.637
ities+0.630
 Advantage+0.604
isite+0.600
iaz+0.587
Neg logit contributions
dash-0.687
hell-0.674
undo-0.673
 ALEC-0.649
boro-0.643
Token bigger
Token ID5749
Feature activation-5.95e-01

Pos logit contributions
dash+1.260
hell+1.259
undo+1.248
 ALEC+1.214
boro+1.197
Neg logit contributions
 fins-1.184
ities-1.177
isite-1.131
 Advantage-1.124
iaz-1.103
Token now
Token ID783
Feature activation+3.19e-01

Pos logit contributions
dash+1.502
hell+1.502
undo+1.485
 ALEC+1.438
boro+1.414
Neg logit contributions
 fins-1.957
ities-1.948
isite-1.879
 Advantage-1.872
iaz-1.842
Token.
Token ID13
Feature activation+9.90e-03

Pos logit contributions
ities+0.998
 fins+0.989
 Advantage+0.951
arily+0.937
isite+0.934
Neg logit contributions
dash-0.852
undo-0.846
hell-0.844
 ALEC-0.814
boro-0.809
Token Mozilla
Token ID29258
Feature activation-7.55e-01

Pos logit contributions
 fins+0.032
ities+0.032
 Advantage+0.031
isite+0.030
pta+0.030
Neg logit contributions
dash-0.026
hell-0.026
undo-0.026
 ALEC-0.024
boro-0.024
Token,
Token ID11
Feature activation-3.10e-01

Pos logit contributions
hell+2.076
dash+2.073
undo+2.053
 ALEC+2.002
boro+1.962
Neg logit contributions
 fins-2.290
ities-2.270
isite-2.219
 Advantage-2.176
iaz-2.163
Token which
Token ID543
Feature activation-3.39e-02

Pos logit contributions
dash+0.973
hell+0.972
undo+0.964
 ALEC+0.939
boro+0.927
Neg logit contributions
 fins-0.832
ities-0.827
isite-0.793
 Advantage-0.788
iaz-0.773
Token timed
Token ID28805
Feature activation-1.18e+00

Pos logit contributions
dash+1.314
hell+1.312
undo+1.304
 ALEC+1.270
boro+1.255
Neg logit contributions
 fins-1.061
ities-1.056
isite-1.009
 Advantage-1.004
iaz-0.983
Token 45
Token ID4153
Feature activation-3.12e-01

Pos logit contributions
hell+3.723
dash+3.709
undo+3.689
 ALEC+3.578
boro+3.524
Neg logit contributions
 fins-3.112
ities-3.063
isite-2.959
 Advantage-2.927
pta-2.888
Token-
Token ID12
Feature activation+1.21e-01

Pos logit contributions
hell+1.051
dash+1.050
undo+1.041
 ALEC+1.018
boro+1.005
Neg logit contributions
 fins-0.763
ities-0.759
isite-0.724
 Advantage-0.720
pta-0.702
Tokenminute
Token ID11374
Feature activation-3.16e-01

Pos logit contributions
ities+0.367
 fins+0.365
isite+0.351
 Advantage+0.350
pta+0.345
Neg logit contributions
hell-0.331
dash-0.330
undo-0.328
 ALEC-0.326
boro-0.316
Token programming
Token ID8300
Feature activation-2.53e-01

Pos logit contributions
dash+0.984
hell+0.982
undo+0.974
 ALEC+0.948
boro+0.937
Neg logit contributions
 fins-0.853
ities-0.849
isite-0.813
 Advantage-0.809
iaz-0.792
Token challenge
Token ID4427
Feature activation-6.89e-01

Pos logit contributions
dash+0.803
hell+0.797
undo+0.796
 ALEC+0.772
boro+0.765
Neg logit contributions
 fins-0.671
ities-0.668
isite-0.636
 Advantage-0.635
iaz-0.619
Token on
Token ID319
Feature activation-6.25e-02

Pos logit contributions
dash+1.732
hell+1.728
undo+1.717
 ALEC+1.660
boro+1.632
Neg logit contributions
 fins-2.273
ities-2.266
isite-2.184
 Advantage-2.176
iaz-2.141
Token Interview
Token ID19371
Feature activation-2.01e-01

Pos logit contributions
dash+0.166
undo+0.166
hell+0.166
 ALEC+0.159
boro+0.157
Neg logit contributions
 fins-0.197
ities-0.196
 Advantage-0.189
isite-0.189
iaz-0.184
TokenStreet
Token ID34356
Feature activation-5.34e-01

