TOP ACTIVATIONS
MAX = 3.089

handling of Mam ad ou Sak ho drugs test Read more
T akeru Kob ay ashi
, was where J iri Rak held forth the other night
in . S ega has released a new set
Metroid series developer Yosh io Sak amoto told me in 2010
mother has lived on Pot rero Hill for 25 years and
with Inside the Dek u Tree ,
Service story . Ark ansas has already honored the
recognition as his highly paid linem ates David De Cast ro
s has some miscar riages in the past ,
oked Hillary Clinton and Deborah Wasserman Schultz will not allow Bernie
- O ri ented , Prec ise - Unt
Cl ad in a Toronto Argon auts football jersey , he
Water Serv ant vs Sak ash ima the Im post
- independence rally at Plaza Esp ana in Barcelona tonight
- independence rally at Plaza Esp ana tonight ahead of Sunday
has been taken to a Sak et court after being held
too : These " lab yrinth ine worlds filled with secrets
Castle , some see " Pokémon people " as an invasive
Is it really likely that Amazon is going to go all

MIN ACTIVATIONS
MIN = -3.300

According to CBS New York cho pper reporter Joe B ier
! HOW TO INST ALL NET FL IX ON
. HOW TO INST ALL NET FL IX ON
by pro - cor porate arbit rators . A
and collect the Cur ric ulum Vit ae of everyone standing
once said . The American Civil War was a dark chapter
" really angry " about Civil War : https :// t
economic turmoil of the American Civil War . This happened because
, and Minnesota 's Xavier Rhodes are playing for bragging rights
, a professor at the Civil Aviation University of China .
under Title VI of the Civil Rights Act of 1964 .
Resource Management ) Cur ric ulum guidelines . Q
. One of the three flight control primary computers then reacted
senior associate at Carnegie End owment of International Peace , also
F ictional In Philip Pull man 's 1995
to invoke a function called vert , which sole responsibility is
slavery did not cause the Civil War and debunked fairy tales
sway your body to and fro ; dance only from the
the university 's board of trustees . " The extension of
who died 16 years before Civil War , was " really

INTERVAL 1.492 - 3.089
CONTAINS 0.400%

sensitive nature of the mission means the exact date and method
s liquor license means he can t
damages linked to emissions from fossil fuels , industry , biomass
with Inside the Dek u Tree ,
point , but we 've reached the point where this sort

INTERVAL -0.105 - 1.492
CONTAINS 63.793%

that was featured in a number of the trailers , prom
On Aug . 12 , 2012 , USA Today / Gall
. A Supreme product is not desperate to sell itself to
ability much closer to that of the other engine
the cities are keeping makes it very difficult to determine if

INTERVAL -1.702 - -0.105
CONTAINS 35.667%

, but anyone who bought bitcoins at last week 's price
/ in coming / article 35 79 23 12 . e
what we chat about : Starting from nothing :
and em inently re - list enable as a cohesive record
rose has housed some exceptional talent in the past , including

INTERVAL -3.300 - -1.702
CONTAINS 0.140%

on that program by Katie Leigh . Jim H
rescue mission that ended with ign omin ious failure in the
; $ 30 for shorter tours throughout the day ).
by Quake D ude from Explosive !!!!!!!! If you give this
MEM OR IAL L ECT URE in Mumbai
Token handling
Token ID9041
Feature activation+4.89e-01

Pos logit contributions
 corrid+1.108
acco+0.977
2020+0.969
+0.967
 retri+0.950
Neg logit contributions
 Brune-0.911
 Haas-0.882
worthiness-0.876
 Dustin-0.853
 NYU-0.838
Token of
Token ID286
Feature activation+8.50e-02

Pos logit contributions
 corrid+0.840
acco+0.744
2020+0.738
+0.736
 retri+0.724
Neg logit contributions
 Brune-0.627
 Haas-0.605
worthiness-0.601
 Dustin-0.588
 NYU-0.571
Token Mam
Token ID29926
Feature activation+1.18e+00

Pos logit contributions
 corrid+0.138
acco+0.122
2020+0.121
+0.120
GGGGGGGG+0.118
Neg logit contributions
 Brune-0.117
 Haas-0.113
worthiness-0.112
 Dustin-0.110
 NYU-0.107
Tokenad
Token ID324
Feature activation+5.53e-01

Pos logit contributions
 corrid+1.448
acco+1.231
2020+1.213
+1.210
 retri+1.185
Neg logit contributions
 Brune-2.069
 Haas-2.013
worthiness-2.009
 Dustin-1.969
 NYU-1.943
Tokenou
Token ID280
Feature activation+7.70e-02

Pos logit contributions
 corrid+0.789
+0.715
2020+0.714
acco+0.713
 retri+0.688
Neg logit contributions
 Brune-0.812
worthiness-0.806
 Haas-0.799
 Dustin-0.785
 NYU-0.777
Token Sak
Token ID13231
Feature activation+3.09e+00

Pos logit contributions
 corrid+0.114
acco+0.098
2020+0.097
+0.097
 retri+0.095
Neg logit contributions
 Brune-0.118
 Haas-0.114
worthiness-0.113
 Dustin-0.111
 NYU-0.109
Tokenho
Token ID8873
Feature activation-2.73e-01

Pos logit contributions
 corrid+4.446
acco+3.982
2020+3.921
 retri+3.847
+3.834
Neg logit contributions
 Brune-4.574
 Haas-4.479
worthiness-4.434
 Dustin-4.323
 NYU-4.265
Token drugs
Token ID5010
Feature activation+4.77e-01

Pos logit contributions
 Brune+0.335
 Haas+0.326
worthiness+0.319
 Dustin+0.316
 NYU+0.303
Neg logit contributions
 corrid-0.482
acco-0.428
2020-0.424
-0.423
GGGGGGGG-0.417
Token test
Token ID1332
Feature activation-9.80e-01

Pos logit contributions
 corrid+0.818
acco+0.720
2020+0.719
+0.719
GGGGGGGG+0.705
Neg logit contributions
 Brune-0.612
 Haas-0.591
worthiness-0.588
 Dustin-0.576
 NYU-0.560
Token Read
Token ID4149
Feature activation+2.41e-01

Pos logit contributions
 Brune+1.227
 Haas+1.203
worthiness+1.185
 Dustin+1.162
 NYU+1.126
Neg logit contributions
 corrid-1.706
acco-1.496
2020-1.491
-1.480
GGGGGGGG-1.470
Token more
Token ID517
Feature activation-1.70e-01

Pos logit contributions
 corrid+0.391
acco+0.344
+0.341
2020+0.341
 retri+0.336
Neg logit contributions
 Brune-0.329
 Haas-0.317
worthiness-0.316
 Dustin-0.308
 NYU-0.302
Token
Token ID198
Feature activation+4.41e-02

Pos logit contributions
 corrid+0.055
acco+0.048
 retri+0.048
2020+0.048
+0.047
Neg logit contributions
 Brune-0.037
 Haas-0.036
worthiness-0.035
 Dustin-0.035
 NYU-0.034
Token
Token ID198
Feature activation+4.70e-03

Pos logit contributions
 corrid+0.081
acco+0.072
+0.071
2020+0.071
 retri+0.070
Neg logit contributions
 Brune-0.052
 Haas-0.050
worthiness-0.049
 Dustin-0.048
 NYU-0.047
Token
Token ID447
Feature activation+7.08e-02

Pos logit contributions
 corrid+0.007
acco+0.006
 retri+0.006
+0.006
2020+0.006
Neg logit contributions
 Brune-0.007
worthiness-0.007
 Haas-0.007
 Dustin-0.007
 NYU-0.007
Token
Token ID250
Feature activation+1.33e-01

Pos logit contributions
 corrid+0.088
acco+0.072
+0.071
2020+0.071
 retri+0.070
Neg logit contributions
 Brune-0.126
 Haas-0.122
worthiness-0.122
 Dustin-0.120
 NYU-0.118
TokenT
Token ID51
Feature activation-4.64e-01

Pos logit contributions
 corrid+0.199
acco+0.170
 retri+0.167
+0.166
2020+0.166
Neg logit contributions
 Brune-0.203
worthiness-0.196
 Haas-0.195
 Dustin-0.192
 NYU-0.188
Tokenakeru
Token ID43246
Feature activation+2.99e+00

Pos logit contributions
 Brune+0.633
 Haas+0.615
worthiness+0.605
 Dustin+0.594
 NYU+0.585
Neg logit contributions
 corrid-0.754
-0.655
acco-0.652
2020-0.651
 retri-0.649
Token Kob
Token ID23403
Feature activation+1.18e+00

Pos logit contributions
 corrid+4.895
acco+4.375
+4.350
2020+4.333
 retri+4.277
Neg logit contributions
 Brune-3.842
worthiness-3.731
 Haas-3.695
 Dustin-3.597
 NYU-3.574
Tokenay
Token ID323
Feature activation+1.06e+00

Pos logit contributions
 corrid+2.006
acco+1.799
2020+1.776
+1.770
 retri+1.747
Neg logit contributions
 Brune-1.494
 Haas-1.437
worthiness-1.428
 Dustin-1.393
 NYU-1.367
Tokenashi
Token ID12144
Feature activation+1.17e+00

Pos logit contributions
 corrid+1.355
acco+1.136
+1.128
2020+1.126
 retri+1.102
Neg logit contributions
 Brune-1.834
 Haas-1.784
worthiness-1.778
 Dustin-1.741
 NYU-1.716
Token
Token ID447
Feature activation+2.42e-01

Pos logit contributions
 corrid+1.888
acco+1.660
+1.647
2020+1.646
 retri+1.620
Neg logit contributions
 Brune-1.604
 Haas-1.549
worthiness-1.543
 Dustin-1.503
 NYU-1.478
Token
Token ID247
Feature activation-1.36e-01

Pos logit contributions
 corrid+0.369
acco+0.322
+0.319
2020+0.319
 retri+0.313
Neg logit contributions
 Brune-0.354
 Haas-0.343
worthiness-0.341
 Dustin-0.333
 NYU-0.327
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
 corrid+0.888
+0.786
acco+0.785
2020+0.779
 retri+0.771
Neg logit contributions
 Brune-0.704
 Haas-0.680
worthiness-0.676
 Dustin-0.657
 NYU-0.648
Token was
Token ID373
Feature activation-1.52e-01

Pos logit contributions
 corrid+0.336
acco+0.299
2020+0.297
+0.296
GGGGGGGG+0.291
Neg logit contributions
 Brune-0.241
 Haas-0.232
worthiness-0.230
 Dustin-0.225
 NYU-0.220
Token where
Token ID810
Feature activation+8.73e-03

Pos logit contributions
 Brune+0.193
 Haas+0.186
worthiness+0.184
 Dustin+0.182
 NYU+0.177
Neg logit contributions
 corrid-0.263
acco-0.234
2020-0.233
-0.231
GGGGGGGG-0.229
Token J
Token ID449
Feature activation-9.38e-02

Pos logit contributions
 corrid+0.015
2020+0.013
acco+0.013
+0.013
GGGGGGGG+0.013
Neg logit contributions
 Brune-0.011
 Haas-0.011
worthiness-0.011
 Dustin-0.011
 NYU-0.010
Tokeniri
Token ID14783
Feature activation+9.32e-01

Pos logit contributions
 Brune+0.124
 Haas+0.120
worthiness+0.119
 Dustin+0.116
 NYU+0.114
Neg logit contributions
 corrid-0.156
acco-0.137
-0.137
2020-0.136
 retri-0.135
Token Rak
Token ID34299
Feature activation+2.84e+00

Pos logit contributions
 corrid+1.629
acco+1.445
2020+1.435
+1.435
 retri+1.413
Neg logit contributions
 Brune-1.157
 Haas-1.113
worthiness-1.107
 Dustin-1.076
 NYU-1.056
Token held
Token ID2714
Feature activation+4.12e-01

Pos logit contributions
 corrid+4.466
acco+4.174
2020+4.057
 retri+3.966
+3.951
Neg logit contributions
 Brune-3.706
worthiness-3.600
 Haas-3.586
 Dustin-3.505
 NYU-3.448
Token forth
Token ID6071
Feature activation-5.36e-01

Pos logit contributions
 corrid+0.708
acco+0.629
2020+0.626
+0.624
GGGGGGGG+0.613
Neg logit contributions
 Brune-0.528
 Haas-0.507
worthiness-0.501
 Dustin-0.494
 NYU-0.485
Token the
Token ID262
Feature activation+8.43e-02

Pos logit contributions
 Brune+0.642
 Haas+0.617
worthiness+0.609
 Dustin+0.596
 NYU+0.585
Neg logit contributions
 corrid-0.964
acco-0.863
2020-0.853
-0.846
GGGGGGGG-0.838
Token other
Token ID584
Feature activation-3.80e-01

Pos logit contributions
 corrid+0.131
acco+0.116
2020+0.115
+0.115
GGGGGGGG+0.113
Neg logit contributions
 Brune-0.121
 Haas-0.117
worthiness-0.116
 Dustin-0.114
 NYU-0.112
Token night
Token ID1755
Feature activation+7.16e-01

Pos logit contributions
 Brune+0.584
 Haas+0.565
worthiness+0.563
 Dustin+0.555
 NYU+0.546
Neg logit contributions
 corrid-0.550
acco-0.484
-0.478
2020-0.478
GGGGGGGG-0.476
Token in
Token ID287
Feature activation+9.02e-02

Pos logit contributions
 corrid+0.043
acco+0.037
+0.037
2020+0.037
GGGGGGGG+0.036
Neg logit contributions
 Brune-0.033
 Haas-0.031
worthiness-0.031
 Dustin-0.030
 NYU-0.030
Token.
Token ID13
Feature activation-4.57e-02

Pos logit contributions
 corrid+0.155
acco+0.137
2020+0.136
+0.135
 retri+0.133
Neg logit contributions
 Brune-0.117
 Haas-0.112
worthiness-0.111
 Dustin-0.108
 NYU-0.106
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
 Brune+0.058
 Haas+0.056
worthiness+0.054
 Dustin+0.054
 NYU+0.053
Neg logit contributions
 corrid-0.081
acco-0.071
 retri-0.070
2020-0.070
-0.070
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
 Brune+0.268
 Haas+0.256
worthiness+0.256
 Dustin+0.248
 NYU+0.243
Neg logit contributions
 corrid-0.447
acco-0.391
-0.387
GGGGGGGG-0.385
2020-0.384
TokenS
Token ID50
Feature activation-8.21e-02

Pos logit contributions
 Brune+0.339
 Haas+0.328
worthiness+0.326
 Dustin+0.318
 NYU+0.314
Neg logit contributions
 corrid-0.370
acco-0.319
 retri-0.312
2020-0.309
-0.308
Tokenega
Token ID26470
Feature activation+2.84e+00

Pos logit contributions
 Brune+0.113
 Haas+0.109
worthiness+0.108
 Dustin+0.105
 NYU+0.104
Neg logit contributions
 corrid-0.133
-0.116
acco-0.116
2020-0.115
 retri-0.114
Token has
Token ID468
Feature activation+1.19e-01

Pos logit contributions
 corrid+4.616
acco+4.139
2020+4.115
+4.107
 retri+4.009
Neg logit contributions
 Brune-3.696
worthiness-3.592
 Haas-3.574
 Dustin-3.460
 NYU-3.405
Token released
Token ID2716
Feature activation+8.06e-01

Pos logit contributions
 corrid+0.198
acco+0.173
2020+0.172
+0.172
GGGGGGGG+0.169
Neg logit contributions
 Brune-0.160
 Haas-0.154
worthiness-0.153
 Dustin-0.150
 NYU-0.146
Token a
Token ID257
Feature activation+2.21e-01

Pos logit contributions
 corrid+1.390
acco+1.232
+1.223
2020+1.223
 retri+1.204
Neg logit contributions
 Brune-1.022
 Haas-0.984
worthiness-0.977
 Dustin-0.952
 NYU-0.934
Token new
Token ID649
Feature activation+1.29e-01

Pos logit contributions
 corrid+0.369
acco+0.326
+0.323
2020+0.323
 retri+0.317
Neg logit contributions
 Brune-0.295
 Haas-0.285
worthiness-0.281
 Dustin-0.275
 NYU-0.270
Token set
Token ID900
Feature activation+4.08e-01

Pos logit contributions
 corrid+0.232
acco+0.206
2020+0.205
+0.205
 retri+0.202
Neg logit contributions
 Brune-0.154
 Haas-0.148
worthiness-0.146
 Dustin-0.142
 NYU-0.139
Token Metroid
Token ID45430
Feature activation+9.94e-01

Pos logit contributions
 Brune+0.305
 Haas+0.295
worthiness+0.289
 Dustin+0.287
 NYU+0.283
Neg logit contributions
 corrid-0.380
acco-0.336
-0.334
2020-0.334
 retri-0.327
Token series
Token ID2168
Feature activation+9.88e-01

Pos logit contributions
 corrid+1.587
acco+1.392
+1.382
2020+1.380
 retri+1.358
Neg logit contributions
 Brune-1.386
 Haas-1.338
worthiness-1.330
 Dustin-1.301
 NYU-1.279
Token developer
Token ID8517
Feature activation-3.60e-01

Pos logit contributions
 corrid+1.678
acco+1.483
+1.474
2020+1.473
 retri+1.447
Neg logit contributions
 Brune-1.280
 Haas-1.232
worthiness-1.225
 Dustin-1.197
 NYU-1.174
Token Yosh
Token ID28563
Feature activation+3.37e-01

Pos logit contributions
 Brune+0.433
 Haas+0.418
worthiness+0.409
 Dustin+0.406
 NYU+0.394
Neg logit contributions
 corrid-0.650
acco-0.576
-0.574
2020-0.572
 retri-0.564
Tokenio
Token ID952
Feature activation-3.75e-01

Pos logit contributions
 corrid+0.510
acco+0.445
2020+0.441
+0.441
 retri+0.432
Neg logit contributions
 Brune-0.496
 Haas-0.480
worthiness-0.479
 Dustin-0.467
 NYU-0.460
Token Sak
Token ID13231
Feature activation+2.83e+00

Pos logit contributions
 Brune+0.541
 Haas+0.525
worthiness+0.519
 Dustin+0.510
 NYU+0.501
Neg logit contributions
 corrid-0.586
acco-0.509
-0.504
2020-0.504
 retri-0.497
Tokenamoto
Token ID25384
Feature activation+8.84e-01

Pos logit contributions
 corrid+3.526
acco+3.295
2020+3.172
+3.066
 retri+3.048
Neg logit contributions
 Brune-4.623
 Haas-4.532
worthiness-4.500
 Dustin-4.426
 NYU-4.324
Token told
Token ID1297
Feature activation-7.87e-01

Pos logit contributions
 corrid+1.580
acco+1.419
2020+1.405
+1.404
 retri+1.385
Neg logit contributions
 Brune-1.039
worthiness-1.001
 Haas-0.999
 Dustin-0.963
 NYU-0.947
Token me
Token ID502
Feature activation+4.74e-01

Pos logit contributions
 Brune+0.727
 Haas+0.696
 Dustin+0.671
worthiness+0.670
 NYU+0.652
Neg logit contributions
 corrid-1.639
acco-1.474
-1.468
2020-1.466
 retri-1.456
Token in
Token ID287
Feature activation-1.14e-01

Pos logit contributions
 corrid+0.809
acco+0.718
+0.714
2020+0.713
 retri+0.703
Neg logit contributions
 Brune-0.602
worthiness-0.578
 Haas-0.578
 Dustin-0.560
 NYU-0.549
Token 2010
Token ID3050
Feature activation+4.53e-01

Pos logit contributions
 Brune+0.143
 Haas+0.137
worthiness+0.135
 Dustin+0.133
 NYU+0.131
Neg logit contributions
 corrid-0.200
acco-0.177
-0.176
2020-0.175
GGGGGGGG-0.172
Token mother
Token ID2802
Feature activation+2.29e-01

Pos logit contributions
 corrid+0.258
acco+0.229
+0.228
2020+0.227
GGGGGGGG+0.222
Neg logit contributions
 Brune-0.200
 Haas-0.193
worthiness-0.191
 Dustin-0.187
 NYU-0.185
Token has
Token ID468
Feature activation+3.68e-01

Pos logit contributions
 corrid+0.379
acco+0.334
+0.331
2020+0.331
 retri+0.327
Neg logit contributions
 Brune-0.303
 Haas-0.293
worthiness-0.292
 Dustin-0.284
 NYU-0.279
Token lived
Token ID5615
Feature activation-9.94e-01

Pos logit contributions
 corrid+0.636
acco+0.564
2020+0.563
+0.563
GGGGGGGG+0.553
Neg logit contributions
 Brune-0.464
 Haas-0.448
worthiness-0.442
 Dustin-0.433
 NYU-0.426
Token on
Token ID319
Feature activation+8.63e-02

Pos logit contributions
 Brune+1.236
 Haas+1.165
 Dustin+1.150
worthiness+1.149
 NYU+1.127
Neg logit contributions
 corrid-1.738
acco-1.560
-1.552
2020-1.548
GGGGGGGG-1.520
Token Pot
Token ID6902
Feature activation-6.09e-01

Pos logit contributions
 corrid+0.146
2020+0.129
+0.129
acco+0.128
 retri+0.127
Neg logit contributions
 Brune-0.114
 Haas-0.109
worthiness-0.107
 Dustin-0.106
 NYU-0.104
Tokenrero
Token ID34785
Feature activation+2.78e+00

Pos logit contributions
 Brune+1.173
 Haas+1.142
worthiness+1.131
 Dustin+1.115
 NYU+1.101
Neg logit contributions
 corrid-0.661
-0.537
2020-0.525
GGGGGGGG-0.525
 retri-0.521
Token Hill
Token ID3327
Feature activation+1.37e-01

Pos logit contributions
 corrid+5.384
acco+4.855
2020+4.810
+4.752
 retri+4.731
Neg logit contributions
 Brune-2.868
worthiness-2.826
 Haas-2.706
 Dustin-2.626
 NYU-2.549
Token for
Token ID329
Feature activation-6.19e-02

Pos logit contributions
 corrid+0.233
acco+0.206
+0.205
2020+0.204
GGGGGGGG+0.201
Neg logit contributions
 Brune-0.179
 Haas-0.172
worthiness-0.169
 Dustin-0.166
 NYU-0.164
Token 25
Token ID1679
Feature activation+7.01e-01

Pos logit contributions
 Brune+0.077
 Haas+0.074
worthiness+0.073
 Dustin+0.072
 NYU+0.071
Neg logit contributions
 corrid-0.109
acco-0.097
-0.097
2020-0.096
GGGGGGGG-0.095
Token years
Token ID812
Feature activation-8.59e-01

Pos logit contributions
 corrid+1.058
acco+0.919
+0.913
2020+0.903
 retri+0.900
Neg logit contributions
 Brune-1.035
 Haas-1.004
worthiness-0.999
 Dustin-0.967
 NYU-0.955
Token and
Token ID290
Feature activation+1.53e-01

Pos logit contributions
 Brune+0.999
 Haas+0.956
worthiness+0.946
 Dustin+0.926
 NYU+0.900
Neg logit contributions
 corrid-1.574
acco-1.403
2020-1.394
-1.389
GGGGGGGG-1.364
Token with
Token ID351
Feature activation+4.88e-02

Pos logit contributions
 Brune+0.050
 Haas+0.048
worthiness+0.048
 Dustin+0.046
 NYU+0.045
Neg logit contributions
 corrid-0.085
acco-0.075
-0.075
2020-0.075
 retri-0.074
Token
Token ID564
Feature activation-4.75e-01

Pos logit contributions
 corrid+0.080
acco+0.071
2020+0.070
+0.070
 retri+0.069
Neg logit contributions
 Brune-0.066
 Haas-0.064
worthiness-0.063
 Dustin-0.062
 NYU-0.061
Token
Token ID246
Feature activation-4.23e-01

Pos logit contributions
 Brune+0.614
 Haas+0.595
worthiness+0.595
 Dustin+0.577
 NYU+0.569
Neg logit contributions
 corrid-0.807
acco-0.708
2020-0.702
-0.697
 retri-0.692
TokenInside
Token ID24441
Feature activation-6.11e-01

Pos logit contributions
 Brune+0.632
 Haas+0.612
worthiness+0.612
 Dustin+0.596
 NYU+0.585
Neg logit contributions
 corrid-0.640
acco-0.550
 retri-0.537
2020-0.536
-0.535
Token the
Token ID262
Feature activation+5.48e-02

Pos logit contributions
 Brune+0.817
 Haas+0.788
worthiness+0.774
 Dustin+0.762
 NYU+0.743
Neg logit contributions
 corrid-1.019
acco-0.900
-0.886
2020-0.881
 retri-0.873
Token Dek
Token ID44297
Feature activation+2.78e+00

Pos logit contributions
 corrid+0.088
acco+0.076
2020+0.076
+0.076
 retri+0.075
Neg logit contributions
 Brune-0.077
 Haas-0.075
worthiness-0.074
 Dustin-0.072
 NYU-0.071
Tokenu
Token ID84
Feature activation+1.70e-01

Pos logit contributions
 corrid+4.960
acco+4.480
2020+4.437
+4.415
 retri+4.346
Neg logit contributions
 Brune-3.259
worthiness-3.137
 Haas-3.129
 Dustin-3.024
 NYU-2.967
Token Tree
Token ID12200
Feature activation+3.08e-01

Pos logit contributions
 corrid+0.243
acco+0.206
+0.205
2020+0.204
GGGGGGGG+0.201
Neg logit contributions
 Brune-0.269
 Haas-0.262
worthiness-0.254
 Dustin-0.252
 NYU-0.247
Token
Token ID447
Feature activation+5.63e-02

Pos logit contributions
 corrid+0.459
acco+0.399
+0.395
2020+0.394
 retri+0.387
Neg logit contributions
 Brune-0.462
 Haas-0.447
worthiness-0.444
 Dustin-0.435
 NYU-0.426
Token
Token ID247
Feature activation-4.90e-02

Pos logit contributions
 corrid+0.087
acco+0.075
2020+0.074
+0.074
GGGGGGGG+0.073
Neg logit contributions
 Brune-0.083
 Haas-0.080
worthiness-0.080
 Dustin-0.078
 NYU-0.077
Token,
Token ID11
Feature activation-4.30e-02

Pos logit contributions
 Brune+0.058
worthiness+0.056
 Haas+0.056
 Dustin+0.054
 NYU+0.053
Neg logit contributions
 corrid-0.088
acco-0.078
2020-0.078
-0.078
GGGGGGGG-0.076
TokenService
Token ID16177
Feature activation+2.21e-01

Pos logit contributions
 corrid+1.778
acco+1.575
+1.564
2020+1.562
 retri+1.539
Neg logit contributions
 Brune-1.323
 Haas-1.274
worthiness-1.268
 Dustin-1.233
 NYU-1.211
Token story
Token ID1621
Feature activation+7.61e-01

Pos logit contributions
 corrid+0.404
acco+0.361
+0.359
2020+0.357
GGGGGGGG+0.352
Neg logit contributions
 Brune-0.257
 Haas-0.246
worthiness-0.245
 Dustin-0.238
 NYU-0.233
Token.
Token ID13
Feature activation-5.10e-02

Pos logit contributions
 corrid+1.376
acco+1.229
2020+1.220
+1.220
 retri+1.204
Neg logit contributions
 Brune-0.894
 Haas-0.857
worthiness-0.853
 Dustin-0.827
 NYU-0.810
Token
Token ID198
Feature activation-9.17e-02

Pos logit contributions
 Brune+0.061
 Haas+0.058
worthiness+0.058
 Dustin+0.057
 NYU+0.056
Neg logit contributions
 corrid-0.095
acco-0.082
-0.082
 retri-0.082
2020-0.081
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
 Brune+0.106
 Haas+0.102
worthiness+0.101
 Dustin+0.098
 NYU+0.096
Neg logit contributions
 corrid-0.171
acco-0.151
-0.149
2020-0.149
GGGGGGGG-0.147
TokenArk
Token ID42007
Feature activation+2.78e+00

Pos logit contributions
 Brune+0.183
worthiness+0.178
 Haas+0.177
 Dustin+0.174
 NYU+0.171
Neg logit contributions
 corrid-0.209
acco-0.177
 retri-0.174
-0.173
GGGGGGGG-0.172
Tokenansas
Token ID6618
Feature activation+9.43e-01

Pos logit contributions
 corrid+2.449
acco+1.960
2020+1.938
+1.918
 retri+1.853
Neg logit contributions
 Brune-5.722
 Haas-5.596
worthiness-5.589
 Dustin-5.468
 NYU-5.411
Token has
Token ID468
Feature activation+1.51e-01

Pos logit contributions
 corrid+1.552
acco+1.360
+1.356
2020+1.354
GGGGGGGG+1.324
Neg logit contributions
 Brune-1.276
 Haas-1.231
worthiness-1.223
 Dustin-1.200
 NYU-1.175
Token already
Token ID1541
Feature activation-9.57e-02

Pos logit contributions
 corrid+0.256
+0.228
acco+0.226
2020+0.226
GGGGGGGG+0.223
Neg logit contributions
 Brune-0.198
 Haas-0.190
worthiness-0.188
 Dustin-0.185
 NYU-0.181
Token honored
Token ID21014
Feature activation+5.20e-01

Pos logit contributions
 Brune+0.128
 Haas+0.123
worthiness+0.122
 Dustin+0.120
 NYU+0.117
Neg logit contributions
 corrid-0.160
-0.142
acco-0.141
2020-0.140
GGGGGGGG-0.139
Token the
Token ID262
Feature activation+2.92e-01

Pos logit contributions
 corrid+0.893
acco+0.789
+0.785
2020+0.784
GGGGGGGG+0.769
Neg logit contributions
 Brune-0.671
 Haas-0.644
worthiness-0.639
 Dustin-0.630
 NYU-0.616
Token recognition
Token ID9465
Feature activation-5.00e-02

Pos logit contributions
 corrid+0.091
+0.081
acco+0.080
2020+0.080
GGGGGGGG+0.078
Neg logit contributions
 Brune-0.071
 Haas-0.069
worthiness-0.068
 Dustin-0.068
 NYU-0.066
Token as
Token ID355
Feature activation+1.88e-01

Pos logit contributions
 Brune+0.064
worthiness+0.061
 Haas+0.061
 Dustin+0.060
 NYU+0.058
Neg logit contributions
 corrid-0.087
acco-0.076
-0.076
2020-0.075
GGGGGGGG-0.074
Token his
Token ID465
Feature activation+9.70e-02

Pos logit contributions
 corrid+0.319
acco+0.282
+0.281
2020+0.279
GGGGGGGG+0.274
Neg logit contributions
 Brune-0.245
 Haas-0.236
worthiness-0.234
 Dustin-0.230
 NYU-0.224
Token highly
Token ID4047
Feature activation+9.04e-01

Pos logit contributions
 corrid+0.165
acco+0.147
+0.146
2020+0.146
 retri+0.143
Neg logit contributions
 Brune-0.125
 Haas-0.120
worthiness-0.119
 Dustin-0.117
 NYU-0.115
Token paid
Token ID3432
Feature activation+5.10e-01

Pos logit contributions
 corrid+1.568
acco+1.388
+1.382
2020+1.377
 retri+1.352
Neg logit contributions
 Brune-1.142
 Haas-1.095
worthiness-1.091
 Dustin-1.062
 NYU-1.044
Token linem
Token ID22774
Feature activation+2.78e+00

Pos logit contributions
 corrid+0.866
acco+0.768
+0.762
2020+0.761
 retri+0.746
Neg logit contributions
 Brune-0.663
 Haas-0.639
worthiness-0.631
 Dustin-0.619
 NYU-0.608
Tokenates
Token ID689
Feature activation-1.70e-01

Pos logit contributions
 corrid+3.320
acco+2.841
2020+2.791
+2.771
 retri+2.736
Neg logit contributions
 Brune-4.845
worthiness-4.769
 Haas-4.760
 Dustin-4.610
 NYU-4.590
Token David
Token ID3271
Feature activation+5.67e-01

Pos logit contributions
 Brune+0.210
 Haas+0.203
 Dustin+0.199
worthiness+0.198
 NYU+0.191
Neg logit contributions
 corrid-0.300
acco-0.266
-0.265
2020-0.264
GGGGGGGG-0.260
Token De
Token ID1024
Feature activation-2.48e-01

Pos logit contributions
 corrid+0.865
acco+0.747
+0.744
2020+0.740
 retri+0.728
Neg logit contributions
 Brune-0.837
 Haas-0.811
worthiness-0.807
 Dustin-0.790
 NYU-0.775
TokenCast
Token ID19248
Feature activation-2.13e-01

Pos logit contributions
 Brune+0.382
 Haas+0.371
worthiness+0.369
 Dustin+0.361
 NYU+0.355
Neg logit contributions
 corrid-0.359
acco-0.310
-0.308
2020-0.307
 retri-0.302
Tokenro
Token ID305
Feature activation+4.91e-01

Pos logit contributions
 Brune+0.206
 Haas+0.195
worthiness+0.195
 Dustin+0.188
 NYU+0.183
Neg logit contributions
 corrid-0.433
acco-0.388
-0.387
2020-0.386
 retri-0.381
Token
Token ID447
Feature activation+2.27e-01

Pos logit contributions
 Brune+0.467
 Haas+0.452
worthiness+0.448
 Dustin+0.436
 NYU+0.425
Neg logit contributions
 corrid-0.640
acco-0.559
-0.559
2020-0.556
GGGGGGGG-0.552
Token
Token ID247
Feature activation-5.63e-02

Pos logit contributions
 corrid+0.356
acco+0.310
2020+0.302
+0.302
GGGGGGGG+0.298
Neg logit contributions
 Brune-0.328
 Haas-0.320
worthiness-0.316
 Dustin-0.311
 NYU-0.303
Tokens
Token ID82
Feature activation+1.74e-01

Pos logit contributions
 Brune+0.064
 Haas+0.062
worthiness+0.062
 Dustin+0.060
 NYU+0.058
Neg logit contributions
 corrid-0.105
acco-0.093
-0.093
GGGGGGGG-0.091
2020-0.091
Token has
Token ID468
Feature activation+1.96e-01

Pos logit contributions
 corrid+0.293
acco+0.258
+0.257
2020+0.256
GGGGGGGG+0.250
Neg logit contributions
 Brune-0.227
 Haas-0.220
worthiness-0.218
 Dustin-0.213
 NYU-0.209
Token some
Token ID617
Feature activation+1.35e-01

Pos logit contributions
 corrid+0.336
acco+0.296
2020+0.295
+0.295
 retri+0.288
Neg logit contributions
 Brune-0.249
 Haas-0.243
worthiness-0.241
 Dustin-0.235
 NYU-0.229
Token miscar
Token ID35976
Feature activation+2.77e+00

Pos logit contributions
 corrid+0.252
acco+0.226
+0.225
2020+0.225
GGGGGGGG+0.220
Neg logit contributions
 Brune-0.152
 Haas-0.146
worthiness-0.145
 Dustin-0.141
 NYU-0.138
Tokenriages
Token ID16451
Feature activation+4.80e-01

Pos logit contributions
 corrid+3.405
acco+3.143
2020+3.088
 retri+3.000
+2.920
Neg logit contributions
 Brune-4.607
 Haas-4.457
worthiness-4.397
 Dustin-4.392
 NYU-4.273
Token in
Token ID287
Feature activation+6.67e-02

Pos logit contributions
 corrid+0.827
acco+0.731
+0.726
2020+0.725
 retri+0.713
Neg logit contributions
 Brune-0.611
 Haas-0.588
worthiness-0.587
 Dustin-0.570
 NYU-0.559
Token the
Token ID262
Feature activation-5.34e-04

Pos logit contributions
 corrid+0.118
acco+0.104
2020+0.104
+0.104
 retri+0.102
Neg logit contributions
 Brune-0.082
 Haas-0.079
worthiness-0.078
 Dustin-0.076
 NYU-0.075
Token past
Token ID1613
Feature activation+1.59e+00

Pos logit contributions
 Brune+0.001
 Haas+0.001
worthiness+0.001
 Dustin+0.001
 NYU+0.001
Neg logit contributions
 corrid-0.001
acco-0.001
-0.001
2020-0.001
GGGGGGGG-0.001
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
 corrid+2.739
acco+2.433
+2.416
2020+2.412
 retri+2.382
Neg logit contributions
 Brune-2.000
 Haas-1.921
worthiness-1.911
 Dustin-1.856
 NYU-1.829
Tokenoked
Token ID6545
Feature activation+4.57e-01

Pos logit contributions
 corrid+0.671
acco+0.578
+0.573
2020+0.573
 retri+0.562
Neg logit contributions
 Brune-0.747
 Haas-0.724
worthiness-0.721
 Dustin-0.706
 NYU-0.695
Token Hillary
Token ID5073
Feature activation-3.34e-01

Pos logit contributions
 corrid+0.882
acco+0.793
2020+0.788
+0.788
 retri+0.778
Neg logit contributions
 Brune-0.484
 Haas-0.462
worthiness-0.459
 Dustin-0.443
 NYU-0.433
Token Clinton
Token ID2605
Feature activation-2.04e-01

Pos logit contributions
 Brune+0.397
worthiness+0.382
 Haas+0.382
 Dustin+0.371
 NYU+0.363
Neg logit contributions
 corrid-0.602
acco-0.535
-0.533
2020-0.530
GGGGGGGG-0.524
Token and
Token ID290
Feature activation+3.85e-02

Pos logit contributions
 Brune+0.241
 Haas+0.232
worthiness+0.232
 Dustin+0.225
 NYU+0.219
Neg logit contributions
 corrid-0.371
acco-0.330
-0.329
2020-0.327
GGGGGGGG-0.322
Token Deborah
Token ID36976
Feature activation-5.86e-01

Pos logit contributions
 corrid+0.075
acco+0.067
+0.067
2020+0.067
 retri+0.066
Neg logit contributions
 Brune-0.040
 Haas-0.039
worthiness-0.038
 Dustin-0.038
 NYU-0.037
Token Wasserman
Token ID38997
Feature activation+2.73e+00

Pos logit contributions
 Brune+0.978
 Haas+0.957
worthiness+0.942
 Dustin+0.927
 NYU+0.914
Neg logit contributions
 corrid-0.788
-0.668
acco-0.668
2020-0.652
 retri-0.643
Token Schultz
Token ID26530
Feature activation+4.87e-01

Pos logit contributions
 corrid+3.923
acco+3.466
2020+3.439
 retri+3.421
+3.409
Neg logit contributions
 Brune-4.022
worthiness-3.838
 Haas-3.828
 NYU-3.738
 Dustin-3.711
Token will
Token ID481
Feature activation-1.66e-01

Pos logit contributions
 corrid+0.855
acco+0.759
+0.754
2020+0.753
 retri+0.742
Neg logit contributions
 Brune-0.601
 Haas-0.578
worthiness-0.575
 Dustin-0.559
 NYU-0.548
Token not
Token ID407
Feature activation+2.13e-01

Pos logit contributions
 Brune+0.213
 Haas+0.205
worthiness+0.204
 Dustin+0.199
 NYU+0.195
Neg logit contributions
 corrid-0.287
acco-0.252
-0.251
2020-0.250
GGGGGGGG-0.248
Token allow
Token ID1249
Feature activation-7.41e-01

Pos logit contributions
 corrid+0.365
acco+0.320
+0.320
2020+0.317
GGGGGGGG+0.315
Neg logit contributions
 Brune-0.276
 Haas-0.266
worthiness-0.265
 Dustin-0.258
 NYU-0.253
Token Bernie
Token ID10477
Feature activation+4.51e-01

Pos logit contributions
 Brune+0.779
 Haas+0.745
worthiness+0.733
 Dustin+0.720
 NYU+0.704
Neg logit contributions
 corrid-1.447
acco-1.299
-1.295
2020-1.282
GGGGGGGG-1.280
Token-
Token ID12
Feature activation+2.64e-01

Pos logit contributions
 corrid+0.290
acco+0.252
+0.249
2020+0.248
 retri+0.244
Neg logit contributions
 Brune-0.263
 Haas-0.255
worthiness-0.255
 Dustin-0.248
 NYU-0.243
TokenO
Token ID46
Feature activation-8.47e-02

Pos logit contributions
 corrid+0.402
acco+0.347
+0.342
2020+0.341
 retri+0.335
Neg logit contributions
 Brune-0.392
worthiness-0.382
 Haas-0.381
 Dustin-0.371
 NYU-0.364
Tokenri
Token ID380
Feature activation+2.30e-01

Pos logit contributions
 Brune+0.105
worthiness+0.102
 Haas+0.102
 Dustin+0.099
 NYU+0.096
Neg logit contributions
 corrid-0.149
acco-0.130
-0.130
2020-0.129
 retri-0.127
Tokenented
Token ID4714
Feature activation-1.53e-01

Pos logit contributions
 corrid+0.353
acco+0.308
+0.306
2020+0.306
 retri+0.300
Neg logit contributions
 Brune-0.335
 Haas-0.324
worthiness-0.323
 Dustin-0.315
 NYU-0.310
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
 Brune+0.191
 Haas+0.184
worthiness+0.181
 Dustin+0.177
 NYU+0.174
Neg logit contributions
 corrid-0.270
acco-0.238
-0.236
2020-0.236
GGGGGGGG-0.232
Token Prec
Token ID28737
Feature activation+2.71e+00

Pos logit contributions
 corrid+0.363
acco+0.317
+0.315
2020+0.313
 retri+0.308
Neg logit contributions
 Brune-0.306
 Haas-0.296
worthiness-0.293
 Dustin-0.286
 NYU-0.282
Tokenise
Token ID786
Feature activation-4.50e-02

Pos logit contributions
 corrid+4.557
acco+4.224
2020+4.153
 retri+4.082
+4.059
Neg logit contributions
 Brune-3.319
worthiness-3.229
 Haas-3.194
 Dustin-3.138
 NYU-3.015
Token
Token ID198
Feature activation+1.35e-01

Pos logit contributions
 Brune+0.057
 Haas+0.055
worthiness+0.054
 Dustin+0.053
 NYU+0.052
Neg logit contributions
 corrid-0.078
acco-0.069
2020-0.069
-0.068
GGGGGGGG-0.067
Token
Token ID198
Feature activation+9.28e-02

Pos logit contributions
 corrid+0.239
acco+0.215
2020+0.214
+0.214
 retri+0.210
Neg logit contributions
 Brune-0.161
 Haas-0.154
worthiness-0.153
 Dustin-0.149
 NYU-0.146
Token-
Token ID12
Feature activation+3.01e-01

Pos logit contributions
 corrid+0.151
acco+0.133
+0.133
2020+0.133
 retri+0.130
Neg logit contributions
 Brune-0.126
 Haas-0.121
worthiness-0.121
 Dustin-0.118
 NYU-0.116
Token Unt
Token ID26970
Feature activation-8.76e-01

Pos logit contributions
 corrid+0.492
acco+0.430
+0.426
2020+0.424
 retri+0.419
Neg logit contributions
 Brune-0.413
 Haas-0.399
worthiness-0.396
 Dustin-0.387
 NYU-0.380
Token Cl
Token ID1012
Feature activation+3.46e-01

Pos logit contributions
 corrid+0.006
acco+0.005
+0.005
 retri+0.005
2020+0.005
Neg logit contributions
 Brune-0.004
 Haas-0.004
worthiness-0.004
 Dustin-0.004
 NYU-0.004
Tokenad
Token ID324
Feature activation+8.32e-01

Pos logit contributions
 corrid+0.583
acco+0.522
2020+0.515
+0.513
 retri+0.506
Neg logit contributions
 Brune-0.446
 Haas-0.431
worthiness-0.429
 Dustin-0.417
 NYU-0.409
Token in
Token ID287
Feature activation+9.92e-02

Pos logit contributions
 corrid+1.352
acco+1.189
+1.180
2020+1.178
 retri+1.161
Neg logit contributions
 Brune-1.134
 Haas-1.093
worthiness-1.091
 Dustin-1.061
 NYU-1.043
Token a
Token ID257
Feature activation+2.28e-01

Pos logit contributions
 corrid+0.170
acco+0.151
2020+0.151
+0.150
GGGGGGGG+0.147
Neg logit contributions
 Brune-0.127
 Haas-0.122
worthiness-0.120
 Dustin-0.118
 NYU-0.116
Token Toronto
Token ID6586
Feature activation-4.83e-01

Pos logit contributions
 corrid+0.366
acco+0.322
2020+0.321
+0.320
GGGGGGGG+0.313
Neg logit contributions
 Brune-0.319
 Haas-0.306
worthiness-0.302
 Dustin-0.299
 NYU-0.293
Token Argon
Token ID49974
Feature activation+2.70e+00

Pos logit contributions
 Brune+0.700
 Haas+0.676
worthiness+0.668
 Dustin+0.664
 NYU+0.648
Neg logit contributions
 corrid-0.741
-0.650
2020-0.647
acco-0.646
GGGGGGGG-0.632
Tokenauts
Token ID17712
Feature activation-3.85e-01

Pos logit contributions
 corrid+3.602
acco+3.197
2020+3.158
+3.128
 retri+3.084
Neg logit contributions
 Brune-4.353
 Haas-4.228
worthiness-4.197
 Dustin-4.127
 NYU-4.042
Token football
Token ID4346
Feature activation+2.49e-01

Pos logit contributions
 Brune+0.532
 Haas+0.515
worthiness+0.502
 Dustin+0.500
 NYU+0.491
Neg logit contributions
 corrid-0.619
2020-0.542
-0.539
acco-0.539
GGGGGGGG-0.531
Token jersey
Token ID22383
Feature activation+9.99e-01

Pos logit contributions
 corrid+0.411
2020+0.361
+0.361
acco+0.361
龍喚士+0.353
Neg logit contributions
 Brune-0.335
 Haas-0.324
worthiness-0.319
 Dustin-0.314
 NYU-0.311
Token,
Token ID11
Feature activation+3.42e-02