Pos logit contributions
dash+0.623
hell+0.622
undo+0.615
 ALEC+0.603
boro+0.592
Neg logit contributions
ities-0.547
 fins-0.547
isite-0.525
 Advantage-0.524
pta-0.509
Token as
Token ID355
Feature activation-7.30e-01

Pos logit contributions
hell+1.340
dash+1.339
undo+1.333
 ALEC+1.290
boro+1.266
Neg logit contributions
 fins-1.760
ities-1.758
isite-1.697
 Advantage-1.696
iaz-1.662
Token a
Token ID257
Feature activation-3.47e-01

Pos logit contributions
dash+1.970
hell+1.965
undo+1.952
 ALEC+1.893
boro+1.863
Neg logit contributions
 fins-2.280
ities-2.269
 Advantage-2.189
isite-2.187
iaz-2.143
Token the
Token ID262
Feature activation-9.80e-02

Pos logit contributions
hell+1.317
dash+1.317
undo+1.303
 ALEC+1.264
boro+1.246
Neg logit contributions
 fins-1.494
ities-1.488
isite-1.433
 Advantage-1.429
iaz-1.400
Token same
Token ID976
Feature activation+7.36e-01

Pos logit contributions
hell+0.365
dash+0.364
undo+0.361
 ALEC+0.352
boro+0.350
Neg logit contributions
 fins-0.206
ities-0.205
 Advantage-0.194
isite-0.194
iaz-0.186
Token thing
Token ID1517
Feature activation+1.71e-01

Pos logit contributions
ities+1.898
 fins+1.852
 Advantage+1.767
ity+1.751
isite+1.739
Neg logit contributions
hell-2.438
dash-2.407
undo-2.376
boro-2.315
 ALEC-2.287
Token.
Token ID13
Feature activation-3.56e-01

Pos logit contributions
ities+0.553
 fins+0.549
 Advantage+0.530
isite+0.528
ity+0.520
Neg logit contributions
dash-0.438
hell-0.437
undo-0.437
 ALEC-0.418
boro-0.416
Token The
Token ID383
Feature activation+1.01e-01

Pos logit contributions
hell+0.991
dash+0.991
undo+0.982
 ALEC+0.951
boro+0.938
Neg logit contributions
 fins-1.076
ities-1.072
isite-1.033
 Advantage-1.030
iaz-1.009
Token news
Token ID1705
Feature activation-1.62e+00

Pos logit contributions
 fins+0.265
ities+0.263
 Advantage+0.251
isite+0.251
iaz+0.244
Neg logit contributions
hell-0.325
dash-0.325
undo-0.323
 ALEC-0.313
boro-0.311
Tokenfeed
Token ID12363
Feature activation-1.04e+00

Pos logit contributions
hell+5.145
dash+5.108
undo+5.067
 ALEC+4.939
boro+4.892
Neg logit contributions
 fins-4.243
ities-4.171
isite-4.042
 Advantage-3.988
pta-3.973
Token,
Token ID11
Feature activation-3.87e-01

Pos logit contributions
dash+3.047
hell+3.036
undo+3.008
 ALEC+2.931
boro+2.877
Neg logit contributions
 fins-2.975
ities-2.942
isite-2.858
 Advantage-2.811
pta-2.796
Token a
Token ID257
Feature activation+3.90e-02

Pos logit contributions
dash+1.168
hell+1.167
undo+1.156
 ALEC+1.126
boro+1.108
Neg logit contributions
 fins-1.079
ities-1.073
isite-1.032
 Advantage-1.022
iaz-1.007
Token staple
Token ID25629
Feature activation-3.61e-01

Pos logit contributions
 fins+0.109
ities+0.108
isite+0.104
 Advantage+0.103
ity+0.101
Neg logit contributions
hell-0.118
dash-0.117
undo-0.117
 ALEC-0.113
boro-0.113
Token of
Token ID286
Feature activation+1.15e-01

Pos logit contributions
hell+1.064
dash+1.064
undo+1.054
 ALEC+1.025
boro+1.011
Neg logit contributions
 fins-1.034
ities-1.028
isite-0.989
 Advantage-0.983
iaz-0.965
Token factor
Token ID5766
Feature activation+6.89e-02