Pos logit contributions
 corrid+1.717
acco+1.523
+1.511
2020+1.510
 retri+1.488
Neg logit contributions
 Brune-1.267
 Haas-1.220
worthiness-1.214
 Dustin-1.180
 NYU-1.159
Token he
Token ID339
Feature activation+1.55e-01

Pos logit contributions
 corrid+0.061
acco+0.054
2020+0.054
+0.054
GGGGGGGG+0.053
Neg logit contributions
 Brune-0.042
 Haas-0.040
worthiness-0.040
 Dustin-0.039
 NYU-0.038
Token
Token ID198
Feature activation-1.42e-01

Pos logit contributions
 Brune+0.172
 Haas+0.165
worthiness+0.164
 Dustin+0.159
 NYU+0.156
Neg logit contributions
 corrid-0.264
acco-0.235
-0.234
2020-0.233
 retri-0.230
TokenWater
Token ID19184
Feature activation-7.61e-01

Pos logit contributions
 Brune+0.208
 Haas+0.201
worthiness+0.201
 Dustin+0.196
 NYU+0.192
Neg logit contributions
 corrid-0.221
acco-0.190
2020-0.186
-0.186
 retri-0.186
Token Serv
Token ID3116
Feature activation+1.11e+00

Pos logit contributions
 Brune+1.041
 Haas+1.003
worthiness+0.996
 Dustin+0.973
 NYU+0.947
Neg logit contributions
 corrid-1.256
acco-1.093
-1.085
2020-1.077
 retri-1.060
Tokenant
Token ID415
Feature activation-2.48e-02

Pos logit contributions
 corrid+1.582
acco+1.361
+1.351
2020+1.349
 retri+1.324
Neg logit contributions
 Brune-1.750
 Haas-1.697
worthiness-1.689
 Dustin-1.653
 NYU-1.628
Token vs
Token ID3691
Feature activation-9.79e-01

Pos logit contributions
 Brune+0.025
 Haas+0.024
worthiness+0.024
 Dustin+0.023
 NYU+0.023
Neg logit contributions
 corrid-0.049
acco-0.044
-0.043
2020-0.043
 retri-0.043
Token Sak
Token ID13231
Feature activation+2.69e+00

Pos logit contributions
 Brune+1.383
 Haas+1.342
worthiness+1.309
 Dustin+1.302
 NYU+1.268
Neg logit contributions
 corrid-1.586
acco-1.368
2020-1.355
-1.345
GGGGGGGG-1.333
Tokenash
Token ID1077
Feature activation-5.72e-01

Pos logit contributions
 corrid+4.522
acco+4.170
2020+4.074
+4.038
 retri+4.007
Neg logit contributions
 Brune-3.277
 Haas-3.176
worthiness-3.152
 Dustin-3.071
 NYU-3.025
Tokenima
Token ID8083
Feature activation-3.92e-01

Pos logit contributions
 Brune+0.759
 Haas+0.737
worthiness+0.735
 Dustin+0.709
 NYU+0.692
Neg logit contributions
 corrid-0.969
acco-0.829
-0.826
2020-0.825
GGGGGGGG-0.824
Token the
Token ID262
Feature activation-1.83e-01

Pos logit contributions
 Brune+0.517
 Haas+0.496
worthiness+0.487
 Dustin+0.481
 NYU+0.467
Neg logit contributions
 corrid-0.668
acco-0.582
2020-0.577
-0.574
GGGGGGGG-0.571
Token Im
Token ID1846
Feature activation+9.43e-01

Pos logit contributions
 Brune+0.261
 Haas+0.252
worthiness+0.248
 Dustin+0.245
 NYU+0.239
Neg logit contributions
 corrid-0.292
acco-0.254
2020-0.251
-0.251
GGGGGGGG-0.248
Tokenpost
Token ID7353
Feature activation+2.80e-01

Pos logit contributions
 corrid+1.343
acco+1.182
2020+1.167
+1.157
 retri+1.147
Neg logit contributions
 Brune-1.451
 Haas-1.408
worthiness-1.400
 Dustin-1.371
 NYU-1.352
Token-
Token ID12
Feature activation-1.28e-01

Pos logit contributions
 corrid+0.852
acco+0.754
+0.748
2020+0.747
 retri+0.737
Neg logit contributions
 Brune-0.618
 Haas-0.596
worthiness-0.592
 Dustin-0.575
 NYU-0.566
Tokenindependence
Token ID39894
Feature activation+4.96e-01

Pos logit contributions
 Brune+0.217
 Haas+0.211
worthiness+0.211
 Dustin+0.205
 NYU+0.203
Neg logit contributions
 corrid-0.166
acco-0.140
-0.138
2020-0.138
 retri-0.136
Token rally
Token ID7903
Feature activation-8.17e-01

Pos logit contributions
 corrid+1.015
acco+0.919
+0.913
2020+0.913
 retri+0.901
Neg logit contributions
 Brune-0.468
 Haas-0.444
worthiness-0.441
 Dustin-0.424
 NYU-0.414
Token at
Token ID379
Feature activation+1.08e+00

Pos logit contributions
 Brune+1.038
 Haas+1.004
worthiness+0.987
 Dustin+0.970
 NYU+0.952
Neg logit contributions
 corrid-1.399
acco-1.243
-1.238
2020-1.225
GGGGGGGG-1.212
Token Plaza
Token ID23280
Feature activation+2.59e-01

Pos logit contributions
 corrid+1.806
acco+1.595
+1.582
2020+1.580
 retri+1.555
Neg logit contributions
 Brune-1.423
worthiness-1.369
 Haas-1.369
 Dustin-1.331
 NYU-1.304
Token Esp
Token ID20386
Feature activation+2.68e+00

Pos logit contributions
 corrid+0.460
acco+0.409
+0.406
2020+0.406
 retri+0.400
Neg logit contributions
 Brune-0.314
 Haas-0.302
worthiness-0.300
 Dustin-0.291
 NYU-0.286
Tokenana
Token ID2271
Feature activation-2.32e-02

Pos logit contributions
 corrid+3.981
2020+3.888
acco+3.852
+3.704
Preview+3.680
Neg logit contributions
 Brune-3.605
worthiness-3.420
 Haas-3.407
 Dustin-3.320
 NYU-3.261
Token in
Token ID287
Feature activation+1.12e-01

Pos logit contributions
 Brune+0.032
 Haas+0.031
worthiness+0.031
 Dustin+0.030
 NYU+0.030
Neg logit contributions
 corrid-0.037
acco-0.033
-0.033
2020-0.032
 retri-0.032
Token Barcelona
Token ID15142
Feature activation+8.19e-01

Pos logit contributions
 corrid+0.175
acco+0.154
+0.153
2020+0.153
 retri+0.150
Neg logit contributions
 Brune-0.159
 Haas-0.154
worthiness-0.152
 Dustin-0.148
 NYU-0.147
Token tonight
Token ID9975
Feature activation+1.17e+00

Pos logit contributions
 corrid+1.428
acco+1.268
+1.258
2020+1.257
 retri+1.239
Neg logit contributions
 Brune-1.022
 Haas-0.983
worthiness-0.977
 Dustin-0.950
 NYU-0.933
Token
Token ID198
Feature activation+9.23e-02

Pos logit contributions
 corrid+2.052
acco+1.826
+1.813
2020+1.812
 retri+1.786
Neg logit contributions
 Brune-1.438
 Haas-1.383
worthiness-1.379
 Dustin-1.336
 NYU-1.311
Token-
Token ID12
Feature activation-1.20e-01

Pos logit contributions
 corrid+0.746
acco+0.654
2020+0.650
+0.648
 retri+0.639
Neg logit contributions
 Brune-0.589
worthiness-0.571
 Haas-0.564
 Dustin-0.554
 NYU-0.542
Tokenindependence
Token ID39894
Feature activation+4.97e-01

Pos logit contributions
 Brune+0.197
worthiness+0.192
 Haas+0.192
 Dustin+0.185
 NYU+0.184
Neg logit contributions
 corrid-0.161
acco-0.136
-0.134
 retri-0.133
2020-0.133
Token rally
Token ID7903
Feature activation-6.57e-01

Pos logit contributions
 corrid+0.874
acco+0.781
+0.776
2020+0.773
 retri+0.761
Neg logit contributions
 Brune-0.609
 Haas-0.588
worthiness-0.582
 Dustin-0.565
 NYU-0.556
Token at
Token ID379
Feature activation+1.07e+00

Pos logit contributions
 Brune+0.826
 Haas+0.792
worthiness+0.777
 Dustin+0.762
 NYU+0.749
Neg logit contributions
 corrid-1.146
-1.015
acco-1.015
2020-1.003
GGGGGGGG-0.996
Token Plaza
Token ID23280
Feature activation+2.88e-01

Pos logit contributions
 corrid+1.806
acco+1.596
+1.587
2020+1.587
 retri+1.561
Neg logit contributions
 Brune-1.410
 Haas-1.364
worthiness-1.342
 Dustin-1.310
 NYU-1.295
Token Esp
Token ID20386
Feature activation+2.68e+00

Pos logit contributions
 corrid+0.504
acco+0.449
+0.447
2020+0.446
 retri+0.440
Neg logit contributions
 Brune-0.358
 Haas-0.345
worthiness-0.338
 Dustin-0.331
 NYU-0.326
Tokenana
Token ID2271
Feature activation-9.62e-02

Pos logit contributions
 corrid+4.661
acco+4.473
2020+4.416
+4.302
Preview+4.259
Neg logit contributions
 Brune-2.985
 Haas-2.882
worthiness-2.855
 Dustin-2.763
 NYU-2.677
Token tonight
Token ID9975
Feature activation+1.34e+00

Pos logit contributions
 Brune+0.120
 Haas+0.116
worthiness+0.112
 Dustin+0.111
 NYU+0.109
Neg logit contributions
 corrid-0.168
acco-0.149
-0.149
2020-0.147
GGGGGGGG-0.145
Token ahead
Token ID4058
Feature activation-1.38e-01

Pos logit contributions
 corrid+2.238
acco+1.980
+1.965
2020+1.965
 retri+1.935
Neg logit contributions
 Brune-1.742
 Haas-1.680
worthiness-1.678
 Dustin-1.627
 NYU-1.598
Token of
Token ID286
Feature activation+1.71e-01

Pos logit contributions
 Brune+0.177
 Haas+0.170
worthiness+0.169
 Dustin+0.165
 NYU+0.162
Neg logit contributions
 corrid-0.241
acco-0.210
-0.208
2020-0.207
GGGGGGGG-0.206
Token Sunday
Token ID3502
Feature activation+3.77e-01

Pos logit contributions
 corrid+0.287
acco+0.254
+0.252
2020+0.251
 retri+0.247
Neg logit contributions
 Brune-0.224
 Haas-0.217
worthiness-0.214
 Dustin-0.208
 NYU-0.206
Token has
Token ID468
Feature activation+4.62e-02

Pos logit contributions
 Brune+0.199
 Haas+0.192
worthiness+0.189
 Dustin+0.185
 NYU+0.181
Neg logit contributions
 corrid-0.286
acco-0.253
-0.252
2020-0.252
GGGGGGGG-0.247
Token been
Token ID587
Feature activation-1.73e-01

Pos logit contributions
 corrid+0.081
acco+0.072
+0.072
2020+0.072
 retri+0.070
Neg logit contributions
 Brune-0.057
 Haas-0.055
worthiness-0.055
 Dustin-0.053
 NYU-0.052
Token taken
Token ID2077
Feature activation+3.83e-01

Pos logit contributions
 Brune+0.227
 Haas+0.219
worthiness+0.217
 Dustin+0.212
 NYU+0.208
Neg logit contributions
 corrid-0.290
acco-0.256
-0.255
2020-0.255
GGGGGGGG-0.249
Token to
Token ID284
Feature activation+6.34e-02

Pos logit contributions
 corrid+0.583
acco+0.508
+0.504
2020+0.504
 retri+0.493
Neg logit contributions
 Brune-0.563
 Haas-0.545
worthiness-0.542
 Dustin-0.530
 NYU-0.522
Token a
Token ID257
Feature activation+1.15e-01

Pos logit contributions
 corrid+0.108
acco+0.095
+0.095
2020+0.095
 retri+0.093
Neg logit contributions
 Brune-0.083
 Haas-0.080
worthiness-0.078
 Dustin-0.076
 NYU-0.076
Token Sak
Token ID13231
Feature activation+2.68e+00

Pos logit contributions
 corrid+0.176
acco+0.153
+0.153
2020+0.152
 retri+0.148
Neg logit contributions
 Brune-0.170
 Haas-0.163
worthiness-0.161
 Dustin-0.158
 NYU-0.156
Tokenet
Token ID316
Feature activation-1.79e-01

Pos logit contributions
 corrid+4.529
acco+4.172
2020+4.045
+3.972
 retri+3.948
Neg logit contributions
 Brune-3.238
 Haas-3.139
worthiness-3.113
 Dustin-3.049
 NYU-2.969
Token court
Token ID2184
Feature activation+2.51e-01

Pos logit contributions
 Brune+0.256
 Haas+0.247
worthiness+0.242
 Dustin+0.237
 NYU+0.235
Neg logit contributions
 corrid-0.282
acco-0.246
-0.246
2020-0.244
 retri-0.240
Token after
Token ID706
Feature activation+2.52e-02

Pos logit contributions
 corrid+0.432
acco+0.383
+0.380
2020+0.380
 retri+0.374
Neg logit contributions
 Brune-0.317
 Haas-0.305
worthiness-0.304
 Dustin-0.295
 NYU-0.290
Token being
Token ID852
Feature activation-1.94e-01

Pos logit contributions
 corrid+0.042
acco+0.037
2020+0.037
+0.037
GGGGGGGG+0.036
Neg logit contributions
 Brune-0.033
 Haas-0.032
worthiness-0.032
 Dustin-0.031
 NYU-0.031
Token held
Token ID2714
Feature activation+3.29e-01

Pos logit contributions
 Brune+0.250
 Haas+0.242
worthiness+0.239
 Dustin+0.233
 NYU+0.229
Neg logit contributions
 corrid-0.332
acco-0.292
2020-0.291
-0.291
 retri-0.285
Token too
Token ID1165
Feature activation-5.32e-01

Pos logit contributions
 Brune+0.035
 Haas+0.034
worthiness+0.033
 Dustin+0.033
 NYU+0.032
Neg logit contributions
 corrid-0.051
acco-0.045
2020-0.045
-0.045
GGGGGGGG-0.044
Token:
Token ID25
Feature activation-4.21e-01

Pos logit contributions
 Brune+0.648
 Haas+0.621
worthiness+0.619
 Dustin+0.599
 NYU+0.590
Neg logit contributions
 corrid-0.939
acco-0.834
-0.830
2020-0.829
 retri-0.819
Token These
Token ID2312
Feature activation-3.03e-01

Pos logit contributions
 Brune+0.532
 Haas+0.514
worthiness+0.500
 Dustin+0.497
 NYU+0.487
Neg logit contributions
 corrid-0.733
acco-0.650
2020-0.647
-0.645
GGGGGGGG-0.633
Token "
Token ID366
Feature activation-6.71e-01

Pos logit contributions
 Brune+0.367
 Haas+0.351
worthiness+0.350
 Dustin+0.340
 NYU+0.333
Neg logit contributions
 corrid-0.540
acco-0.484
-0.480
2020-0.479
GGGGGGGG-0.470
Tokenlab
Token ID23912
Feature activation+1.19e+00

Pos logit contributions
 Brune+0.910
worthiness+0.886
 Haas+0.880
 Dustin+0.854
 NYU+0.839
Neg logit contributions
 corrid-1.093
acco-0.955
-0.943
2020-0.938
GGGGGGGG-0.932
Tokenyrinth
Token ID21324
Feature activation+2.67e+00

Pos logit contributions
 corrid+1.632
acco+1.403
2020+1.386
+1.385
 retri+1.363
Neg logit contributions
 Brune-1.930
 Haas-1.875
worthiness-1.869
 Dustin-1.829
 NYU-1.803
Tokenine
Token ID500
Feature activation-5.54e-03

Pos logit contributions
 corrid+4.344
acco+3.822
2020+3.790
+3.780
 retri+3.766
Neg logit contributions
 Brune-3.576
 Haas-3.441
worthiness-3.434
 Dustin-3.346
 NYU-3.301
Token worlds
Token ID11621
Feature activation+6.17e-01

Pos logit contributions
 Brune+0.007
 Haas+0.007
worthiness+0.007
 Dustin+0.007
 NYU+0.007
Neg logit contributions
 corrid-0.009
acco-0.008
2020-0.008
-0.008
GGGGGGGG-0.008
Token filled
Token ID5901
Feature activation+1.64e-01

Pos logit contributions
 corrid+0.930
acco+0.809
+0.803
2020+0.802
 retri+0.788
Neg logit contributions
 Brune-0.914
 Haas-0.884
worthiness-0.881
 Dustin-0.860
 NYU-0.847
Token with
Token ID351
Feature activation+6.50e-02

Pos logit contributions
 corrid+0.285
acco+0.252
+0.250
2020+0.250
 retri+0.246
Neg logit contributions
 Brune-0.206
 Haas-0.200
worthiness-0.198
 Dustin-0.192
 NYU-0.189
Token secrets
Token ID13141
Feature activation+7.69e-01

Pos logit contributions
 corrid+0.107
acco+0.094
2020+0.094
+0.094
GGGGGGGG+0.091
Neg logit contributions
 Brune-0.088
 Haas-0.085
worthiness-0.084
 Dustin-0.082
 NYU-0.081
Token Castle
Token ID11312
Feature activation+4.25e-01

Pos logit contributions
 Brune+0.478
 Haas+0.462
worthiness+0.461
 Dustin+0.451
 NYU+0.443
Neg logit contributions
 corrid-0.517
-0.449
2020-0.447
acco-0.447
 retri-0.438
Token,
Token ID11
Feature activation+3.55e-02

Pos logit contributions
 corrid+0.715
acco+0.624
+0.624
2020+0.623
GGGGGGGG+0.611
Neg logit contributions
 Brune-0.559
 Haas-0.543
worthiness-0.536
 Dustin-0.530
 NYU-0.516
Token some
Token ID617
Feature activation+9.36e-02

Pos logit contributions
 corrid+0.060
2020+0.053
acco+0.053
+0.053
GGGGGGGG+0.052
Neg logit contributions
 Brune-0.046
 Haas-0.045
worthiness-0.044
 Dustin-0.044
 NYU-0.043
Token see
Token ID766
Feature activation-5.77e-01

Pos logit contributions
 corrid+0.158
acco+0.140
+0.140
2020+0.139
GGGGGGGG+0.137
Neg logit contributions
 Brune-0.122
 Haas-0.117
worthiness-0.115
 Dustin-0.114
 NYU-0.112
Token "
Token ID366
Feature activation-4.87e-01

Pos logit contributions
 Brune+0.765
 Haas+0.741
 Dustin+0.724
worthiness+0.721
 NYU+0.706
Neg logit contributions
 corrid-0.957
2020-0.848
acco-0.846
-0.846
龍喚士-0.827
TokenPokémon
Token ID46602
Feature activation+2.66e+00

Pos logit contributions
 Brune+0.694
worthiness+0.676
 Haas+0.672
 Dustin+0.654
 NYU+0.643
Neg logit contributions
 corrid-0.757
acco-0.655
-0.648
 retri-0.645
2020-0.644
Token people
Token ID661
Feature activation-1.28e-01

Pos logit contributions
 corrid+4.038
acco+3.480
2020+3.473
+3.451
 retri+3.421
Neg logit contributions
 Brune-3.897
worthiness-3.752
 Haas-3.735
 Dustin-3.636
 NYU-3.587
Token"
Token ID1
Feature activation+8.53e-01

Pos logit contributions
 Brune+0.183
 Haas+0.177
worthiness+0.176
 Dustin+0.173
 NYU+0.170
Neg logit contributions
 corrid-0.201
-0.176
acco-0.175
2020-0.174
 retri-0.171
Token as
Token ID355
Feature activation+3.28e-02

Pos logit contributions
 corrid+1.460
acco+1.292
+1.289
2020+1.283
 retri+1.260
Neg logit contributions
 Brune-1.092
 Haas-1.054
worthiness-1.046
 Dustin-1.022
 NYU-1.001
Token an
Token ID281
Feature activation-5.67e-01

Pos logit contributions
 corrid+0.053
+0.047
2020+0.047
acco+0.047
 retri+0.046
Neg logit contributions
 Brune-0.045
 Haas-0.044
worthiness-0.043
 Dustin-0.042
 NYU-0.042
Token invasive
Token ID27376
Feature activation+1.07e+00

Pos logit contributions
 Brune+0.800
 Haas+0.779
worthiness+0.773
 Dustin+0.756
 NYU+0.747
Neg logit contributions
 corrid-0.896
-0.780
acco-0.779
2020-0.774
 retri-0.762
TokenIs
Token ID3792
Feature activation-2.32e-01

Pos logit contributions
 corrid+0.111
acco+0.094
GGGGGGGG+0.092
+0.092
 retri+0.092
Neg logit contributions
 Brune-0.105
worthiness-0.102
 Haas-0.101
 Dustin-0.098
 NYU-0.097
Token it
Token ID340
Feature activation+2.95e-02

Pos logit contributions
 Brune+0.340
 Haas+0.329
worthiness+0.322
 Dustin+0.320
 NYU+0.316
Neg logit contributions
 corrid-0.358
acco-0.308
-0.304
2020-0.304
GGGGGGGG-0.303
Token really
Token ID1107
Feature activation+3.18e-01

Pos logit contributions
 corrid+0.050
acco+0.044
+0.044
2020+0.043
GGGGGGGG+0.043
Neg logit contributions
 Brune-0.039
 Haas-0.037
worthiness-0.037
 Dustin-0.036
 NYU-0.036
Token likely
Token ID1884
Feature activation-3.89e-01

Pos logit contributions
 corrid+0.548
acco+0.485
+0.479
2020+0.476
GGGGGGGG+0.473
Neg logit contributions
 Brune-0.411
 Haas-0.393
worthiness-0.389
 Dustin-0.383
 NYU-0.376
Token that
Token ID326
Feature activation+1.22e-01

Pos logit contributions
 Brune+0.523
 Haas+0.499
worthiness+0.497
 Dustin+0.490
 NYU+0.479
Neg logit contributions
 corrid-0.654
acco-0.568
-0.565
GGGGGGGG-0.563
2020-0.559
Token Amazon
Token ID6186
Feature activation+2.64e+00

Pos logit contributions
 corrid+0.202
acco+0.175
+0.175
GGGGGGGG+0.174
2020+0.173
Neg logit contributions
 Brune-0.168
 Haas-0.161
worthiness-0.159
 Dustin-0.157
 NYU-0.154
Token is
Token ID318
Feature activation-6.72e-02

Pos logit contributions
 corrid+4.629
acco+4.123
2020+4.100
+4.096
 retri+4.040
Neg logit contributions
 Brune-3.227
 Haas-3.112
worthiness-3.094
 Dustin-2.996
 NYU-2.954
Token going
Token ID1016
Feature activation+7.45e-02