Pos logit contributions
 fins+0.691
ities+0.678
isite+0.621
 Advantage+0.620
ity+0.620
Neg logit contributions
hell-1.572
dash-1.566
undo-1.553
 ALEC-1.544
boro-1.519
Token"
Token ID1
Feature activation+1.42e-01

Pos logit contributions
 fins+0.196
ities+0.196
 Advantage+0.187
isite+0.186
iaz+0.183
Neg logit contributions
hell-0.205
dash-0.204
undo-0.203
 ALEC-0.198
boro-0.196
Token number
Token ID1271
Feature activation-3.73e-01

Pos logit contributions
 fins+0.381
ities+0.380
 Advantage+0.363
isite+0.361
iaz+0.354
Neg logit contributions
hell-0.444
dash-0.443
undo-0.438
 ALEC-0.428
boro-0.424
Token that
Token ID326
Feature activation-3.65e-01

Pos logit contributions
hell+1.012
dash+1.011
undo+1.004
 ALEC+0.973
boro+0.957
Neg logit contributions
 fins-1.156
ities-1.151
isite-1.107
 Advantage-1.103
iaz-1.084
Token is
Token ID318
Feature activation-7.16e-02

Pos logit contributions
dash+1.072
hell+1.072
undo+1.064
 ALEC+1.032
boro+1.017
Neg logit contributions
 fins-1.057
ities-1.051
 Advantage-1.004
isite-1.004
iaz-0.983
Token greater
Token ID3744
Feature activation-1.19e+00

Pos logit contributions
dash+0.211
hell+0.210
undo+0.209
 ALEC+0.202
boro+0.200
Neg logit contributions
 fins-0.206
ities-0.205
 Advantage-0.197
isite-0.195
iaz-0.192
Token than
Token ID621
Feature activation-6.51e-01

Pos logit contributions
dash+2.886
hell+2.874
undo+2.838
 ALEC+2.735
boro+2.689
Neg logit contributions
 fins-3.973
ities-3.938
isite-3.847
 Advantage-3.792
pta-3.770
Token 0
Token ID657
Feature activation-7.79e-01

Pos logit contributions
hell+1.994
dash+1.993
undo+1.977
 ALEC+1.924
boro+1.897
Neg logit contributions
 fins-1.794
ities-1.784
isite-1.708
 Advantage-1.705
iaz-1.667
Token,
Token ID11
Feature activation+2.36e-01

Pos logit contributions
dash+1.920
hell+1.919
undo+1.898
 ALEC+1.836
boro+1.804
Neg logit contributions
 fins-2.607
ities-2.594
isite-2.510
 Advantage-2.496
iaz-2.458
Token and
Token ID290
Feature activation+8.15e-01

Pos logit contributions
 fins+0.636
ities+0.632
 Advantage+0.608
isite+0.596
iaz+0.588
Neg logit contributions
dash-0.731
hell-0.730
undo-0.728
 ALEC-0.710
boro-0.692
Token then
Token ID788
Feature activation+1.46e+00

Pos logit contributions
 fins+2.240
ities+2.231
 Advantage+2.149
ity+2.055
isite+2.051
Neg logit contributions
dash-2.468
undo-2.451
hell-2.449
 ALEC-2.375
boro-2.346
Token was
Token ID373
Feature activation+1.28e-01

Pos logit contributions
 fins+0.851
ities+0.848
 Advantage+0.803
isite+0.794
ity+0.789
Neg logit contributions
hell-0.855
dash-0.854
undo-0.854
 ALEC-0.818
boro-0.804
Token once
Token ID1752
Feature activation+9.48e-01

Pos logit contributions
 fins+0.371
ities+0.366
 Advantage+0.349
arily+0.346
ity+0.345
Neg logit contributions
dash-0.374
undo-0.369
hell-0.368
 ALEC-0.354
boro-0.352
Token seemed
Token ID3947
Feature activation+9.45e-01

Pos logit contributions
 fins+2.746
ities+2.703
 Advantage+2.602
ity+2.586
arily+2.578
Neg logit contributions
dash-2.728
hell-2.689
undo-2.678
acus-2.586
boro-2.568
Token like
Token ID588
Feature activation+2.24e-01

Pos logit contributions
ities+2.664
 fins+2.647
isite+2.517
ity+2.508
arily+2.505
Neg logit contributions
dash-2.769
undo-2.737
hell-2.697
 ALEC-2.661
FTWARE-2.650
Token a
Token ID257
Feature activation-1.49e-02