Pos logit contributions
 Brune+0.089
 Haas+0.084
worthiness+0.084
 Dustin+0.082
 NYU+0.081
Neg logit contributions
 corrid-0.114
acco-0.100
-0.099
2020-0.099
GGGGGGGG-0.098
Token to
Token ID284
Feature activation+2.36e-01

Pos logit contributions
 corrid+0.112
acco+0.097
+0.096
2020+0.096
 retri+0.094
Neg logit contributions
 Brune-0.111
 Haas-0.107
worthiness-0.107
 Dustin-0.104
 NYU-0.103
Token go
Token ID467
Feature activation+3.14e-01

Pos logit contributions
 corrid+0.396
acco+0.347
+0.343
2020+0.343
GGGGGGGG+0.342
Neg logit contributions
 Brune-0.317
 Haas-0.303
worthiness-0.301
 Dustin-0.296
 NYU-0.290
Token all
Token ID477
Feature activation+2.91e-01

Pos logit contributions
 corrid+0.523
acco+0.462
2020+0.457
+0.454
GGGGGGGG+0.451
Neg logit contributions
 Brune-0.420
 Haas-0.405
worthiness-0.395
 Dustin-0.392
 NYU-0.387
TokenAccording
Token ID4821
Feature activation-6.64e-01

Pos logit contributions
 Brune+0.286
 Haas+0.276
worthiness+0.275
 Dustin+0.271
 NYU+0.267
Neg logit contributions
 corrid-0.308
acco-0.260
 retri-0.254
-0.253
2020-0.251
Token to
Token ID284
Feature activation+1.76e-01

Pos logit contributions
 Brune+0.926
 Haas+0.895
worthiness+0.886
 Dustin+0.872
 NYU+0.860
Neg logit contributions
 corrid-1.114
acco-0.946
GGGGGGGG-0.944
-0.937
2020-0.922
Token CBS
Token ID11133
Feature activation+8.62e-01

Pos logit contributions
 corrid+0.300
acco+0.265
2020+0.265
+0.264
GGGGGGGG+0.257
Neg logit contributions
 Brune-0.230
 Haas-0.221
worthiness-0.217
 Dustin-0.216
 NYU-0.212
Token New
Token ID968
Feature activation+4.44e-02

Pos logit contributions
 corrid+1.516
acco+1.347
2020+1.339
+1.338
 retri+1.319
Neg logit contributions
 Brune-1.058
 Haas-1.017
worthiness-1.013
 Dustin-0.982
 NYU-0.964
Token York
Token ID1971
Feature activation-2.79e-01

Pos logit contributions
 corrid+0.065
acco+0.056
+0.056
2020+0.055
 retri+0.054
Neg logit contributions
 Brune-0.068
 Haas-0.066
worthiness-0.066
 Dustin-0.065
 NYU-0.064
Token cho
Token ID1727
Feature activation-3.30e+00

Pos logit contributions
 Brune+0.352
 Haas+0.338
worthiness+0.335
 Dustin+0.328
 NYU+0.322
Neg logit contributions
 corrid-0.482
acco-0.427
-0.424
2020-0.424
 retri-0.416
Tokenpper
Token ID2848
Feature activation-6.09e-01

Pos logit contributions
 Brune+3.408
 Haas+3.236
 Dustin+3.139
worthiness+3.111
 NYU+3.077
Neg logit contributions
 corrid-6.425
-5.691
GGGGGGGG-5.626
龍喚士-5.606
 retri-5.539
Token reporter
Token ID9095
Feature activation+4.86e-01

Pos logit contributions
 Brune+0.737
 Haas+0.708
worthiness+0.703
 Dustin+0.692
 NYU+0.674
Neg logit contributions
 corrid-1.087
acco-0.969
-0.961
2020-0.960
GGGGGGGG-0.942
Token Joe
Token ID5689
Feature activation+3.29e-01

Pos logit contributions
 corrid+0.895
acco+0.803
2020+0.798
+0.797
 retri+0.788
Neg logit contributions
 Brune-0.549
worthiness-0.526
 Haas-0.526
 Dustin-0.503
 NYU-0.496
Token B
Token ID347
Feature activation-2.50e-01

Pos logit contributions
 corrid+0.549
acco+0.486
2020+0.481
+0.481
 retri+0.474
Neg logit contributions
 Brune-0.433
 Haas-0.417
worthiness-0.416
 Dustin-0.405
 NYU-0.398
Tokenier
Token ID959
Feature activation-9.22e-01

Pos logit contributions
 Brune+0.335
 Haas+0.324
worthiness+0.322
 Dustin+0.314
 NYU+0.308
Neg logit contributions
 corrid-0.411
acco-0.362
-0.359
2020-0.359
 retri-0.354
Token!
Token ID0
Feature activation+2.68e-01

Pos logit contributions
 corrid+0.302
acco+0.267
+0.266
2020+0.265
GGGGGGGG+0.261
Neg logit contributions
 Brune-0.208
 Haas-0.200
worthiness-0.198
 Dustin-0.193
 NYU-0.190
Token
Token ID198
Feature activation-4.52e-02

Pos logit contributions
 corrid+0.482
acco+0.428
+0.426
2020+0.425
 retri+0.420
Neg logit contributions
 Brune-0.320
 Haas-0.307
worthiness-0.305
 Dustin-0.297
 NYU-0.292
Token
Token ID198
Feature activation-6.17e-02

Pos logit contributions
 Brune+0.052
 Haas+0.050
worthiness+0.050
 Dustin+0.049
 NYU+0.048
Neg logit contributions
 corrid-0.084
acco-0.074
-0.073
2020-0.073
 retri-0.072
TokenHOW
Token ID37181
Feature activation-5.67e-01

Pos logit contributions
 Brune+0.090
worthiness+0.088
 Haas+0.087
 Dustin+0.085
 NYU+0.084
Neg logit contributions
 corrid-0.095
acco-0.081
 retri-0.079
-0.079
GGGGGGGG-0.079
Token TO
Token ID5390
Feature activation-7.49e-01

Pos logit contributions
 Brune+0.753
 Haas+0.726
worthiness+0.718
 Dustin+0.706
 NYU+0.694
Neg logit contributions
 corrid-0.945
acco-0.835
-0.826
2020-0.820
 retri-0.813
Token INST
Token ID40589
Feature activation-2.75e+00

Pos logit contributions
 Brune+0.901
 Haas+0.866
worthiness+0.854
 Dustin+0.836
 NYU+0.827
Neg logit contributions
 corrid-1.360
acco-1.204
-1.180
2020-1.175
GGGGGGGG-1.162
TokenALL
Token ID7036
Feature activation-9.82e-01

Pos logit contributions
 Brune+2.487
 Haas+2.338
 Dustin+2.337
worthiness+2.319
 NYU+2.253
Neg logit contributions
 corrid-5.680
acco-5.073
 retri-5.023
-4.948
termination-4.944
Token NET
Token ID30502
Feature activation-1.08e+00

Pos logit contributions
 Brune+1.195
 Haas+1.160
worthiness+1.140
 Dustin+1.117
 NYU+1.110
Neg logit contributions
 corrid-1.748
acco-1.545
-1.523
 retri-1.521
2020-1.520
TokenFL
Token ID3697
Feature activation-1.07e+00

Pos logit contributions
 Brune+1.781
worthiness+1.757
 Haas+1.742
 Dustin+1.693
lis+1.672
Neg logit contributions
 corrid-1.506
acco-1.243
 retri-1.207
-1.179
GGGGGGGG-1.179
TokenIX
Token ID10426
Feature activation-6.14e-01

Pos logit contributions
 Brune+1.242
worthiness+1.195
 Haas+1.190
 Dustin+1.166
 NYU+1.143
Neg logit contributions
 corrid-2.041
acco-1.758
 retri-1.729
GGGGGGGG-1.715
-1.707
Token ON
Token ID6177
Feature activation-1.31e+00

Pos logit contributions
 Brune+0.853
 Haas+0.835
worthiness+0.824
 Dustin+0.800
 NYU+0.797
Neg logit contributions
 corrid-0.991
acco-0.865
 retri-0.847
-0.844
2020-0.830
Token.
Token ID13
Feature activation+1.32e-01

Pos logit contributions
 corrid+0.859
acco+0.765
+0.759
2020+0.758
 retri+0.747
Neg logit contributions
 Brune-0.579
 Haas-0.556
worthiness-0.553
 Dustin-0.537
 NYU-0.527
Token
Token ID198
Feature activation-2.54e-02

Pos logit contributions
 corrid+0.234
acco+0.207
+0.204
 retri+0.203
2020+0.203
Neg logit contributions
 Brune-0.163
 Haas-0.157
worthiness-0.156
 Dustin-0.152
 NYU-0.149
Token
Token ID198
Feature activation-6.86e-02

Pos logit contributions
 Brune+0.030
 Haas+0.028
worthiness+0.028
 Dustin+0.028
 NYU+0.027
Neg logit contributions
 corrid-0.046
acco-0.041
-0.041
2020-0.041
 retri-0.040
TokenHOW
Token ID37181
Feature activation-6.08e-01

Pos logit contributions
 Brune+0.101
worthiness+0.098
 Haas+0.097
 Dustin+0.095
 NYU+0.094
Neg logit contributions
 corrid-0.105
acco-0.091
-0.089
 retri-0.088
2020-0.088
Token TO
Token ID5390
Feature activation-7.94e-01

Pos logit contributions
 Brune+0.845
 Haas+0.816
worthiness+0.814
 Dustin+0.792
 NYU+0.778
Neg logit contributions
 corrid-0.971
acco-0.852
2020-0.846
-0.845
 retri-0.831
Token INST
Token ID40589
Feature activation-2.68e+00

Pos logit contributions
 Brune+0.953
 Haas+0.917
worthiness+0.902
 Dustin+0.886
 NYU+0.878
Neg logit contributions
 corrid-1.445
acco-1.282
-1.256
2020-1.249
GGGGGGGG-1.233
TokenALL
Token ID7036
Feature activation-7.70e-01

Pos logit contributions
 Brune+2.472
 Haas+2.323
 Dustin+2.319
worthiness+2.291
 NYU+2.271
Neg logit contributions
 corrid-5.700
acco-4.959
 retri-4.902
GGGGGGGG-4.819
termination-4.818
Token NET
Token ID30502
Feature activation-9.36e-01

Pos logit contributions
 Brune+0.872
 Haas+0.844
worthiness+0.826
 Dustin+0.812
 NYU+0.805
Neg logit contributions
 corrid-1.430
acco-1.278
-1.264
2020-1.260
 retri-1.251
TokenFL
Token ID3697
Feature activation-1.00e+00

Pos logit contributions
 Brune+1.542
worthiness+1.525
 Haas+1.514
 Dustin+1.479
 NYU+1.462
Neg logit contributions
 corrid-1.324
acco-1.076
 retri-1.049
GGGGGGGG-1.027
-1.015
TokenIX
Token ID10426
Feature activation-6.03e-01

Pos logit contributions
 Brune+1.777
worthiness+1.741
 Haas+1.738
 Dustin+1.715
 NYU+1.694
Neg logit contributions
 corrid-1.281
acco-1.008
 retri-1.003
GGGGGGGG-0.983
-0.972
Token ON
Token ID6177
Feature activation-1.19e+00

Pos logit contributions
 Brune+0.711
 Haas+0.684
worthiness+0.675
 Dustin+0.660
 NYU+0.652
Neg logit contributions
 corrid-1.099
acco-0.978
-0.965
2020-0.952
 retri-0.949
Token by
Token ID416
Feature activation-5.20e-02

Pos logit contributions
 corrid+0.899
+0.785
acco+0.784
2020+0.780
 retri+0.767
Neg logit contributions
 Brune-0.796
 Haas-0.766
worthiness-0.762
 Dustin-0.740
 NYU-0.732
Token pro
Token ID386
Feature activation+2.87e-01

Pos logit contributions
 Brune+0.069
 Haas+0.067
worthiness+0.066
 Dustin+0.064
 NYU+0.064
Neg logit contributions
 corrid-0.087
acco-0.077
-0.076
2020-0.076
龍喚士-0.075
Token-
Token ID12
Feature activation-2.32e-01

Pos logit contributions
 corrid+0.490
acco+0.434
2020+0.430
+0.430
 retri+0.423
Neg logit contributions
 Brune-0.368
 Haas-0.355
worthiness-0.354
 Dustin-0.344
 NYU-0.338
Tokencor
Token ID10215
Feature activation+3.35e-01

Pos logit contributions
 Brune+0.308
worthiness+0.298
 Haas+0.297
 Dustin+0.284
 NYU+0.283
Neg logit contributions
 corrid-0.388
acco-0.339
-0.336
 retri-0.333
2020-0.333
Tokenporate
Token ID38133
Feature activation+2.93e-01

Pos logit contributions
 corrid+0.718
acco+0.652
+0.648
2020+0.648
 retri+0.641
Neg logit contributions
 Brune-0.283
 Haas-0.268
worthiness-0.266
 Dustin-0.254
 NYU-0.247
Token arbit
Token ID9277
Feature activation-2.58e+00

Pos logit contributions
 corrid+0.508
acco+0.453
+0.449
2020+0.449
GGGGGGGG+0.440
Neg logit contributions
 Brune-0.371
 Haas-0.356
worthiness-0.352
 Dustin-0.343
 NYU-0.339
Tokenrators
Token ID18942
Feature activation-2.00e+00

Pos logit contributions
 Brune+2.786
 Haas+2.633
worthiness+2.630
rage+2.626
 Dustin+2.526
Neg logit contributions
 corrid-4.992
-4.441
acco-4.361
GGGGGGGG-4.360
2020-4.309
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
 Brune+2.320
 Haas+2.238
worthiness+2.174
 Dustin+2.122
 NYU+2.087
Neg logit contributions
 corrid-3.686
acco-3.298
-3.251
2020-3.239
GGGGGGGG-3.187
Token
Token ID198
Feature activation-1.15e-02

Pos logit contributions
 Brune+0.193
 Haas+0.186
worthiness+0.181
 Dustin+0.178
 NYU+0.177
Neg logit contributions
 corrid-0.274
acco-0.240
 retri-0.234
-0.234
2020-0.232
Token
Token ID198
Feature activation-4.17e-02

Pos logit contributions
 Brune+0.013
 Haas+0.013
worthiness+0.013
 Dustin+0.012
 NYU+0.012
Neg logit contributions
 corrid-0.021
acco-0.019
-0.019
2020-0.019
 retri-0.018
TokenA
Token ID32
Feature activation+4.17e-01

Pos logit contributions
 Brune+0.062
 Haas+0.060
worthiness+0.060
 Dustin+0.058
 NYU+0.058
Neg logit contributions
 corrid-0.064
acco-0.055
 retri-0.053
-0.053
2020-0.053
Token and
Token ID290
Feature activation-1.11e-01

Pos logit contributions
 Brune+0.356
 Haas+0.344
worthiness+0.341
 Dustin+0.334
 NYU+0.328
Neg logit contributions
 corrid-0.444
acco-0.393
2020-0.389
-0.389
 retri-0.383
Token collect
Token ID2824
Feature activation+1.58e-01

Pos logit contributions
 Brune+0.140
 Haas+0.135
worthiness+0.134
 Dustin+0.131
 NYU+0.128
Neg logit contributions
 corrid-0.194
acco-0.171
-0.170
2020-0.169
GGGGGGGG-0.168
Token the
Token ID262
Feature activation-1.79e-02

Pos logit contributions
 corrid+0.269
acco+0.237
+0.236
2020+0.236
GGGGGGGG+0.232
Neg logit contributions
 Brune-0.204
 Haas-0.197
worthiness-0.195
 Dustin-0.191
 NYU-0.187
Token Cur
Token ID4424
Feature activation-1.33e+00

Pos logit contributions
 Brune+0.024
 Haas+0.023
worthiness+0.023
 Dustin+0.023
 NYU+0.022
Neg logit contributions
 corrid-0.029
acco-0.026
2020-0.026
-0.026
GGGGGGGG-0.025
Tokenric
Token ID1173
Feature activation+1.35e-01

Pos logit contributions
 Brune+1.799
 Haas+1.719
worthiness+1.716
 Dustin+1.680
lis+1.662
Neg logit contributions
 corrid-2.200
-1.915
2020-1.890
GGGGGGGG-1.873
 retri-1.870
Tokenulum
Token ID14452
Feature activation-2.54e+00

Pos logit contributions
 corrid+0.290
acco+0.262
+0.262
2020+0.261
 retri+0.258
Neg logit contributions
 Brune-0.114
 Haas-0.107
worthiness-0.106
 Dustin-0.102
 NYU-0.099
Token Vit
Token ID18271
Feature activation-2.54e-01

Pos logit contributions
 Brune+3.275
 Haas+3.181
 Dustin+3.102
worthiness+3.031
 NYU+3.005
Neg logit contributions
 corrid-4.321
-3.732
acco-3.695
termination-3.637
GGGGGGGG-3.633
Tokenae
Token ID3609
Feature activation-1.01e+00

Pos logit contributions
 Brune+0.265
 Haas+0.253
worthiness+0.251
 Dustin+0.243
 NYU+0.238
Neg logit contributions
 corrid-0.497
acco-0.443
-0.442
2020-0.441
 retri-0.435
Token of
Token ID286
Feature activation-1.55e-01

Pos logit contributions
 Brune+1.250
 Haas+1.204
worthiness+1.182
 Dustin+1.172
 NYU+1.142
Neg logit contributions
 corrid-1.776
-1.559
acco-1.556
2020-1.547
GGGGGGGG-1.537
Token everyone
Token ID2506
Feature activation-1.41e-01

Pos logit contributions
 Brune+0.197
 Haas+0.190
worthiness+0.187
 Dustin+0.184
 NYU+0.182
Neg logit contributions
 corrid-0.267
acco-0.236
-0.235
2020-0.234
GGGGGGGG-0.230
Token standing
Token ID5055
Feature activation-2.07e-01

Pos logit contributions
 Brune+0.172
 Haas+0.166
worthiness+0.164
 Dustin+0.160
 NYU+0.157
Neg logit contributions
 corrid-0.251
acco-0.223
-0.222
2020-0.221
GGGGGGGG-0.217
Token once
Token ID1752
Feature activation+7.30e-01

Pos logit contributions
 Brune+0.329
 Haas+0.316
worthiness+0.312
 Dustin+0.308
 NYU+0.300
Neg logit contributions
 corrid-0.435
acco-0.385
-0.383
2020-0.382
GGGGGGGG-0.377
Token said
Token ID531
Feature activation-1.10e-01

Pos logit contributions
 corrid+1.281
acco+1.138
+1.129
2020+1.128
 retri+1.113
Neg logit contributions
 Brune-0.899
 Haas-0.865
worthiness-0.861
 Dustin-0.835
 NYU-0.820
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
 Brune+0.130
 Haas+0.124
worthiness+0.124
 Dustin+0.120
 NYU+0.118
Neg logit contributions
 corrid-0.201
acco-0.179
2020-0.178
-0.177
 retri-0.175
Token The
Token ID383
Feature activation-4.78e-01

Pos logit contributions
 Brune+0.172
 Haas+0.164
worthiness+0.161
 Dustin+0.159
 NYU+0.155
Neg logit contributions
 corrid-0.296
acco-0.261
 retri-0.259
-0.258
2020-0.255
Token American
Token ID1605
Feature activation-6.81e-01

Pos logit contributions
 Brune+0.658
 Haas+0.633
worthiness+0.618
 Dustin+0.617
 NYU+0.605
Neg logit contributions
 corrid-0.774
acco-0.685
-0.685
2020-0.681
GGGGGGGG-0.672
Token Civil
Token ID7511
Feature activation-2.54e+00

Pos logit contributions
 Brune+0.874
 Haas+0.842
 Dustin+0.834
worthiness+0.832
 NYU+0.802
Neg logit contributions
 corrid-1.152
acco-1.022
2020-1.017
-1.016
GGGGGGGG-1.004
Token War
Token ID1810
Feature activation-9.09e-01

Pos logit contributions
 Brune+2.446
 Haas+2.345
 Dustin+2.309
worthiness+2.288
 NYU+2.234
Neg logit contributions
 corrid-5.375
GGGGGGGG-4.701
acco-4.493
-4.486
龍喚士-4.484
Token was
Token ID373
Feature activation-4.61e-01

Pos logit contributions
 Brune+1.139
 Haas+1.094
worthiness+1.075
 Dustin+1.069
 NYU+1.039
Neg logit contributions
 corrid-1.586
-1.403
acco-1.401
2020-1.392
GGGGGGGG-1.378
Token a
Token ID257
Feature activation+2.13e-02

Pos logit contributions
 Brune+0.584
 Haas+0.557
worthiness+0.543
 Dustin+0.542
 NYU+0.533
Neg logit contributions
 corrid-0.809
-0.715
2020-0.712
acco-0.712
GGGGGGGG-0.697
Token dark
Token ID3223
Feature activation+1.29e+00

Pos logit contributions
 corrid+0.034
acco+0.030
+0.030
2020+0.030
GGGGGGGG+0.029
Neg logit contributions
 Brune-0.030
 Haas-0.029
worthiness-0.028
 Dustin-0.028
 NYU-0.027
Token chapter
Token ID6843
Feature activation+7.38e-01

Pos logit contributions
 corrid+2.180
acco+1.928
+1.914
2020+1.911
 retri+1.889
Neg logit contributions
 Brune-1.660
 Haas-1.599
worthiness-1.592
 Dustin-1.547
 NYU-1.519
Token "
Token ID366
Feature activation-6.04e-01

Pos logit contributions
 Brune+0.182
 Haas+0.175
worthiness+0.173
 Dustin+0.170
 NYU+0.166
Neg logit contributions
 corrid-0.251
acco-0.222
2020-0.221
-0.220
 retri-0.216
Tokenreally
Token ID27485
Feature activation+5.25e-01

Pos logit contributions
 Brune+0.763
worthiness+0.746
 Haas+0.733
 Dustin+0.716
 NYU+0.699
Neg logit contributions
 corrid-1.051
acco-0.914
-0.904
2020-0.898
GGGGGGGG-0.896
Token angry
Token ID7954
Feature activation-1.04e+00

Pos logit contributions
 corrid+0.899
acco+0.797
+0.792
2020+0.791
 retri+0.777
Neg logit contributions
 Brune-0.670
 Haas-0.645
worthiness-0.641
 Dustin-0.625
 NYU-0.614
Token"
Token ID1
Feature activation+6.14e-01

Pos logit contributions
 Brune+1.352
worthiness+1.306
 Haas+1.305
 Dustin+1.287
 NYU+1.252
Neg logit contributions
 corrid-1.762
acco-1.554
-1.534
2020-1.532
 retri-1.498
Token about
Token ID546
Feature activation+8.64e-02

Pos logit contributions
 corrid+1.038
acco+0.914
2020+0.905
+0.905
 retri+0.890
Neg logit contributions
 Brune-0.803
 Haas-0.776
worthiness-0.771
 Dustin-0.756
 NYU-0.740
Token Civil
Token ID7511
Feature activation-2.54e+00

Pos logit contributions
 corrid+0.147
acco+0.130
2020+0.129
+0.128
 retri+0.127
Neg logit contributions
 Brune-0.112
 Haas-0.108
worthiness-0.107
 Dustin-0.105
 NYU-0.103
Token War
Token ID1810
Feature activation-4.76e-01

Pos logit contributions
 Brune+1.888
 Haas+1.773
worthiness+1.732
 Dustin+1.726
 NYU+1.688
Neg logit contributions
 corrid-5.871
GGGGGGGG-5.184
acco-5.114
 retri-5.084
-5.081
Token:
Token ID25
Feature activation-3.03e-01

Pos logit contributions
 Brune+0.554
 Haas+0.530
worthiness+0.528
 Dustin+0.523
 NYU+0.505
Neg logit contributions
 corrid-0.870
acco-0.773
2020-0.768
-0.766
GGGGGGGG-0.756
Token https
Token ID3740
Feature activation+3.17e-01

Pos logit contributions
 Brune+0.340
 Haas+0.327
worthiness+0.324
 Dustin+0.315
 NYU+0.308
Neg logit contributions
 corrid-0.564
acco-0.504
-0.500
2020-0.500
 retri-0.495
Token://
Token ID1378
Feature activation+1.06e+00

Pos logit contributions
 corrid+0.426
acco+0.361
+0.356
2020+0.355
 retri+0.350
Neg logit contributions
 Brune-0.525
 Haas-0.510
worthiness-0.509
 Dustin-0.498
 NYU-0.492
Tokent
Token ID83
Feature activation-3.92e-01

Pos logit contributions
 corrid+2.166
acco+1.983
2020+1.976
+1.969
 retri+1.940
Neg logit contributions
 Brune-0.968
 Haas-0.920
worthiness-0.904
 Dustin-0.877
 NYU-0.851
Token economic
Token ID3034
Feature activation-3.66e-01

Pos logit contributions
 Brune+0.113
 Haas+0.108
worthiness+0.107
 Dustin+0.105
 NYU+0.102
Neg logit contributions
 corrid-0.177
acco-0.158
-0.157
2020-0.157
 retri-0.154
Token turmoil
Token ID26962
Feature activation-9.49e-01

Pos logit contributions
 Brune+0.456
 Haas+0.438
worthiness+0.435
 Dustin+0.426
 NYU+0.415
Neg logit contributions
 corrid-0.640
acco-0.571
-0.567
2020-0.566
GGGGGGGG-0.557
Token of
Token ID286
Feature activation-8.64e-02

Pos logit contributions
 Brune+1.207
 Haas+1.156
worthiness+1.148
 Dustin+1.125
 NYU+1.099
Neg logit contributions
 corrid-1.649
acco-1.455
2020-1.453
-1.439
GGGGGGGG-1.435
Token the
Token ID262
Feature activation-3.90e-02

Pos logit contributions
 Brune+0.108
 Haas+0.103
worthiness+0.102
 Dustin+0.101
 NYU+0.098
Neg logit contributions
 corrid-0.151
acco-0.134
2020-0.133
-0.133
 retri-0.132
Token American
Token ID1605
Feature activation-3.62e-01

Pos logit contributions
 Brune+0.048
 Haas+0.046
worthiness+0.045
 Dustin+0.044
 NYU+0.043
Neg logit contributions
 corrid-0.069
acco-0.062
-0.061
2020-0.061
 retri-0.061
Token Civil
Token ID7511
Feature activation-2.49e+00

Pos logit contributions
 Brune+0.458
 Haas+0.440
 Dustin+0.430
worthiness+0.429
 NYU+0.415
Neg logit contributions
 corrid-0.627
acco-0.553
2020-0.551
-0.549
GGGGGGGG-0.548
Token War
Token ID1810
Feature activation-5.74e-01

Pos logit contributions
 Brune+1.844
 Haas+1.744
 Dustin+1.705
worthiness+1.701
 NYU+1.619
Neg logit contributions
 corrid-5.776
GGGGGGGG-5.168
龍喚士-5.000
acco-4.989
 retri-4.983
Token.
Token ID13
Feature activation-9.23e-02

Pos logit contributions
 Brune+0.616
 Haas+0.591
worthiness+0.585
 Dustin+0.568
 NYU+0.552
Neg logit contributions
 corrid-1.106
acco-0.984
-0.980
2020-0.980
GGGGGGGG-0.968
Token This
Token ID770
Feature activation-2.63e-01

Pos logit contributions
 Brune+0.112
 Haas+0.108
worthiness+0.107
 Dustin+0.105
 NYU+0.103
Neg logit contributions
 corrid-0.167
acco-0.147
-0.145
 retri-0.145
2020-0.144
Token happened
Token ID3022
Feature activation+5.97e-01

Pos logit contributions
 Brune+0.340
 Haas+0.327
worthiness+0.325
 Dustin+0.318
 NYU+0.312
Neg logit contributions
 corrid-0.447
acco-0.397
2020-0.395
-0.395
GGGGGGGG-0.388
Token because
Token ID780
Feature activation+7.29e-02

Pos logit contributions
 corrid+0.947
acco+0.829
+0.823
2020+0.822
 retri+0.807
Neg logit contributions
 Brune-0.841
 Haas-0.812
worthiness-0.808
 Dustin-0.789
 NYU-0.776
Token,
Token ID11
Feature activation-4.97e-02

Pos logit contributions
 Brune+0.844
 Haas+0.817
worthiness+0.811
 Dustin+0.791
 NYU+0.771
Neg logit contributions
 corrid-1.248
2020-1.097
-1.095
acco-1.091
 retri-1.071
Token and
Token ID290
Feature activation+1.60e-01

Pos logit contributions
 Brune+0.061
 Haas+0.059
worthiness+0.058
 Dustin+0.057
 NYU+0.056
Neg logit contributions
 corrid-0.088
-0.078
acco-0.078
2020-0.078
GGGGGGGG-0.076
Token Minnesota
Token ID8919
Feature activation+1.15e+00

Pos logit contributions
 corrid+0.282
acco+0.248
+0.248
2020+0.247
GGGGGGGG+0.242
Neg logit contributions
 Brune-0.200
 Haas-0.193
worthiness-0.191
 Dustin-0.188
 NYU-0.183
Token's
Token ID338
Feature activation-3.73e-01

Pos logit contributions
 corrid+2.031
acco+1.793
+1.790
2020+1.788
 retri+1.754
Neg logit contributions
 Brune-1.405
 Haas-1.352
worthiness-1.340
 Dustin-1.313
 NYU-1.282
Token Xavier
Token ID30825
Feature activation+6.65e-01

Pos logit contributions
 Brune+0.480
 Haas+0.467
worthiness+0.459
 Dustin+0.459
 NYU+0.442
Neg logit contributions
 corrid-0.642
-0.566
acco-0.562
2020-0.557
龍喚士-0.546
Token Rhodes
Token ID25656
Feature activation-2.49e+00

Pos logit contributions
 corrid+1.586
acco+1.473
+1.463
2020+1.462
 retri+1.446
Neg logit contributions
 Brune-0.373
worthiness-0.346
 Haas-0.337
 Dustin-0.319
 NYU-0.303
Token are
Token ID389
Feature activation+9.55e-02

Pos logit contributions
 Brune+2.935
 Haas+2.861
worthiness+2.849
 Dustin+2.776
lis+2.656
Neg logit contributions
 corrid-4.546
-3.924
2020-3.894
GGGGGGGG-3.850
-3.837
Token playing
Token ID2712
Feature activation+4.61e-02

Pos logit contributions
 corrid+0.162
+0.143
2020+0.142
acco+0.142
GGGGGGGG+0.139
Neg logit contributions
 Brune-0.125
 Haas-0.121
worthiness-0.120
 Dustin-0.118
 NYU-0.116
Token for
Token ID329
Feature activation+9.73e-02

Pos logit contributions
 corrid+0.077
acco+0.069
+0.069
2020+0.068
GGGGGGGG+0.067
Neg logit contributions
 Brune-0.061
 Haas-0.059
worthiness-0.058
 Dustin-0.057
 NYU-0.056
Token bragging
Token ID43018
Feature activation-2.74e-01

Pos logit contributions
 corrid+0.167
+0.147
acco+0.147
2020+0.146
GGGGGGGG+0.144
Neg logit contributions
 Brune-0.125
 Haas-0.122
worthiness-0.120
 Dustin-0.119
 NYU-0.116
Token rights
Token ID2489
Feature activation+2.33e-01

Pos logit contributions
 Brune+0.456
worthiness+0.447
 Haas+0.445
 Dustin+0.435
 NYU+0.430
Neg logit contributions
 corrid-0.365
acco-0.310
-0.307
2020-0.302
 retri-0.296
Token,
Token ID11
Feature activation-2.20e-02

Pos logit contributions
 Brune+0.059
 Haas+0.057
worthiness+0.056
 Dustin+0.055
 NYU+0.054
Neg logit contributions
 corrid-0.085
acco-0.075
-0.074
2020-0.074
 retri-0.073
Token a
Token ID257
Feature activation+2.20e-01

Pos logit contributions
 Brune+0.026
 Haas+0.025
worthiness+0.025
 Dustin+0.024
 NYU+0.024
Neg logit contributions
 corrid-0.040
acco-0.035
-0.035
2020-0.035
 retri-0.034
Token professor
Token ID6240
Feature activation-7.32e-01

Pos logit contributions
 corrid+0.380
acco+0.337
+0.336
2020+0.334
 retri+0.329
Neg logit contributions
 Brune-0.280
 Haas-0.269
worthiness-0.265
 Dustin-0.260
 NYU-0.257
Token at
Token ID379
Feature activation+8.05e-01

Pos logit contributions
 Brune+1.010
 Haas+0.976
worthiness+0.966
 Dustin+0.946
 NYU+0.932
Neg logit contributions
 corrid-1.185
acco-1.039
-1.031
2020-1.029
 retri-1.012
Token the
Token ID262
Feature activation+6.91e-02

Pos logit contributions
 corrid+1.446
acco+1.296
2020+1.284
+1.283
 retri+1.267
Neg logit contributions
 Brune-0.940
worthiness-0.910
 Haas-0.901
 Dustin-0.874
 NYU-0.847
Token Civil
Token ID7511
Feature activation-2.47e+00

Pos logit contributions
 corrid+0.123
acco+0.110
+0.109
2020+0.109
 retri+0.107
Neg logit contributions
 Brune-0.083
 Haas-0.080
worthiness-0.080
 Dustin-0.077
 NYU-0.076
Token Aviation
Token ID25186
Feature activation-1.70e+00

Pos logit contributions
 Brune+2.290
 Haas+2.218
worthiness+2.186
 NYU+2.086
 Dustin+2.070
Neg logit contributions
 corrid-5.220
acco-4.573
 retri-4.565
-4.548
GGGGGGGG-4.519
Token University
Token ID2059
Feature activation+1.24e-02

Pos logit contributions
 Brune+2.291
 Haas+2.235
worthiness+2.194
 NYU+2.159
 Dustin+2.145
Neg logit contributions
 corrid-2.845
acco-2.454
-2.435
2020-2.413
GGGGGGGG-2.403
Token of
Token ID286
Feature activation-6.18e-02

Pos logit contributions
 corrid+0.021
acco+0.018
2020+0.018
+0.018
 retri+0.018
Neg logit contributions
 Brune-0.016
worthiness-0.016
 Haas-0.016
 Dustin-0.015
 NYU-0.015
Token China
Token ID2807
Feature activation-8.69e-01

Pos logit contributions
 Brune+0.056
 Haas+0.053
worthiness+0.053
 Dustin+0.051
 NYU+0.049
Neg logit contributions
 corrid-0.129
acco-0.117
-0.116
2020-0.116
 retri-0.114
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
 Brune+1.002
 Haas+0.963
worthiness+0.941
 Dustin+0.921
 NYU+0.911
Neg logit contributions
 corrid-1.613
acco-1.436
-1.427
2020-1.417
 retri-1.403
Token under
Token ID739
Feature activation-3.85e-01

Pos logit contributions
 corrid+2.404
acco+2.129
+2.113
2020+2.113
 retri+2.090
Neg logit contributions
 Brune-1.802
 Haas-1.736
worthiness-1.736
 Dustin-1.682
 NYU-1.656
Token Title
Token ID11851
Feature activation+3.74e-01

Pos logit contributions
 Brune+0.505
 Haas+0.482
worthiness+0.472
 Dustin+0.466
 NYU+0.460
Neg logit contributions
 corrid-0.659
acco-0.581
2020-0.577
-0.575
GGGGGGGG-0.565
Token VI
Token ID13889
Feature activation+2.51e-01

Pos logit contributions
 corrid+0.641
acco+0.563
+0.561
2020+0.557
 retri+0.553
Neg logit contributions
 Brune-0.484
 Haas-0.464
worthiness-0.461
 Dustin-0.449
 NYU-0.441
Token of
Token ID286
Feature activation+7.10e-02

Pos logit contributions
 corrid+0.426
acco+0.376
2020+0.373
+0.373
 retri+0.368
Neg logit contributions
 Brune-0.327
 Haas-0.314
worthiness-0.313
 Dustin-0.304
 NYU-0.299
Token the
Token ID262
Feature activation+6.45e-02

Pos logit contributions
 corrid+0.125
acco+0.110
+0.110
2020+0.110
 retri+0.108
Neg logit contributions
 Brune-0.089
 Haas-0.085
worthiness-0.084
 Dustin-0.082
 NYU-0.081
Token Civil
Token ID7511
Feature activation-2.47e+00

Pos logit contributions
 corrid+0.126
acco+0.112
+0.111
2020+0.111
 retri+0.110
Neg logit contributions
 Brune-0.069
 Haas-0.065
worthiness-0.064
 Dustin-0.063
 NYU-0.062
Token Rights
Token ID6923
Feature activation+3.58e-01

Pos logit contributions
 Brune+3.416
 Haas+3.319
worthiness+3.231
 Dustin+3.215
 NYU+3.197
Neg logit contributions
 corrid-4.331
acco-3.533
GGGGGGGG-3.505
 retri-3.502
-3.494
Token Act
Token ID2191
Feature activation-3.04e-01

Pos logit contributions
 corrid+0.605
acco+0.533
+0.529
2020+0.529
 retri+0.521
Neg logit contributions
 Brune-0.466
 Haas-0.449
worthiness-0.446
 Dustin-0.435
 NYU-0.427
Token of
Token ID286
Feature activation+1.92e-01

Pos logit contributions
 Brune+0.387
 Haas+0.371
worthiness+0.368
 Dustin+0.359
 NYU+0.352
Neg logit contributions
 corrid-0.524
acco-0.463
2020-0.459
-0.459
 retri-0.453
Token 1964
Token ID17575
Feature activation+7.66e-01

Pos logit contributions
 corrid+0.318
acco+0.284
2020+0.283
+0.281
 retri+0.278
Neg logit contributions
 Brune-0.251
 Haas-0.244
worthiness-0.242
 Dustin-0.235
 NYU-0.230
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
 corrid+1.342
acco+1.193
+1.185
2020+1.184
 retri+1.168
Neg logit contributions
 Brune-0.942
 Haas-0.907
worthiness-0.902
 Dustin-0.877
 NYU-0.861
Token Resource
Token ID20857
Feature activation-8.86e-01

Pos logit contributions
 Brune+0.583
 Haas+0.563
worthiness+0.560
 Dustin+0.533
 NYU+0.526
Neg logit contributions
 corrid-0.983
acco-0.868
-0.862
2020-0.850
GGGGGGGG-0.846
Token Management
Token ID8549
Feature activation-1.13e+00

Pos logit contributions
 Brune+1.036
 Haas+1.000
worthiness+0.994
 Dustin+0.962
 NYU+0.949
Neg logit contributions
 corrid-1.652
acco-1.452
-1.439
GGGGGGGG-1.424
2020-1.413
Token)
Token ID8
Feature activation+1.88e-01

Pos logit contributions
 Brune+1.343
worthiness+1.293
 Haas+1.288
 Dustin+1.242
 NYU+1.225
Neg logit contributions
 corrid-2.070
acco-1.827
-1.815
GGGGGGGG-1.790
2020-1.785
Token Cur
Token ID4424
Feature activation-1.53e+00

Pos logit contributions
 corrid+0.317
acco+0.280
+0.278
2020+0.276
 retri+0.273
Neg logit contributions
 Brune-0.246
 Haas-0.237
worthiness-0.235
 Dustin-0.229
 NYU-0.226
Tokenric
Token ID1173
Feature activation-8.37e-02

Pos logit contributions
 Brune+1.216
 Haas+1.148
worthiness+1.127
 Dustin+1.084
lis+1.069
Neg logit contributions
 corrid-3.402
-3.048
acco-3.031
龍喚士-3.001
2020-3.000
Tokenulum
Token ID14452
Feature activation-2.47e+00

Pos logit contributions
 Brune+0.072
 Haas+0.068
worthiness+0.067
 Dustin+0.064
 NYU+0.063
Neg logit contributions
 corrid-0.179
acco-0.162
-0.161
2020-0.161
 retri-0.159
Token guidelines
Token ID9949
Feature activation-1.40e-01

Pos logit contributions
 Brune+2.957
 Haas+2.855
worthiness+2.787
 Dustin+2.771
 NYU+2.736
Neg logit contributions
 corrid-4.415
acco-3.839
-3.809
GGGGGGGG-3.767
龍喚士-3.751
Token.
Token ID13
Feature activation+6.07e-02

Pos logit contributions
 Brune+0.160
 Haas+0.154
worthiness+0.153
 Dustin+0.149
 NYU+0.146
Neg logit contributions
 corrid-0.258
acco-0.229
-0.228
2020-0.227
 retri-0.224
Token
Token ID198
Feature activation+2.69e-03

Pos logit contributions
 corrid+0.108
acco+0.095
+0.093
 retri+0.093
2020+0.092
Neg logit contributions
 Brune-0.077
 Haas-0.074
worthiness-0.073
 Dustin-0.072
 NYU-0.070
Token
Token ID198
Feature activation-4.06e-02

Pos logit contributions
 corrid+0.005
acco+0.004
+0.004
2020+0.004
 retri+0.004
Neg logit contributions
 Brune-0.003
 Haas-0.003
worthiness-0.003
 Dustin-0.003
 NYU-0.003
TokenQ
Token ID48
Feature activation-6.92e-01

Pos logit contributions
 Brune+0.062
 Haas+0.060
worthiness+0.060
 Dustin+0.059
 NYU+0.058
Neg logit contributions
 corrid-0.060
acco-0.051
-0.050
 retri-0.050
2020-0.050
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
 Brune+2.217
 Haas+2.136
worthiness+2.133
 Dustin+2.057
 NYU+1.959
Neg logit contributions
 corrid-4.088
acco-3.654
-3.636
2020-3.605
GGGGGGGG-3.605
Token One
Token ID1881
Feature activation-5.62e-03

Pos logit contributions
 Brune+0.398
 Haas+0.382
worthiness+0.376
 Dustin+0.371
 NYU+0.363
Neg logit contributions
 corrid-0.571
acco-0.499
-0.490
 retri-0.488
2020-0.487
Token of
Token ID286
Feature activation-1.37e-01

Pos logit contributions
 Brune+0.007
 Haas+0.007
worthiness+0.007
 Dustin+0.007
 NYU+0.007
Neg logit contributions
 corrid-0.010
acco-0.009
-0.008
2020-0.008
GGGGGGGG-0.008
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
 Brune+0.182
 Haas+0.176
worthiness+0.175
 Dustin+0.171
 NYU+0.168
Neg logit contributions
 corrid-0.232
acco-0.203
2020-0.202
-0.201
GGGGGGGG-0.197
Token three
Token ID1115
Feature activation-2.22e-01

Pos logit contributions
 Brune+0.169
worthiness+0.162
 Haas+0.162
 Dustin+0.158
 NYU+0.155
Neg logit contributions
 corrid-0.203
acco-0.180
-0.178
2020-0.178
GGGGGGGG-0.175
Token flight
Token ID5474
Feature activation-2.47e+00

Pos logit contributions
 Brune+0.299
worthiness+0.287
 Haas+0.286
 Dustin+0.278
 NYU+0.274
Neg logit contributions
 corrid-0.372
acco-0.329
-0.327
2020-0.326
GGGGGGGG-0.321
Token control
Token ID1630
Feature activation-7.31e-02

Pos logit contributions
worthiness+3.461
 Brune+3.388
 Dustin+3.221
 Haas+3.210
 NYU+3.148
Neg logit contributions
 corrid-3.906
acco-3.421
2020-3.372
-3.360
GGGGGGGG-3.348
Token primary
Token ID4165
Feature activation-1.66e-01

Pos logit contributions
 Brune+0.107
worthiness+0.103
 Haas+0.103
 Dustin+0.100
 NYU+0.098
Neg logit contributions
 corrid-0.113
acco-0.099
-0.098
2020-0.098
GGGGGGGG-0.096
Token computers
Token ID9061
Feature activation+2.56e-01

Pos logit contributions
 Brune+0.238
worthiness+0.230
 Haas+0.229
 Dustin+0.223
 NYU+0.220
Neg logit contributions
 corrid-0.261
acco-0.229
2020-0.226
-0.225
GGGGGGGG-0.222
Token then
Token ID788
Feature activation-2.89e-01

Pos logit contributions
 corrid+0.451
+0.399
acco+0.398
2020+0.395
GGGGGGGG+0.390
Neg logit contributions
 Brune-0.321
 Haas-0.307
worthiness-0.306
 Dustin-0.297
 NYU-0.292
Token reacted
Token ID22798
Feature activation-3.30e-01

Pos logit contributions
 Brune+0.378
 Haas+0.361
worthiness+0.360
 Dustin+0.350
 NYU+0.343
Neg logit contributions
 corrid-0.497
-0.440
acco-0.434
2020-0.432
GGGGGGGG-0.430
Token senior
Token ID4664
Feature activation-1.25e-01

Pos logit contributions
 corrid+0.507
acco+0.449
+0.447
2020+0.445
GGGGGGGG+0.437
Neg logit contributions
 Brune-0.367
 Haas-0.354
worthiness-0.348
 Dustin-0.341
 NYU-0.337
Token associate
Token ID11602
Feature activation-7.28e-01

Pos logit contributions
 Brune+0.159
 Haas+0.154
worthiness+0.151
 Dustin+0.148
 NYU+0.148
Neg logit contributions
 corrid-0.217
acco-0.191
-0.190
2020-0.190
GGGGGGGG-0.186
Token at
Token ID379
Feature activation+8.92e-01

Pos logit contributions
 Brune+0.838
 Haas+0.808
worthiness+0.790
 Dustin+0.774
 NYU+0.773
Neg logit contributions
 corrid-1.353
acco-1.201
-1.196
2020-1.190
GGGGGGGG-1.171
Token Carnegie
Token ID33976
Feature activation-1.05e+00

Pos logit contributions
 corrid+1.596
acco+1.425
2020+1.413
+1.413
 retri+1.393
Neg logit contributions
 Brune-1.060
worthiness-1.018
 Haas-1.014
 Dustin-0.984
 NYU-0.958
Token End
Token ID5268
Feature activation+2.73e-01