Pos logit contributions
 fins+0.678
ities+0.668
 Advantage+0.644
isite+0.635
ity+0.634
Neg logit contributions
undo-0.627
hell-0.621
dash-0.616
 ALEC-0.600
FTWARE-0.592
Token summer
Token ID3931
Feature activation-1.15e+00

Pos logit contributions
dash+0.044
hell+0.044
undo+0.044
 ALEC+0.042
boro+0.042
Neg logit contributions
 fins-0.043
ities-0.042
isite-0.040
 Advantage-0.040
ity-0.040
Token memory
Token ID4088
Feature activation+1.33e-01

Pos logit contributions
dash+3.303
hell+3.301
undo+3.267
 ALEC+3.176
boro+3.136
Neg logit contributions
 fins-3.394
ities-3.375
isite-3.256
 Advantage-3.232
pta-3.179
Token from
Token ID422
Feature activation-4.45e-01

Pos logit contributions
 fins+0.430
ities+0.427
 Advantage+0.411
isite+0.409
arily+0.405
Neg logit contributions
dash-0.343
hell-0.341
undo-0.341
 ALEC-0.328
boro-0.321
Token the
Token ID262
Feature activation+1.50e-01

Pos logit contributions
dash+1.238
hell+1.236
undo+1.225
 ALEC+1.189
boro+1.170
Neg logit contributions
 fins-1.349
ities-1.342
isite-1.290
 Advantage-1.287
iaz-1.261
Token ancient
Token ID6156
Feature activation+6.66e-01

Pos logit contributions
 fins+0.410
ities+0.408
 Advantage+0.388
isite+0.386
iaz+0.378
Neg logit contributions
dash-0.464
hell-0.461
undo-0.457
 ALEC-0.446
boro-0.441
Token past
Token ID1613
Feature activation-1.88e-01

Pos logit contributions
ities+1.735
 fins+1.685
ity+1.582
 Advantage+1.580
isite+1.537
Neg logit contributions
dash-2.183
undo-2.155
hell-2.142
 ALEC-2.082
boro-2.049
Token]
Token ID60
Feature activation+2.85e-01

Pos logit contributions
hell+1.316
dash+1.316
undo+1.304
 ALEC+1.264
boro+1.236
Neg logit contributions
 fins-1.914
ities-1.912
isite-1.848
 Advantage-1.837
iaz-1.809
Token optional
Token ID11902
Feature activation-1.26e+00

Pos logit contributions
ities+0.835
 fins+0.831
 Advantage+0.797
isite+0.790
pta+0.782
Neg logit contributions
hell-0.812
dash-0.811
 ALEC-0.805
undo-0.802
boro-0.780
Token white
Token ID2330
Feature activation+8.75e-02

Pos logit contributions
dash+3.850
undo+3.818
hell+3.812
 ALEC+3.655
boro+3.613
Neg logit contributions
 fins-3.419
ities-3.352
isite-3.286
iaz-3.230
 Advantage-3.217
Token space
Token ID2272
Feature activation-3.35e-01

Pos logit contributions
ities+0.237
 fins+0.235
 Advantage+0.225
isite+0.224
ity+0.220
Neg logit contributions
hell-0.272
dash-0.270
undo-0.267
 ALEC-0.266
boro-0.261
Token {
Token ID1391
Feature activation-2.83e-01

Pos logit contributions
hell+0.998
dash+0.995
undo+0.987
 ALEC+0.964
boro+0.950
Neg logit contributions
 fins-0.954
ities-0.951
 Advantage-0.910
isite-0.909
iaz-0.885
Tokenoptions
Token ID25811
Feature activation-1.16e+00

Pos logit contributions
hell+0.899
dash+0.896
undo+0.885
 ALEC+0.883
boro+0.863
Neg logit contributions
 fins-0.739
ities-0.737
isite-0.705
 Advantage-0.702
pta-0.691
Token}
Token ID92
Feature activation-1.22e-01

Pos logit contributions
hell+2.794
dash+2.792
undo+2.763
 ALEC+2.653
boro+2.613
Neg logit contributions
 fins-3.933
ities-3.907
isite-3.787
 Advantage-3.768
iaz-3.720
Token a
Token ID257
Feature activation-4.24e-01