Pos logit contributions
 Brune+0.452
 Haas+0.414
worthiness+0.385
 Dustin+0.359
 NYU+0.344
Neg logit contributions
 corrid-2.724
acco-2.498
-2.483
2020-2.467
GGGGGGGG-2.462
Tokenowment
Token ID36569
Feature activation-2.45e+00

Pos logit contributions
 corrid+0.445
acco+0.385
+0.384
2020+0.382
 retri+0.378
Neg logit contributions
 Brune-0.372
 Haas-0.364
worthiness-0.361
 Dustin-0.354
 NYU-0.350
Token of
Token ID286
Feature activation+1.08e-02

Pos logit contributions
 Brune+3.031
 Haas+2.909
worthiness+2.831
 Dustin+2.812
 NYU+2.797
Neg logit contributions
 corrid-4.330
acco-3.775
GGGGGGGG-3.763
-3.754
龍喚士-3.730
Token International
Token ID4037
Feature activation-8.10e-01

Pos logit contributions
 corrid+0.022
acco+0.020
+0.019
2020+0.019
 retri+0.019
Neg logit contributions
 Brune-0.011
 Haas-0.010
worthiness-0.010
 Dustin-0.010
 NYU-0.009
Token Peace
Token ID12689
Feature activation-7.58e-01

Pos logit contributions
 Brune+0.999
 Haas+0.961
worthiness+0.955
 Dustin+0.929
 NYU+0.912
Neg logit contributions
 corrid-1.417
acco-1.261
-1.252
2020-1.251
 retri-1.232
Token,
Token ID11
Feature activation-4.88e-02

Pos logit contributions
 Brune+0.935
 Haas+0.897
worthiness+0.888
 Dustin+0.865
 NYU+0.857
Neg logit contributions
 corrid-1.339
acco-1.187
-1.174
2020-1.172
 retri-1.159
Token also
Token ID635
Feature activation-4.73e-01

Pos logit contributions
 Brune+0.059
 Haas+0.057
worthiness+0.056
 Dustin+0.055
 NYU+0.054
Neg logit contributions
 corrid-0.087
acco-0.077
2020-0.077
-0.077
 retri-0.076
TokenF
Token ID37
Feature activation-6.75e-01

Pos logit contributions
 Brune+0.067
worthiness+0.065
 Haas+0.065
 Dustin+0.064
 NYU+0.063
Neg logit contributions
 corrid-0.070
acco-0.060
-0.059
2020-0.059
 retri-0.059
Tokenictional
Token ID47273
Feature activation+1.36e+00

Pos logit contributions
 Brune+0.871
worthiness+0.836
 Haas+0.830
 Dustin+0.811
 NYU+0.794
Neg logit contributions
 corrid-1.140
-1.017
acco-0.991
2020-0.989
龍喚士-0.986
Token
Token ID198
Feature activation+1.23e-01

Pos logit contributions
 corrid+2.402
acco+2.133
+2.122
2020+2.116
 retri+2.100
Neg logit contributions
 Brune-1.665
 Haas-1.602
worthiness-1.590
 Dustin-1.538
 NYU-1.516
Token
Token ID198
Feature activation+8.99e-02

Pos logit contributions
 corrid+0.223
acco+0.199
+0.197
2020+0.197
 retri+0.194
Neg logit contributions
 Brune-0.145
 Haas-0.139
worthiness-0.139
 Dustin-0.134
 NYU-0.132
TokenIn
Token ID818
Feature activation+9.29e-02

Pos logit contributions
 corrid+0.136
acco+0.117
+0.114
 retri+0.114
2020+0.114
Neg logit contributions
 Brune-0.134
worthiness-0.130
 Haas-0.130
 Dustin-0.127
 NYU-0.124
Token Philip
Token ID14576
Feature activation-2.43e+00

Pos logit contributions
 corrid+0.163
acco+0.144
+0.143
2020+0.143
 retri+0.141
Neg logit contributions
 Brune-0.116
 Haas-0.112
worthiness-0.110
 Dustin-0.109
 NYU-0.106
Token Pull
Token ID21429
Feature activation+3.29e-01

Pos logit contributions
 Brune+3.130
 Haas+3.023
 Dustin+2.919
worthiness+2.856
 NYU+2.824
Neg logit contributions
 corrid-4.258
-3.710
2020-3.681
 retri-3.636
GGGGGGGG-3.628
Tokenman
Token ID805
Feature activation+7.53e-03

Pos logit contributions
 corrid+0.419
2020+0.349
acco+0.348
+0.345
GGGGGGGG+0.339
Neg logit contributions
 Brune-0.570
worthiness-0.553
 Haas-0.552
 Dustin-0.544
 NYU-0.533
Token's
Token ID338
Feature activation-6.28e-01

Pos logit contributions
 corrid+0.014
acco+0.012
+0.012
2020+0.012
 retri+0.012
Neg logit contributions
 Brune-0.009
worthiness-0.009
 Haas-0.009
 Dustin-0.008
 NYU-0.008
Token 1995
Token ID8735
Feature activation+1.25e+00

Pos logit contributions
 Brune+0.821
 Haas+0.792
 Dustin+0.781
worthiness+0.779
 NYU+0.759
Neg logit contributions
 corrid-1.054
acco-0.934
-0.932
2020-0.918
龍喚士-0.912
Token
Token ID1906
Feature activation+1.11e+00

Pos logit contributions
 corrid+1.952
acco+1.709
+1.696
2020+1.693
 retri+1.663
Neg logit contributions
 Brune-1.794
 Haas-1.734
worthiness-1.726
 Dustin-1.687
 NYU-1.660
Token to
Token ID284
Feature activation-8.64e-03

Pos logit contributions
 Brune+0.379
 Haas+0.367
worthiness+0.364
 Dustin+0.356
 NYU+0.350
Neg logit contributions
 corrid-0.425
acco-0.372
-0.369
2020-0.367
 retri-0.362
Token invoke
Token ID26342
Feature activation-1.04e+00

Pos logit contributions
 Brune+0.012
 Haas+0.011
worthiness+0.011
 Dustin+0.011
 NYU+0.011
Neg logit contributions
 corrid-0.014
acco-0.013
-0.013
2020-0.013
GGGGGGGG-0.012
Token a
Token ID257
Feature activation+4.56e-02

Pos logit contributions
 Brune+1.327
 Haas+1.277
worthiness+1.253
 Dustin+1.232
 NYU+1.213
Neg logit contributions
 corrid-1.800
acco-1.605
-1.591
2020-1.587
GGGGGGGG-1.556
Token function
Token ID2163
Feature activation-2.79e-01

Pos logit contributions
 corrid+0.075
acco+0.066
+0.066
2020+0.066
 retri+0.064
Neg logit contributions
 Brune-0.062
 Haas-0.059
worthiness-0.059
 Dustin-0.057
 NYU-0.056
Token called
Token ID1444
Feature activation-9.92e-02

Pos logit contributions
 Brune+0.372
 Haas+0.358
worthiness+0.352
 Dustin+0.346
 NYU+0.341
Neg logit contributions
 corrid-0.466
acco-0.412
-0.408
2020-0.407
GGGGGGGG-0.399
Token vert
Token ID9421
Feature activation-2.43e+00

Pos logit contributions
 Brune+0.127
 Haas+0.122
worthiness+0.122
 Dustin+0.118
 NYU+0.116
Neg logit contributions
 corrid-0.170
acco-0.150
-0.149
2020-0.149
 retri-0.147
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
 Brune+3.090
 Haas+2.979
worthiness+2.938
 Dustin+2.880
 NYU+2.808
Neg logit contributions
 corrid-4.150
acco-3.666
-3.604
2020-3.588
 retri-3.561
Token which
Token ID543
Feature activation+1.60e-01

Pos logit contributions
 Brune+0.226
 Haas+0.217
worthiness+0.214
 Dustin+0.210
 NYU+0.204
Neg logit contributions
 corrid-0.329
acco-0.292
-0.291
2020-0.289
GGGGGGGG-0.286
Token sole
Token ID6195
Feature activation-1.05e+00

Pos logit contributions
 corrid+0.288
acco+0.257
+0.255
2020+0.255
 retri+0.251
Neg logit contributions
 Brune-0.191
 Haas-0.183
worthiness-0.182
 Dustin-0.177
 NYU-0.174
Token responsibility
Token ID5798
Feature activation-4.43e-01

Pos logit contributions
 Brune+1.259
 Haas+1.214
worthiness+1.208
 Dustin+1.165
 NYU+1.144
Neg logit contributions
 corrid-1.886
acco-1.684
-1.676
2020-1.663
GGGGGGGG-1.639
Token is
Token ID318
Feature activation+4.56e-03

Pos logit contributions
 Brune+0.532
 Haas+0.510
worthiness+0.510
 Dustin+0.493
 NYU+0.485
Neg logit contributions
 corrid-0.796
acco-0.708
-0.705
2020-0.700
GGGGGGGG-0.692
Token slavery
Token ID13503
Feature activation+3.92e-01

Pos logit contributions
 corrid+0.005
acco+0.004
2020+0.004
+0.004
GGGGGGGG+0.004
Neg logit contributions
 Brune-0.005
 Haas-0.005
worthiness-0.005
 Dustin-0.005
 NYU-0.005
Token did
Token ID750
Feature activation-2.25e-01

Pos logit contributions
 corrid+0.642
acco+0.565
+0.565
2020+0.562
GGGGGGGG+0.552
Neg logit contributions
 Brune-0.534
 Haas-0.515
worthiness-0.513
 Dustin-0.499
 NYU-0.489
Token not
Token ID407
Feature activation+6.27e-02

Pos logit contributions
 Brune+0.279
 Haas+0.268
worthiness+0.266
 Dustin+0.259
 NYU+0.254
Neg logit contributions
 corrid-0.395
acco-0.351
2020-0.349
-0.349
 retri-0.342
Token cause
Token ID2728
Feature activation-9.60e-01

Pos logit contributions
 corrid+0.108
+0.095
acco+0.095
2020+0.094
GGGGGGGG+0.093
Neg logit contributions
 Brune-0.081
worthiness-0.078
 Haas-0.078
 Dustin-0.076
 NYU-0.074
Token the
Token ID262
Feature activation+7.33e-02

Pos logit contributions
 Brune+1.353
 Haas+1.300
worthiness+1.283
 Dustin+1.270
 NYU+1.241
Neg logit contributions
 corrid-1.537
2020-1.346
acco-1.343
-1.341
GGGGGGGG-1.322
Token Civil
Token ID7511
Feature activation-2.42e+00

Pos logit contributions
 corrid+0.124
acco+0.109
2020+0.109
+0.109
 retri+0.107
Neg logit contributions
 Brune-0.096
 Haas-0.092
worthiness-0.091
 Dustin-0.089
 NYU-0.088
Token War
Token ID1810
Feature activation-5.93e-01

Pos logit contributions
 Brune+1.853
 Haas+1.745
 Dustin+1.701
worthiness+1.683
 NYU+1.622
Neg logit contributions
 corrid-5.653
GGGGGGGG-4.955
-4.842
 retri-4.841
acco-4.840
Token and
Token ID290
Feature activation+5.74e-04

Pos logit contributions
 Brune+0.674
 Haas+0.644
worthiness+0.643
 Dustin+0.626
 NYU+0.602
Neg logit contributions
 corrid-1.100
acco-0.979
-0.974
2020-0.973
GGGGGGGG-0.964
Token debunked
Token ID46682
Feature activation-1.31e-02

Pos logit contributions
 corrid+0.001
acco+0.001
+0.001
2020+0.001
GGGGGGGG+0.001
Neg logit contributions
 Brune-0.001
 Haas-0.001
worthiness-0.001
 Dustin-0.001
 NYU-0.001
Token fairy
Token ID25607
Feature activation+1.46e+00

Pos logit contributions
 Brune+0.017
 Haas+0.016
worthiness+0.016
 Dustin+0.016
 NYU+0.016
Neg logit contributions
 corrid-0.022
acco-0.020
-0.020
2020-0.020
GGGGGGGG-0.019
Token tales
Token ID19490
Feature activation+3.36e-02

Pos logit contributions
 corrid+1.992
acco+1.691
+1.673
2020+1.671
 retri+1.654
Neg logit contributions
 Brune-2.369
 Haas-2.301
worthiness-2.283
 Dustin-2.225
 NYU-2.202
Token sway
Token ID20009
Feature activation+1.20e-01

Pos logit contributions
 corrid+0.643
acco+0.570
+0.569
2020+0.568
 retri+0.557
Neg logit contributions
 Brune-0.446
 Haas-0.428
worthiness-0.425
 Dustin-0.414
 NYU-0.406
Token your
Token ID534
Feature activation+4.53e-02

Pos logit contributions
 corrid+0.211
acco+0.187
+0.186
2020+0.186
 retri+0.182
Neg logit contributions
 Brune-0.148
 Haas-0.142
worthiness-0.142
 Dustin-0.138
 NYU-0.135
Token body
Token ID1767
Feature activation+4.96e-01

Pos logit contributions
 corrid+0.083
2020+0.074
acco+0.074
+0.073
GGGGGGGG+0.072
Neg logit contributions
 Brune-0.053
 Haas-0.051
worthiness-0.050
 Dustin-0.049
 NYU-0.048
Token to
Token ID284
Feature activation-8.46e-02

Pos logit contributions
 corrid+0.851
acco+0.750
+0.749
2020+0.745
 retri+0.731
Neg logit contributions
 Brune-0.636
 Haas-0.613
worthiness-0.612
 Dustin-0.593
 NYU-0.581
Token and
Token ID290
Feature activation-2.54e-02

Pos logit contributions
 Brune+0.109
 Haas+0.105
worthiness+0.104
 Dustin+0.102
 NYU+0.099
Neg logit contributions
 corrid-0.145
2020-0.128
-0.128
acco-0.127
GGGGGGGG-0.125
Token fro
Token ID8400
Feature activation-2.42e+00

Pos logit contributions
 Brune+0.032
 Haas+0.031
worthiness+0.031
 Dustin+0.030
 NYU+0.030
Neg logit contributions
 corrid-0.043
acco-0.038
-0.038
2020-0.038
 retri-0.038
Token;
Token ID26
Feature activation-1.94e-01

Pos logit contributions
 Brune+2.672
worthiness+2.618
 Haas+2.560
 Dustin+2.501
 civ+2.400
Neg logit contributions
 corrid-4.527
-4.044
2020-4.015
acco-3.983
Adapt-3.927
Token dance
Token ID9280
Feature activation-4.52e-01

Pos logit contributions
 Brune+0.250
 Haas+0.240
worthiness+0.237
 Dustin+0.233
 NYU+0.227
Neg logit contributions
 corrid-0.333
acco-0.294
2020-0.293
-0.292
GGGGGGGG-0.289
Token only
Token ID691
Feature activation-4.47e-01

Pos logit contributions
 Brune+0.599
 Haas+0.576
worthiness+0.574
 Dustin+0.560
 NYU+0.547
Neg logit contributions
 corrid-0.754
acco-0.671
-0.669
2020-0.664
GGGGGGGG-0.649
Token from
Token ID422
Feature activation-6.39e-01

Pos logit contributions
 Brune+0.566
 Haas+0.548
worthiness+0.542
 Dustin+0.529
 NYU+0.516
Neg logit contributions
 corrid-0.773
acco-0.687
-0.686
2020-0.682
GGGGGGGG-0.667
Token the
Token ID262
Feature activation-1.12e-01

Pos logit contributions
 Brune+0.783
 Haas+0.754
worthiness+0.747
 Dustin+0.726
 NYU+0.713
Neg logit contributions
 corrid-1.131
acco-1.008
-1.008
2020-1.006
GGGGGGGG-0.984
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
 corrid+0.217
acco+0.192
2020+0.191
+0.191
 retri+0.188
Neg logit contributions
 Brune-0.159
 Haas-0.153
worthiness-0.151
 Dustin-0.148
 NYU-0.145
Token university
Token ID6403
Feature activation+9.03e-02

Pos logit contributions
 corrid+0.232
acco+0.204
+0.202
2020+0.202
 retri+0.199
Neg logit contributions
 Brune-0.192
 Haas-0.186
worthiness-0.184
 Dustin-0.180
 NYU-0.177
Token's
Token ID338
Feature activation-5.92e-01

Pos logit contributions
 corrid+0.165
acco+0.147
2020+0.146
+0.146
 retri+0.144
Neg logit contributions
 Brune-0.106
 Haas-0.101
worthiness-0.101
 Dustin-0.098
 NYU-0.096
Token board
Token ID3096
Feature activation-8.50e-01

Pos logit contributions
 Brune+0.738
 Haas+0.713
worthiness+0.698
 Dustin+0.684
 NYU+0.672
Neg logit contributions
 corrid-1.041
acco-0.920
-0.915
2020-0.913
GGGGGGGG-0.905
Token of
Token ID286
Feature activation+1.18e-01

Pos logit contributions
 Brune+1.054
 Haas+1.014
worthiness+1.009
 Dustin+0.986
 NYU+0.961
Neg logit contributions
 corrid-1.491
acco-1.319
2020-1.313
-1.304
GGGGGGGG-1.292
Token trustees
Token ID36636
Feature activation-2.40e+00

Pos logit contributions
 corrid+0.261
acco+0.237
+0.236
2020+0.235
 retri+0.232
Neg logit contributions
 Brune-0.093
 Haas-0.087
worthiness-0.086
 Dustin-0.083
 NYU-0.080
Token.
Token ID13
Feature activation+1.37e-01

Pos logit contributions
 Brune+2.583
 Haas+2.495
worthiness+2.449
 Dustin+2.416
 NYU+2.330
Neg logit contributions
 corrid-4.574
acco-4.083
GGGGGGGG-4.060
2020-4.055
-4.006
Token "
Token ID366
Feature activation-4.62e-01

Pos logit contributions
 corrid+0.259
acco+0.233
+0.232
2020+0.232
 retri+0.228
Neg logit contributions
 Brune-0.147
worthiness-0.140
 Haas-0.140
 Dustin-0.135
 NYU-0.132
TokenThe
Token ID464
Feature activation+2.38e-01

Pos logit contributions
 Brune+0.677
 Haas+0.653
worthiness+0.649
 Dustin+0.632
 NYU+0.626
Neg logit contributions
 corrid-0.737
acco-0.623
 retri-0.616
-0.603
GGGGGGGG-0.601
Token extension
Token ID7552
Feature activation+3.57e-01

Pos logit contributions
 corrid+0.390
acco+0.341
+0.339
2020+0.339
GGGGGGGG+0.334
Neg logit contributions
 Brune-0.327
 Haas-0.317
worthiness-0.312
 Dustin-0.305
 NYU-0.302
Token of
Token ID286
Feature activation+2.39e-01

Pos logit contributions
 corrid+0.625
acco+0.551
+0.550
2020+0.546
GGGGGGGG+0.541
Neg logit contributions
 Brune-0.453
 Haas-0.434
worthiness-0.433
 Dustin-0.419
 NYU-0.413
Token who
Token ID508
Feature activation-5.47e-02

Pos logit contributions
 Brune+0.115
 Haas+0.110
worthiness+0.109
 Dustin+0.108
 NYU+0.105
Neg logit contributions
 corrid-0.164
acco-0.145
2020-0.144
-0.144
GGGGGGGG-0.142
Token died
Token ID3724
Feature activation-9.69e-01

Pos logit contributions
 Brune+0.071
 Haas+0.068
worthiness+0.067
 Dustin+0.066
 NYU+0.065
Neg logit contributions
 corrid-0.094
acco-0.083
2020-0.082
-0.082
GGGGGGGG-0.081
Token 16
Token ID1467
Feature activation+6.86e-01

Pos logit contributions
 Brune+1.231
 Haas+1.170
worthiness+1.151
 Dustin+1.150
 NYU+1.114
Neg logit contributions
 corrid-1.690
acco-1.502
-1.483
2020-1.476
GGGGGGGG-1.454
Token years
Token ID812
Feature activation-8.38e-01

Pos logit contributions
 corrid+1.073
acco+0.939
2020+0.932
+0.932
 retri+0.916
Neg logit contributions
 Brune-0.974
 Haas-0.942
worthiness-0.938
 Dustin-0.914
 NYU-0.900
Token before
Token ID878
Feature activation+1.98e-01

Pos logit contributions
 Brune+0.967
worthiness+0.920
 Haas+0.920
 Dustin+0.893
 NYU+0.876
Neg logit contributions
 corrid-1.545
acco-1.382
2020-1.374
-1.371
GGGGGGGG-1.342
Token Civil
Token ID7511
Feature activation-2.40e+00

Pos logit contributions
 corrid+0.352
acco+0.313
2020+0.309
+0.309
 retri+0.305
Neg logit contributions
 Brune-0.244
 Haas-0.233
worthiness-0.232
 Dustin-0.227
 NYU-0.223
Token War
Token ID1810
Feature activation-4.37e-01

Pos logit contributions
 Brune+1.788
 Haas+1.686
worthiness+1.636
 Dustin+1.617
 NYU+1.581
Neg logit contributions
 corrid-5.581
GGGGGGGG-4.910
 retri-4.847
acco-4.832
-4.795
Token,
Token ID11
Feature activation-7.15e-02

Pos logit contributions
 Brune+0.543
 Haas+0.521
worthiness+0.519
 Dustin+0.512
 NYU+0.498
Neg logit contributions
 corrid-0.761
acco-0.674
-0.670
2020-0.669
GGGGGGGG-0.657
Token was
Token ID373
Feature activation-1.45e-01

Pos logit contributions
 Brune+0.091
 Haas+0.088
worthiness+0.088
 Dustin+0.086
 NYU+0.084
Neg logit contributions
 corrid-0.123
acco-0.108
-0.108
2020-0.108
GGGGGGGG-0.106
Token "
Token ID366
Feature activation-6.04e-01

Pos logit contributions
 Brune+0.182
 Haas+0.175
worthiness+0.173
 Dustin+0.170
 NYU+0.166
Neg logit contributions
 corrid-0.251
acco-0.222
2020-0.221
-0.220
 retri-0.216
Tokenreally
Token ID27485
Feature activation+5.25e-01

Pos logit contributions
 Brune+0.763
worthiness+0.746
 Haas+0.733
 Dustin+0.716
 NYU+0.699
Neg logit contributions
 corrid-1.051
acco-0.914
-0.904
2020-0.898
GGGGGGGG-0.896
Token sensitive
Token ID8564
Feature activation+3.40e-01

Pos logit contributions
 corrid+0.148
acco+0.131
+0.130
2020+0.130
GGGGGGGG+0.129
Neg logit contributions
 Brune-0.117
 Haas-0.114
worthiness-0.111
 Dustin-0.110
 NYU-0.109
Token nature
Token ID3450
Feature activation+2.36e-01

Pos logit contributions
 corrid+0.561
acco+0.492
2020+0.491
+0.489
GGGGGGGG+0.488
Neg logit contributions
 Brune-0.460
 Haas-0.445
worthiness-0.438
 NYU-0.428
 Dustin-0.427
Token of
Token ID286
Feature activation+1.25e-01