Pos logit contributions
dash+0.363
hell+0.363
undo+0.360
 ALEC+0.352
boro+0.347
Neg logit contributions
 fins-0.344
ities-0.342
 Advantage-0.328
isite-0.328
pta-0.320
Token list
Token ID1351
Feature activation-1.12e+00

Pos logit contributions
hell+1.321
dash+1.316
undo+1.303
 ALEC+1.285
boro+1.260
Neg logit contributions
 fins-1.141
ities-1.141
isite-1.089
 Advantage-1.083
pta-1.065
Token of
Token ID286
Feature activation-1.62e-01

Pos logit contributions
dash+3.198
hell+3.192
undo+3.175
 ALEC+3.071
boro+3.026
Neg logit contributions
 fins-3.309
ities-3.283
isite-3.168
 Advantage-3.145
iaz-3.093
Token option
Token ID3038
Feature activation-2.74e-01

Pos logit contributions
hell+0.498
dash+0.495
undo+0.490
 ALEC+0.481
boro+0.475
Neg logit contributions
 fins-0.446
ities-0.444
 Advantage-0.422
isite-0.421
pta-0.412
Token F
Token ID376
Feature activation-1.71e-01

Pos logit contributions
 fins+0.393
ities+0.393
 Advantage+0.373
isite+0.370
ity+0.365
Neg logit contributions
dash-0.488
undo-0.488
hell-0.485
 ALEC-0.469
boro-0.464
Token-
Token ID12
Feature activation+3.24e-01

Pos logit contributions
dash+0.494
hell+0.494
undo+0.488
 ALEC+0.474
boro+0.468
Neg logit contributions
 fins-0.498
ities-0.493
isite-0.477
 Advantage-0.474
pta-0.465
Token150
Token ID8628
Feature activation+4.44e-01

Pos logit contributions
ities+0.830
 fins+0.813
 Advantage+0.774
isite+0.768
ity+0.760
Neg logit contributions
hell-1.058
undo-1.054
dash-1.042
 ALEC-1.041
boro-1.005
Token Eco
Token ID38719
Feature activation-8.77e-01

Pos logit contributions
 fins+1.246
ities+1.240
 Advantage+1.192
isite+1.166
ity+1.157
Neg logit contributions
undo-1.339
dash-1.329
hell-1.319
 ALEC-1.287
boro-1.258
TokenBoost
Token ID45686
Feature activation+9.47e-02

Pos logit contributions
hell+2.133
dash+2.131
undo+2.111
 ALEC+2.043
boro+2.002
Neg logit contributions
 fins-2.970
ities-2.953
isite-2.858
 Advantage-2.848
iaz-2.801
Token Tort
Token ID28467
Feature activation-1.40e+00

Pos logit contributions
 fins+0.273
ities+0.272
 Advantage+0.262
isite+0.259
iaz+0.256
Neg logit contributions
dash-0.277
undo-0.277
hell-0.276
 ALEC-0.268
boro-0.263
Tokenure
Token ID495
Feature activation+1.05e-01

Pos logit contributions
hell+4.452
dash+4.450
undo+4.412
 ALEC+4.299
boro+4.242
Neg logit contributions
 fins-3.711
ities-3.689
isite-3.538
 Advantage-3.512
iaz-3.444
Token Test
Token ID6208
Feature activation+7.20e-01

Pos logit contributions
 fins+0.303
ities+0.296
 Advantage+0.291
isite+0.284
iaz+0.279
Neg logit contributions
undo-0.310
dash-0.308
hell-0.304
 ALEC-0.301
FTWARE-0.294
Token truck
Token ID7779
Feature activation-3.64e-02

Pos logit contributions
ities+2.034
 fins+2.025
 Advantage+1.967
isite+1.918
iaz+1.902
Neg logit contributions
undo-2.109
dash-2.090
hell-2.089
 ALEC-2.059
boro-1.992
Token in
Token ID287
Feature activation+3.69e-01

Pos logit contributions
undo+0.106
dash+0.105
hell+0.105
 ALEC+0.102
boro+0.100
Neg logit contributions
 fins-0.107
ities-0.106
 Advantage-0.101
isite-0.101
iaz-0.099
Token the
Token ID262
Feature activation+9.45e-02

Pos logit contributions
 fins+1.068
ities+1.054
 Advantage+1.009
isite+0.998
ity+0.985
Neg logit contributions
hell-1.083
undo-1.080
dash-1.078
 ALEC-1.028
boro-1.027