Pos logit contributions
 corrid+0.393
acco+0.347
+0.345
2020+0.344
 retri+0.339
Neg logit contributions
 Brune-0.312
 Haas-0.300
worthiness-0.299
 Dustin-0.291
 NYU-0.286
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
 corrid+0.219
2020+0.193
acco+0.192
+0.191
GGGGGGGG+0.191
Neg logit contributions
 Brune-0.157
 Haas-0.152
worthiness-0.149
 Dustin-0.145
 NYU-0.144
Token mission
Token ID4365
Feature activation+6.30e-02

Pos logit contributions
 corrid+0.332
acco+0.292
2020+0.292
GGGGGGGG+0.291
+0.290
Neg logit contributions
 Brune-0.276
 Haas-0.268
worthiness-0.264
 Dustin-0.258
 NYU-0.257
Token means
Token ID1724
Feature activation+1.58e+00

Pos logit contributions
 corrid+0.108
acco+0.095
+0.095
2020+0.094
GGGGGGGG+0.094
Neg logit contributions
 Brune-0.081
 Haas-0.078
worthiness-0.078
 Dustin-0.075
 NYU-0.074
Token the
Token ID262
Feature activation+3.22e-01

Pos logit contributions
 corrid+2.533
acco+2.222
2020+2.205
+2.204
 retri+2.165
Neg logit contributions
 Brune-2.201
 Haas-2.127
worthiness-2.116
 Dustin-2.064
 NYU-2.031
Token exact
Token ID2748
Feature activation+1.02e-01

Pos logit contributions
 corrid+0.535
acco+0.470
2020+0.469
+0.467
GGGGGGGG+0.463
Neg logit contributions
 Brune-0.432
 Haas-0.418
worthiness-0.413
 Dustin-0.403
 NYU-0.401
Token date
Token ID3128
Feature activation+4.80e-01

Pos logit contributions
 corrid+0.183
acco+0.164
2020+0.162
+0.162
GGGGGGGG+0.161
Neg logit contributions
 Brune-0.125
worthiness-0.120
 Haas-0.119
 Dustin-0.115
 NYU-0.113
Token and
Token ID290
Feature activation+9.16e-02

Pos logit contributions
 corrid+0.833
acco+0.738
+0.732
2020+0.730
 retri+0.719
Neg logit contributions
 Brune-0.606
 Haas-0.582
worthiness-0.579
 Dustin-0.562
 NYU-0.553
Token method
Token ID2446
Feature activation+1.18e+00

Pos logit contributions
 corrid+0.155
acco+0.137
2020+0.136
+0.136
GGGGGGGG+0.134
Neg logit contributions
 Brune-0.120
worthiness-0.115
 Haas-0.115
 Dustin-0.112
 NYU-0.110
Token
Token ID447
Feature activation+6.06e-02

Pos logit contributions
 corrid+0.285
acco+0.253
+0.251
2020+0.251
GGGGGGGG+0.247
Neg logit contributions
 Brune-0.198
 Haas-0.190
worthiness-0.189
 Dustin-0.184
 NYU-0.180
Token
Token ID247
Feature activation-1.09e-01

Pos logit contributions
 corrid+0.098
acco+0.086
+0.084
2020+0.084
GGGGGGGG+0.083
Neg logit contributions
 Brune-0.084
 Haas-0.082
worthiness-0.082
 Dustin-0.079
 NYU-0.078
Tokens
Token ID82
Feature activation+1.76e-01

Pos logit contributions
 Brune+0.135
worthiness+0.131
 Haas+0.130
 Dustin+0.126
 NYU+0.123
Neg logit contributions
 corrid-0.191
acco-0.168
-0.168
2020-0.167
GGGGGGGG-0.165
Token liquor
Token ID20030
Feature activation+1.19e-01

Pos logit contributions
 corrid+0.290
acco+0.256
+0.253
2020+0.252
GGGGGGGG+0.250
Neg logit contributions
 Brune-0.237
 Haas-0.229
worthiness-0.227
 Dustin-0.222
 NYU-0.220
Token license
Token ID5964
Feature activation+5.07e-01

Pos logit contributions
 corrid+0.223
acco+0.200
2020+0.199
+0.198
GGGGGGGG+0.196
Neg logit contributions
 Brune-0.133
worthiness-0.128
 Haas-0.128
 Dustin-0.123
 NYU-0.121
Token means
Token ID1724
Feature activation+1.51e+00

Pos logit contributions
 corrid+0.859
acco+0.759
+0.754
2020+0.753
 retri+0.740
Neg logit contributions
 Brune-0.659
 Haas-0.636
worthiness-0.633
 Dustin-0.616
 NYU-0.604
Token he
Token ID339
Feature activation+2.79e-01

Pos logit contributions
 corrid+2.515
acco+2.221
+2.204
2020+2.203
 retri+2.169
Neg logit contributions
 Brune-1.994
 Haas-1.922
worthiness-1.914
 Dustin-1.863
 NYU-1.830
Token can
Token ID460
Feature activation+5.57e-01

Pos logit contributions
 corrid+0.493
acco+0.436
+0.434
2020+0.433
 retri+0.427
Neg logit contributions
 Brune-0.342
 Haas-0.328
worthiness-0.327
 Dustin-0.317
 NYU-0.311
Token
Token ID447
Feature activation+2.07e-01

Pos logit contributions
 corrid+0.861
acco+0.744
+0.739
2020+0.736
GGGGGGGG+0.728
Neg logit contributions
 Brune-0.816
 Haas-0.785
worthiness-0.780
 Dustin-0.765
 NYU-0.752
Token
Token ID247
Feature activation-4.19e-03

Pos logit contributions
 corrid+0.320
acco+0.277
+0.273
2020+0.270
GGGGGGGG+0.269
Neg logit contributions
 Brune-0.304
 Haas-0.296
worthiness-0.294
 Dustin-0.287
 NYU-0.281
Tokent
Token ID83
Feature activation-4.59e-01

Pos logit contributions
 Brune+0.004
 Haas+0.004
worthiness+0.004
 Dustin+0.003
 NYU+0.003
Neg logit contributions
 corrid-0.009
acco-0.008
-0.008
2020-0.008
 retri-0.008
Token damages
Token ID12616
Feature activation-1.99e-01

Pos logit contributions
 corrid+0.066
acco+0.059
+0.058
2020+0.058
GGGGGGGG+0.058
Neg logit contributions
 Brune-0.044
worthiness-0.042
 Haas-0.042
 Dustin-0.041
 NYU-0.040
Token linked
Token ID6692
Feature activation+3.87e-01

Pos logit contributions
 Brune+0.229
worthiness+0.219
 Haas+0.219
 Dustin+0.210
 NYU+0.205
Neg logit contributions
 corrid-0.373
acco-0.329
-0.328
GGGGGGGG-0.327
2020-0.326
Token to
Token ID284
Feature activation+1.17e-02

Pos logit contributions
 corrid+0.559
acco+0.483
+0.480
2020+0.478
 retri+0.471
Neg logit contributions
 Brune-0.592
 Haas-0.579
worthiness-0.574
 Dustin-0.562
 NYU-0.554
Token emissions
Token ID8971
Feature activation+1.10e+00

Pos logit contributions
 corrid+0.020
acco+0.017
+0.017
2020+0.017
GGGGGGGG+0.017
Neg logit contributions
 Brune-0.016
 Haas-0.015
worthiness-0.015
 Dustin-0.014
 NYU-0.014
Token from
Token ID422
Feature activation-7.23e-01

Pos logit contributions
 corrid+1.915
acco+1.696
+1.685
2020+1.683
 retri+1.657
Neg logit contributions
 Brune-1.382
 Haas-1.331
worthiness-1.324
 Dustin-1.286
 NYU-1.261
Token fossil
Token ID12584
Feature activation+1.56e+00

Pos logit contributions
 Brune+0.915
 Haas+0.868
worthiness+0.845
 Dustin+0.839
 NYU+0.826
Neg logit contributions
 corrid-1.286
-1.132
2020-1.124
acco-1.121
龍喚士-1.113
Token fuels
Token ID18017
Feature activation+8.96e-01

Pos logit contributions
 corrid+2.685
acco+2.383
+2.364
2020+2.351
 retri+2.334
Neg logit contributions
 Brune-1.960
worthiness-1.887
 Haas-1.884
 Dustin-1.826
 NYU-1.800
Token,
Token ID11
Feature activation+2.59e-02

Pos logit contributions
 corrid+1.666
acco+1.491
+1.481
2020+1.480
 retri+1.459
Neg logit contributions
 Brune-1.013
 Haas-0.970
worthiness-0.965
 Dustin-0.935
 NYU-0.916
Token industry
Token ID2831
Feature activation-1.26e-01

Pos logit contributions
 corrid+0.042
acco+0.037
+0.037
2020+0.036
GGGGGGGG+0.036
Neg logit contributions
 Brune-0.036
 Haas-0.035
worthiness-0.034
 Dustin-0.034
 NYU-0.033
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
 Brune+0.152
 Haas+0.146
worthiness+0.144
 Dustin+0.141
 NYU+0.137
Neg logit contributions
 corrid-0.226
acco-0.202
-0.201
2020-0.200
GGGGGGGG-0.198
Token biomass
Token ID42584
Feature activation+1.35e+00

Pos logit contributions
 corrid+0.344
+0.302
acco+0.302
2020+0.301
GGGGGGGG+0.296
Neg logit contributions
 Brune-0.270
 Haas-0.259
worthiness-0.256
 Dustin-0.251
 NYU-0.247
Token with
Token ID351
Feature activation+4.88e-02

Pos logit contributions
 Brune+0.050
 Haas+0.048
worthiness+0.048
 Dustin+0.046
 NYU+0.045
Neg logit contributions
 corrid-0.085
acco-0.075
-0.075
2020-0.075
 retri-0.074
Token
Token ID564
Feature activation-4.75e-01

Pos logit contributions
 corrid+0.080
acco+0.071
2020+0.070
+0.070
 retri+0.069
Neg logit contributions
 Brune-0.066
 Haas-0.064
worthiness-0.063
 Dustin-0.062
 NYU-0.061
Token
Token ID246
Feature activation-4.23e-01

Pos logit contributions
 Brune+0.614
 Haas+0.595
worthiness+0.595
 Dustin+0.577
 NYU+0.569
Neg logit contributions
 corrid-0.807
acco-0.708
2020-0.702
-0.697
 retri-0.692
TokenInside
Token ID24441
Feature activation-6.11e-01

Pos logit contributions
 Brune+0.632
 Haas+0.612
worthiness+0.612
 Dustin+0.596
 NYU+0.585
Neg logit contributions
 corrid-0.640
acco-0.550
 retri-0.537
2020-0.536
-0.535
Token the
Token ID262
Feature activation+5.48e-02

Pos logit contributions
 Brune+0.817
 Haas+0.788
worthiness+0.774
 Dustin+0.762
 NYU+0.743
Neg logit contributions
 corrid-1.019
acco-0.900
-0.886
2020-0.881
 retri-0.873
Token Dek
Token ID44297
Feature activation+2.78e+00

Pos logit contributions
 corrid+0.088
acco+0.076
2020+0.076
+0.076
 retri+0.075
Neg logit contributions
 Brune-0.077
 Haas-0.075
worthiness-0.074
 Dustin-0.072
 NYU-0.071
Tokenu
Token ID84
Feature activation+1.70e-01

Pos logit contributions
 corrid+4.960
acco+4.480
2020+4.437
+4.415
 retri+4.346
Neg logit contributions
 Brune-3.259
worthiness-3.137
 Haas-3.129
 Dustin-3.024
 NYU-2.967
Token Tree
Token ID12200
Feature activation+3.08e-01

Pos logit contributions
 corrid+0.243
acco+0.206
+0.205
2020+0.204
GGGGGGGG+0.201
Neg logit contributions
 Brune-0.269
 Haas-0.262
worthiness-0.254
 Dustin-0.252
 NYU-0.247
Token
Token ID447
Feature activation+5.63e-02

Pos logit contributions
 corrid+0.459
acco+0.399
+0.395
2020+0.394
 retri+0.387
Neg logit contributions
 Brune-0.462
 Haas-0.447
worthiness-0.444
 Dustin-0.435
 NYU-0.426
Token
Token ID247
Feature activation-4.90e-02

Pos logit contributions
 corrid+0.087
acco+0.075
2020+0.074
+0.074
GGGGGGGG+0.073
Neg logit contributions
 Brune-0.083
 Haas-0.080
worthiness-0.080
 Dustin-0.078
 NYU-0.077
Token,
Token ID11
Feature activation-4.30e-02

Pos logit contributions
 Brune+0.058
worthiness+0.056
 Haas+0.056
 Dustin+0.054
 NYU+0.053
Neg logit contributions
 corrid-0.088
acco-0.078
2020-0.078
-0.078
GGGGGGGG-0.076
Token point
Token ID966
Feature activation-6.01e-01

Pos logit contributions
 Brune+0.645
 Haas+0.620
worthiness+0.618
 Dustin+0.604
 NYU+0.594
Neg logit contributions
 corrid-0.876
acco-0.779
-0.774
2020-0.770
GGGGGGGG-0.757
Token,
Token ID11
Feature activation+3.75e-02

Pos logit contributions
 Brune+0.727
worthiness+0.698
 Haas+0.698
 Dustin+0.680
 NYU+0.664
Neg logit contributions
 corrid-1.083
acco-0.958
-0.944
2020-0.943
GGGGGGGG-0.929
Token but
Token ID475
Feature activation+4.35e-01

Pos logit contributions
 corrid+0.064
acco+0.057
+0.056
2020+0.056
 retri+0.055
Neg logit contributions
 Brune-0.048
 Haas-0.047
worthiness-0.046
 Dustin-0.045
 NYU-0.044
Token we
Token ID356
Feature activation-2.59e-01

Pos logit contributions
 corrid+0.765
acco+0.676
+0.672
2020+0.671
GGGGGGGG+0.659
Neg logit contributions
 Brune-0.546
 Haas-0.524
worthiness-0.520
 Dustin-0.508
 NYU-0.498
Token've
Token ID1053
Feature activation-3.34e-02

Pos logit contributions
 Brune+0.304
 Haas+0.289
worthiness+0.287
 Dustin+0.280
 NYU+0.275
Neg logit contributions
 corrid-0.476
acco-0.422
-0.421
2020-0.419
GGGGGGGG-0.418
Token reached
Token ID4251
Feature activation+1.62e+00

Pos logit contributions
 Brune+0.042
 Haas+0.041
worthiness+0.040
 Dustin+0.040
 NYU+0.039
Neg logit contributions
 corrid-0.058
-0.051
acco-0.051
2020-0.051
GGGGGGGG-0.050
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
 corrid+2.724
acco+2.413
+2.397
2020+2.395
 retri+2.362
Neg logit contributions
 Brune-2.086
 Haas-2.013
worthiness-2.009
 Dustin-1.944
 NYU-1.910
Token point
Token ID966
Feature activation-5.52e-01

Pos logit contributions
 corrid+0.236
+0.208
acco+0.207
2020+0.205
GGGGGGGG+0.204
Neg logit contributions
 Brune-0.190
 Haas-0.185
worthiness-0.182
 Dustin-0.179
 NYU-0.177
Token where
Token ID810
Feature activation+1.13e-02

Pos logit contributions
 Brune+0.587
 Haas+0.559
worthiness+0.551
 Dustin+0.537
 NYU+0.528
Neg logit contributions
 corrid-1.086
acco-0.966
2020-0.961
-0.955
 retri-0.944
Token this
Token ID428
Feature activation-1.93e-01

Pos logit contributions
 corrid+0.020
acco+0.017
+0.017
2020+0.017
GGGGGGGG+0.017
Neg logit contributions
 Brune-0.015
 Haas-0.014
worthiness-0.014
 Dustin-0.014
 NYU-0.013
Token sort
Token ID3297
Feature activation-2.74e-01

Pos logit contributions
 Brune+0.233
 Haas+0.225
worthiness+0.224
 Dustin+0.218
 NYU+0.214
Neg logit contributions
 corrid-0.345
acco-0.309
-0.307
2020-0.306
GGGGGGGG-0.300
Token that
Token ID326
Feature activation-1.38e-01

Pos logit contributions
 Brune+0.480
worthiness+0.455
 Haas+0.454
 Dustin+0.445
 NYU+0.434
Neg logit contributions
 corrid-0.688
2020-0.611
acco-0.611
-0.608
GGGGGGGG-0.600
Token was
Token ID373
Feature activation-2.84e-01

Pos logit contributions
 Brune+0.172
 Haas+0.166
worthiness+0.164
 Dustin+0.163
 NYU+0.159
Neg logit contributions
 corrid-0.242
acco-0.214
2020-0.213
-0.213
 retri-0.210
Token featured
Token ID8096
Feature activation-1.26e-01

Pos logit contributions
 Brune+0.375
 Haas+0.361
worthiness+0.354
 Dustin+0.352
 NYU+0.346
Neg logit contributions
 corrid-0.477
acco-0.420
2020-0.418
-0.418
GGGGGGGG-0.409
Token in
Token ID287
Feature activation-8.21e-02

Pos logit contributions
 Brune+0.155
 Haas+0.149
worthiness+0.149
 Dustin+0.145
 NYU+0.142
Neg logit contributions
 corrid-0.222
acco-0.197
-0.196
2020-0.195
 retri-0.193
Token a
Token ID257
Feature activation+1.13e-02

Pos logit contributions
 Brune+0.104
 Haas+0.100
worthiness+0.099
 Dustin+0.097
 NYU+0.095
Neg logit contributions
 corrid-0.142
acco-0.126
2020-0.125
-0.125
 retri-0.124
Token number
Token ID1271
Feature activation+3.33e-01

Pos logit contributions
 corrid+0.019
acco+0.017
+0.017
2020+0.017
 retri+0.017
Neg logit contributions
 Brune-0.015
 Haas-0.014
worthiness-0.014
 Dustin-0.014
 NYU-0.013
Token of
Token ID286
Feature activation-4.28e-04

Pos logit contributions
 corrid+0.571
acco+0.501
+0.497
2020+0.496
GGGGGGGG+0.491
Neg logit contributions
 Brune-0.430
 Haas-0.414
worthiness-0.412
 Dustin-0.402
 NYU-0.394
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
 Brune+0.001
 Haas+0.001
worthiness+0.001
 Dustin+0.001
 NYU+0.001
Neg logit contributions
 corrid-0.001
acco-0.001
-0.001
2020-0.001
 retri-0.001
Token trailers
Token ID33122
Feature activation-1.61e+00

Pos logit contributions
 Brune+0.132
 Haas+0.128
worthiness+0.127
 Dustin+0.125
 NYU+0.122
Neg logit contributions
 corrid-0.173
acco-0.153
-0.153
2020-0.153
 retri-0.151
Token,
Token ID11
Feature activation-6.58e-02

Pos logit contributions
 Brune+1.894
 Haas+1.846
worthiness+1.809
 Dustin+1.806
 NYU+1.732
Neg logit contributions
 corrid-2.912
2020-2.558
acco-2.557
-2.532
GGGGGGGG-2.520
Token prom
Token ID1552
Feature activation-1.29e+00

Pos logit contributions
 Brune+0.087
 Haas+0.084
worthiness+0.083
 Dustin+0.082
 NYU+0.080
Neg logit contributions
 corrid-0.111
acco-0.097
2020-0.097
-0.097
GGGGGGGG-0.095
TokenOn
Token ID2202
Feature activation+6.01e-02

Pos logit contributions
 corrid+0.262
acco+0.222
 retri+0.217
+0.215
2020+0.213
Neg logit contributions
 Brune-0.262
worthiness-0.255
 Haas-0.254
 Dustin-0.249
 NYU-0.245
Token Aug
Token ID2447
Feature activation-2.32e-01

Pos logit contributions
 corrid+0.109
acco+0.096
+0.095
2020+0.095
GGGGGGGG+0.094
Neg logit contributions
 Brune-0.073
 Haas-0.070
worthiness-0.069
 Dustin-0.068
 NYU-0.067
Token.
Token ID13
Feature activation+2.65e-03

Pos logit contributions
 Brune+0.242
 Haas+0.231
worthiness+0.231
 Dustin+0.222
 NYU+0.217
Neg logit contributions
 corrid-0.460
acco-0.407
-0.406
2020-0.402
 retri-0.400
Token 12
Token ID1105
Feature activation+5.83e-01

Pos logit contributions
 corrid+0.005
acco+0.004
+0.004
GGGGGGGG+0.004
2020+0.004
Neg logit contributions
 Brune-0.003
 Haas-0.003
worthiness-0.003
 Dustin-0.003
 NYU-0.003
Token,
Token ID11
Feature activation+7.46e-02

Pos logit contributions
 corrid+0.981
acco+0.870
+0.865
2020+0.864
 retri+0.851
Neg logit contributions
 Brune-0.751
 Haas-0.725
worthiness-0.722
 Dustin-0.701
 NYU-0.689
Token 2012
Token ID2321
Feature activation+2.03e-01

Pos logit contributions
 corrid+0.132
acco+0.116
+0.115
2020+0.115
GGGGGGGG+0.114
Neg logit contributions
 Brune-0.094
 Haas-0.090
worthiness-0.089
 Dustin-0.088
 NYU-0.086
Token,
Token ID11
Feature activation+1.95e-01

Pos logit contributions
 corrid+0.340
acco+0.301
+0.300
2020+0.298
 retri+0.294
Neg logit contributions
 Brune-0.265
 Haas-0.254
worthiness-0.254
 Dustin-0.246
 NYU-0.242
Token USA
Token ID4916
Feature activation+7.78e-01

Pos logit contributions
 corrid+0.344
acco+0.304
2020+0.302
+0.302
 retri+0.297
Neg logit contributions
 Brune-0.242
 Haas-0.233
worthiness-0.230
 Dustin-0.227
 NYU-0.222
Token Today
Token ID6288
Feature activation+7.96e-02

Pos logit contributions
 corrid+1.343
acco+1.192
2020+1.184
+1.183
 retri+1.164
Neg logit contributions
 Brune-0.979
 Haas-0.942
worthiness-0.938
 Dustin-0.911
 NYU-0.894
Token/
Token ID14
Feature activation-8.23e-02

Pos logit contributions
 corrid+0.135
acco+0.119
2020+0.118
+0.118
GGGGGGGG+0.116
Neg logit contributions
 Brune-0.104
 Haas-0.100
worthiness-0.099
 Dustin-0.097
 NYU-0.095
TokenGall
Token ID37122
Feature activation+9.62e-01

Pos logit contributions
 Brune+0.137
 Haas+0.134
worthiness+0.133
 Dustin+0.130
 NYU+0.129
Neg logit contributions
 corrid-0.109
acco-0.093
-0.091
2020-0.091
 retri-0.090
Token.
Token ID13
Feature activation-8.98e-02

Pos logit contributions
 Brune+0.242
 Haas+0.233
worthiness+0.232
 Dustin+0.226
 NYU+0.219
Neg logit contributions
 corrid-0.395
acco-0.351
-0.349
2020-0.349
GGGGGGGG-0.342
Token A
Token ID317
Feature activation+1.40e-01

Pos logit contributions
 Brune+0.107
 Haas+0.103
worthiness+0.101
 Dustin+0.101
 NYU+0.098
Neg logit contributions
 corrid-0.168
acco-0.147
-0.145
 retri-0.145
2020-0.143
Token Supreme
Token ID5617
Feature activation+1.20e+00

Pos logit contributions
 corrid+0.246
acco+0.220
+0.219
2020+0.218
GGGGGGGG+0.215
Neg logit contributions
 Brune-0.172
 Haas-0.165
worthiness-0.164
 Dustin-0.162
 NYU-0.157
Token product
Token ID1720
Feature activation+5.17e-01

Pos logit contributions
 corrid+2.098
acco+1.869
2020+1.854
+1.852
 retri+1.819
Neg logit contributions
 Brune-1.479
 Haas-1.419
worthiness-1.411
 Dustin-1.378
 NYU-1.348
Token is
Token ID318
Feature activation-1.67e-01

Pos logit contributions
 corrid+0.919
acco+0.816
+0.812
2020+0.810
GGGGGGGG+0.796
Neg logit contributions
 Brune-0.630
 Haas-0.605
worthiness-0.604
 Dustin-0.587
 NYU-0.571
Token not
Token ID407
Feature activation+4.37e-03

Pos logit contributions
 Brune+0.212
 Haas+0.203
worthiness+0.202
 Dustin+0.199
 NYU+0.193
Neg logit contributions
 corrid-0.287
acco-0.254
-0.254
2020-0.254
GGGGGGGG-0.250
Token desperate
Token ID12111
Feature activation-2.21e-01

Pos logit contributions
 corrid+0.007
+0.007
acco+0.007
2020+0.007
GGGGGGGG+0.006
Neg logit contributions
 Brune-0.006
 Haas-0.005
worthiness-0.005
 Dustin-0.005
 NYU-0.005
Token to
Token ID284
Feature activation+3.37e-02

Pos logit contributions
 Brune+0.280
worthiness+0.270
 Haas+0.270
 Dustin+0.263
 NYU+0.254
Neg logit contributions
 corrid-0.380
-0.337
acco-0.335
2020-0.334
GGGGGGGG-0.328
Token sell
Token ID3677
Feature activation+4.42e-01

Pos logit contributions
 corrid+0.058
acco+0.051
+0.051
2020+0.051
GGGGGGGG+0.050
Neg logit contributions
 Brune-0.043
worthiness-0.041
 Haas-0.041
 Dustin-0.041
 NYU-0.039
Token itself
Token ID2346
Feature activation+3.89e-01

Pos logit contributions
 corrid+0.774
acco+0.688
+0.685
2020+0.680
GGGGGGGG+0.670
Neg logit contributions
 Brune-0.549
worthiness-0.526
 Haas-0.525
 Dustin-0.515
 NYU-0.499
Token to
Token ID284
Feature activation-3.22e-02

Pos logit contributions
 corrid+0.687
acco+0.610
+0.607
2020+0.603
GGGGGGGG+0.593
Neg logit contributions
 Brune-0.480
worthiness-0.462
 Haas-0.461
 Dustin-0.448
 NYU-0.436
Tokenability
Token ID1799
Feature activation-8.11e-01

Pos logit contributions
 Brune+0.705
worthiness+0.687
 Haas+0.662
 Dustin+0.632
 NYU+0.621
Neg logit contributions
 corrid-1.439
acco-1.284
-1.279
2020-1.265
GGGGGGGG-1.261
Token much
Token ID881
Feature activation+1.55e-01

Pos logit contributions
 Brune+0.977
worthiness+0.962
 Haas+0.940
 Dustin+0.902
 NYU+0.887
Neg logit contributions
 corrid-1.460
acco-1.296
-1.294
2020-1.272
GGGGGGGG-1.262
Token closer
Token ID5699
Feature activation-9.77e-03

Pos logit contributions
 corrid+0.233
+0.202
2020+0.201
acco+0.201
GGGGGGGG+0.196
Neg logit contributions
 Brune-0.233
 Haas-0.227
worthiness-0.225
 Dustin-0.220
 NYU-0.217
Token to
Token ID284
Feature activation+1.46e-01

Pos logit contributions
 Brune+0.014
 Haas+0.014
worthiness+0.014
 Dustin+0.014
 NYU+0.013
Neg logit contributions
 corrid-0.015
acco-0.013
2020-0.013
-0.013
 retri-0.013
Token that
Token ID326
Feature activation+8.21e-02

Pos logit contributions
 corrid+0.241
acco+0.212
+0.210
2020+0.209
GGGGGGGG+0.206
Neg logit contributions
 Brune-0.196
 Haas-0.191
worthiness-0.190
 Dustin-0.184
 NYU-0.182
Token of
Token ID286
Feature activation-2.47e-02

Pos logit contributions
 corrid+0.137
acco+0.121
+0.120
2020+0.120
 retri+0.118
Neg logit contributions
 Brune-0.108
 Haas-0.105
worthiness-0.104
 Dustin-0.101
 NYU-0.100
Token the
Token ID262
Feature activation-8.28e-02

Pos logit contributions
 Brune+0.032
 Haas+0.031
worthiness+0.030
 Dustin+0.030
 NYU+0.029
Neg logit contributions
 corrid-0.042
acco-0.037
-0.037
2020-0.037
 retri-0.036
Token other
Token ID584
Feature activation-3.78e-01

Pos logit contributions
 Brune+0.105
 Haas+0.102
worthiness+0.101
 Dustin+0.098
 NYU+0.097
Neg logit contributions
 corrid-0.143
acco-0.126
-0.125
2020-0.125
GGGGGGGG-0.123
Token engine
Token ID3113
Feature activation-7.94e-01

Pos logit contributions
 Brune+0.448
 Haas+0.433
worthiness+0.429
 Dustin+0.417
 NYU+0.409
Neg logit contributions
 corrid-0.684
acco-0.608
-0.604
2020-0.604
GGGGGGGG-0.593
Token
Token ID198
Feature activation-1.84e-01

Pos logit contributions
 Brune+0.971
 Haas+0.942
worthiness+0.936
 Dustin+0.906
 NYU+0.885
Neg logit contributions
 corrid-1.406
acco-1.242
-1.240
2020-1.225
龍喚士-1.211
Token
Token ID198
Feature activation-8.92e-02

Pos logit contributions
 Brune+0.212
 Haas+0.203
worthiness+0.202
 Dustin+0.196
 NYU+0.192
Neg logit contributions
 corrid-0.345
acco-0.303
-0.301
2020-0.299
GGGGGGGG-0.298
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
 corrid+0.162
acco+0.144
2020+0.144
+0.143
GGGGGGGG+0.141
Neg logit contributions
 Brune-0.120
 Haas-0.116
worthiness-0.115
 Dustin-0.112
 NYU-0.110
Token cities
Token ID4736
Feature activation-3.11e-01

Pos logit contributions
 corrid+0.024
acco+0.021
+0.021
2020+0.021
GGGGGGGG+0.021
Neg logit contributions
 Brune-0.023
 Haas-0.022
worthiness-0.022
 Dustin-0.022
 NYU-0.021
Token are
Token ID389
Feature activation-1.80e-02

Pos logit contributions
 Brune+0.395
 Haas+0.376
worthiness+0.375
 Dustin+0.365
 NYU+0.357
Neg logit contributions
 corrid-0.541
2020-0.476
acco-0.475
-0.475
GGGGGGGG-0.471
Token keeping
Token ID5291
Feature activation+5.37e-01

Pos logit contributions
 Brune+0.025
 Haas+0.024
worthiness+0.023
 Dustin+0.023
 NYU+0.023
Neg logit contributions
 corrid-0.030
acco-0.026
2020-0.026
-0.026
GGGGGGGG-0.025
Token makes
Token ID1838
Feature activation-1.52e-01

Pos logit contributions
 corrid+0.957
acco+0.852
+0.847
2020+0.846
 retri+0.831
Neg logit contributions
 Brune-0.649
 Haas-0.623
worthiness-0.620
 Dustin-0.602
 NYU-0.590
Token it
Token ID340
Feature activation+1.11e-01

Pos logit contributions
 Brune+0.189
 Haas+0.182
worthiness+0.179
 Dustin+0.176
 NYU+0.173
Neg logit contributions
 corrid-0.266
2020-0.236
-0.235
acco-0.235
GGGGGGGG-0.233
Token very
Token ID845
Feature activation+6.75e-01

Pos logit contributions
 corrid+0.182
+0.160
acco+0.160
2020+0.159
GGGGGGGG+0.157
Neg logit contributions
 Brune-0.150
worthiness-0.144
 Haas-0.144
 Dustin-0.140
 NYU-0.139
Token difficult
Token ID2408
Feature activation+9.62e-01

Pos logit contributions
 corrid+1.058
acco+0.925
+0.921
2020+0.918
GGGGGGGG+0.906
Neg logit contributions
 Brune-0.960
 Haas-0.928
worthiness-0.922
 Dustin-0.902
 NYU-0.891
Token to
Token ID284
Feature activation+1.26e-01

Pos logit contributions
 corrid+1.468
acco+1.279
2020+1.269
+1.266
 retri+1.247
Neg logit contributions
 Brune-1.402
 Haas-1.361
worthiness-1.353
 Dustin-1.325
 NYU-1.301
Token determine
Token ID5004
Feature activation-6.00e-01

Pos logit contributions
 corrid+0.221
acco+0.194
+0.193
2020+0.192
GGGGGGGG+0.191
Neg logit contributions
 Brune-0.160
 Haas-0.152
worthiness-0.152
 Dustin-0.148
 NYU-0.146
Token if
Token ID611
Feature activation-2.57e-01

Pos logit contributions
 Brune+0.730
worthiness+0.700
 Haas+0.699
 Dustin+0.675
 NYU+0.667
Neg logit contributions
 corrid-1.067
acco-0.957
-0.949
2020-0.945
GGGGGGGG-0.933
Token,
Token ID11
Feature activation-1.16e-01

Pos logit contributions
 Brune+0.645
 Haas+0.615
worthiness+0.613
 Dustin+0.597
 NYU+0.582
Neg logit contributions
 corrid-1.036
acco-0.917
-0.913
2020-0.909
GGGGGGGG-0.899
Token but
Token ID475
Feature activation+3.83e-01

Pos logit contributions
 Brune+0.162
 Haas+0.157
worthiness+0.154
 Dustin+0.153
 NYU+0.150
Neg logit contributions
 corrid-0.187
acco-0.163
-0.163
2020-0.161
GGGGGGGG-0.160
Token anyone
Token ID2687
Feature activation-4.27e-01

Pos logit contributions
 corrid+0.664
acco+0.586
+0.584
2020+0.583
GGGGGGGG+0.570
Neg logit contributions
 Brune-0.490
 Haas-0.472
worthiness-0.466
 Dustin-0.459
 NYU-0.449
Token who
Token ID508
Feature activation-1.97e-01

Pos logit contributions
 Brune+0.504
 Haas+0.483
worthiness+0.480
 Dustin+0.467
 NYU+0.458
Neg logit contributions
 corrid-0.775
acco-0.691
-0.687
2020-0.685
GGGGGGGG-0.673
Token bought
Token ID5839
Feature activation-2.94e-01

Pos logit contributions
 Brune+0.248
 Haas+0.238
worthiness+0.237
 Dustin+0.231
 NYU+0.226
Neg logit contributions
 corrid-0.345
-0.304
acco-0.303
2020-0.302
GGGGGGGG-0.298
Token bitcoins
Token ID22690
Feature activation-7.27e-01

Pos logit contributions
 Brune+0.363
 Haas+0.346
worthiness+0.342
 Dustin+0.336
 NYU+0.329
Neg logit contributions
 corrid-0.520
acco-0.462
-0.459
2020-0.459
GGGGGGGG-0.452
Token at
Token ID379
Feature activation+7.04e-01

Pos logit contributions
 Brune+0.913
 Haas+0.877
worthiness+0.873
 Dustin+0.853
 NYU+0.835
Neg logit contributions
 corrid-1.278
-1.131
acco-1.127
GGGGGGGG-1.113
2020-1.110
Token last
Token ID938
Feature activation+3.42e-01

Pos logit contributions
 corrid+1.207
acco+1.068
+1.062
2020+1.061
 retri+1.043
Neg logit contributions
 Brune-0.904
 Haas-0.871
worthiness-0.860
 Dustin-0.843
 NYU-0.829
Token week
Token ID1285
Feature activation-8.54e-01

Pos logit contributions
 corrid+0.497
acco+0.428
+0.424
2020+0.423
GGGGGGGG+0.417
Neg logit contributions
 Brune-0.527
 Haas-0.511
worthiness-0.510
 Dustin-0.501
 NYU-0.491
Token's
Token ID338
Feature activation-6.19e-01

Pos logit contributions
 Brune+0.920
 Haas+0.878
worthiness+0.869
 Dustin+0.849
 NYU+0.832
Neg logit contributions
 corrid-1.630
acco-1.457
-1.454
2020-1.449
 retri-1.430
Token price
Token ID2756
Feature activation+3.84e-01

Pos logit contributions
 Brune+0.837
 Haas+0.804
 Dustin+0.789
worthiness+0.788
 NYU+0.773
Neg logit contributions
 corrid-1.022
2020-0.899
acco-0.898
-0.897
GGGGGGGG-0.881
Token/
Token ID14
Feature activation+5.24e-01

Pos logit contributions
 corrid+0.660
acco+0.588
+0.584
2020+0.583
 retri+0.575
Neg logit contributions
 Brune-0.440
 Haas-0.423
worthiness-0.421
 Dustin-0.408
 NYU-0.400
Tokenin
Token ID259
Feature activation-1.30e-01

Pos logit contributions
 corrid+0.699
acco+0.592
+0.585
2020+0.583
 retri+0.576
Neg logit contributions
 Brune-0.871
worthiness-0.847
 Haas-0.844
 Dustin-0.826
 NYU-0.814
Tokencoming
Token ID4976
Feature activation+6.54e-01

Pos logit contributions
 Brune+0.142
worthiness+0.135
 Haas+0.134
 Dustin+0.130
 NYU+0.127
Neg logit contributions
 corrid-0.250
acco-0.221
-0.220
2020-0.218
 retri-0.217
Token/
Token ID14
Feature activation+5.27e-01

Pos logit contributions
 corrid+1.216
acco+1.067
+1.064
2020+1.055
GGGGGGGG+1.054
Neg logit contributions
 Brune-0.759
worthiness-0.723
 Haas-0.720
 Dustin-0.698
 NYU-0.684
Tokenarticle
Token ID20205
Feature activation+2.99e-01

Pos logit contributions
 corrid+0.771
acco+0.658
+0.654
 retri+0.647
2020+0.646
Neg logit contributions
 Brune-0.811
worthiness-0.789
 Haas-0.782
 Dustin-0.766
 NYU-0.756
Token35
Token ID2327
Feature activation-3.92e-01

Pos logit contributions
 corrid+0.432
acco+0.368
+0.363
2020+0.361
 retri+0.358
Neg logit contributions
 Brune-0.469
 Haas-0.455
worthiness-0.453
 Dustin-0.442
 NYU-0.435
Token79
Token ID3720
Feature activation-6.26e-01

Pos logit contributions
 Brune+0.617
worthiness+0.597
 Haas+0.591
 Dustin+0.581
 NYU+0.571
Neg logit contributions
 corrid-0.566
acco-0.476
 retri-0.472
GGGGGGGG-0.471
-0.468
Token23
Token ID1954
Feature activation+1.06e-01

Pos logit contributions
 Brune+1.042
worthiness+1.010
 Haas+1.008
 Dustin+0.986
 NYU+0.974
Neg logit contributions
 corrid-0.850
acco-0.704
-0.694
 retri-0.692
GGGGGGGG-0.683
Token12
Token ID1065
Feature activation-1.26e-01

Pos logit contributions
 corrid+0.136
acco+0.114
+0.113
2020+0.112
 retri+0.111
Neg logit contributions
 Brune-0.182
 Haas-0.177
worthiness-0.177
 Dustin-0.173
 NYU-0.171
Token.
Token ID13
Feature activation+4.05e-01

Pos logit contributions
 Brune+0.134
 Haas+0.127
worthiness+0.127
 Dustin+0.123
 NYU+0.120
Neg logit contributions
 corrid-0.247
acco-0.220
-0.219
2020-0.217
 retri-0.216
Tokene
Token ID68
Feature activation-2.13e-01

Pos logit contributions
 corrid+0.773
+0.682
acco+0.681
GGGGGGGG+0.680
 retri+0.677
Neg logit contributions
 Brune-0.437
worthiness-0.424
 Haas-0.418
 Dustin-0.412
 NYU-0.403
Token what
Token ID644
Feature activation+4.39e-01

Pos logit contributions
 corrid+0.270
acco+0.239
+0.237
2020+0.237
 retri+0.233
Neg logit contributions
 Brune-0.196
 Haas-0.189
worthiness-0.188
 Dustin-0.185
 NYU-0.180
Token we
Token ID356
Feature activation-1.23e-01

Pos logit contributions
 corrid+0.766
acco+0.681
+0.676
2020+0.675
 retri+0.664
Neg logit contributions
 Brune-0.547
 Haas-0.528
worthiness-0.523
 Dustin-0.515
 NYU-0.503
Token chat
Token ID8537
Feature activation-5.60e-01

Pos logit contributions
 Brune+0.147
 Haas+0.140
worthiness+0.138
 Dustin+0.137
 NYU+0.133
Neg logit contributions
 corrid-0.221
acco-0.196
2020-0.194
-0.194
 retri-0.192
Token about
Token ID546
Feature activation+1.89e-01

Pos logit contributions
 Brune+0.700
 Haas+0.674
worthiness+0.669
 Dustin+0.660
 NYU+0.646
Neg logit contributions
 corrid-0.979
acco-0.862
2020-0.853
-0.851
 retri-0.843
Token:
Token ID25
Feature activation-7.55e-01

Pos logit contributions
 corrid+0.335
acco+0.298
2020+0.295
+0.295
 retri+0.291
Neg logit contributions
 Brune-0.231
 Haas-0.222
worthiness-0.220
 Dustin-0.215
 NYU-0.211
Token
Token ID198
Feature activation-7.51e-01

Pos logit contributions
 Brune+0.893
 Haas+0.858
worthiness+0.853
 Dustin+0.829
 NYU+0.812
Neg logit contributions
 corrid-1.361
acco-1.213
-1.205
2020-1.204
 retri-1.187
Token
Token ID198
Feature activation-6.10e-01

Pos logit contributions
 Brune+0.841
 Haas+0.802
worthiness+0.802
 Dustin+0.779
 NYU+0.763
Neg logit contributions
 corrid-1.461
acco-1.267
-1.256
GGGGGGGG-1.256
 retri-1.241
TokenStarting
Token ID22851
Feature activation+1.33e-01

Pos logit contributions
 Brune+0.892
worthiness+0.871
 Haas+0.865
 Dustin+0.853
 NYU+0.835
Neg logit contributions
 corrid-0.934
acco-0.802
-0.781
GGGGGGGG-0.779
 retri-0.779
Token from
Token ID422
Feature activation-5.54e-01

Pos logit contributions
 corrid+0.228
acco+0.202
+0.200
2020+0.200
 retri+0.197
Neg logit contributions
 Brune-0.170
 Haas-0.164
worthiness-0.162
 Dustin-0.159
 NYU-0.156
Token nothing
Token ID2147
Feature activation+5.27e-01

Pos logit contributions
 Brune+0.612
 Haas+0.586
worthiness+0.579
 Dustin+0.566
 NYU+0.554
Neg logit contributions
 corrid-1.045
acco-0.936
-0.930
2020-0.929
 retri-0.916
Token:
Token ID25
Feature activation-3.76e-01

Pos logit contributions
 corrid+0.937
acco+0.830
+0.826
2020+0.824
 retri+0.810
Neg logit contributions
 Brune-0.642
 Haas-0.617
worthiness-0.613
 Dustin-0.600
 NYU-0.587
Token and
Token ID290
Feature activation+1.44e-01

Pos logit contributions
 Brune+0.003
 Haas+0.003
worthiness+0.003
 Dustin+0.003
 NYU+0.003
Neg logit contributions
 corrid-0.004
acco-0.004
2020-0.004
-0.004
 retri-0.004
Token em
Token ID795
Feature activation-2.99e-01

Pos logit contributions
 corrid+0.246
acco+0.219
+0.217
2020+0.217
 retri+0.212
Neg logit contributions
 Brune-0.185
 Haas-0.178
worthiness-0.177
 Dustin-0.173
 NYU-0.169
Tokeninently
Token ID26528
Feature activation+3.15e-01

Pos logit contributions
 Brune+0.363
 Haas+0.348
worthiness+0.347
 Dustin+0.337
 NYU+0.330
Neg logit contributions
 corrid-0.531
acco-0.472
-0.469
2020-0.469
 retri-0.462
Token re
Token ID302
Feature activation-1.36e-01

Pos logit contributions
 corrid+0.529
acco+0.468
+0.465
2020+0.464
 retri+0.454
Neg logit contributions
 Brune-0.413
 Haas-0.397
worthiness-0.396
 Dustin-0.386
 NYU-0.378
Token-
Token ID12
Feature activation-9.62e-02

Pos logit contributions
 Brune+0.180
 Haas+0.174
worthiness+0.174
 Dustin+0.169
 NYU+0.165
Neg logit contributions
 corrid-0.227
acco-0.199
-0.198
2020-0.197
 retri-0.195
Tokenlist
Token ID4868
Feature activation-1.09e+00

Pos logit contributions
 Brune+0.133
 Haas+0.129
worthiness+0.129
 Dustin+0.125
 NYU+0.123
Neg logit contributions
 corrid-0.154
acco-0.135
-0.134
2020-0.133
 retri-0.132
Tokenenable
Token ID21633
Feature activation-8.23e-01

Pos logit contributions
 Brune+1.543
worthiness+1.491
 Haas+1.489
 Dustin+1.447
 NYU+1.419
Neg logit contributions
 corrid-1.722
-1.501
acco-1.472
GGGGGGGG-1.465
2020-1.465
Token as
Token ID355
Feature activation+3.14e-02

Pos logit contributions
 Brune+1.022
 Haas+0.982
worthiness+0.981
 Dustin+0.951
 NYU+0.927
Neg logit contributions
 corrid-1.438
acco-1.271
-1.260
2020-1.257
GGGGGGGG-1.236
Token a
Token ID257
Feature activation+1.28e-02

Pos logit contributions
 corrid+0.054
acco+0.048
+0.048
2020+0.047
 retri+0.047
Neg logit contributions
 Brune-0.040
 Haas-0.038
worthiness-0.038
 Dustin-0.037
 NYU-0.037
Token cohesive
Token ID42403
Feature activation-1.17e+00

Pos logit contributions
 corrid+0.021
acco+0.019
+0.019
2020+0.019
 retri+0.018
Neg logit contributions
 Brune-0.017
 Haas-0.016
worthiness-0.016
 Dustin-0.016
 NYU-0.016
Token record
Token ID1700
Feature activation+2.77e-01

Pos logit contributions
 Brune+1.492
 Haas+1.441
worthiness+1.419
 Dustin+1.403
 NYU+1.377
Neg logit contributions
 corrid-1.982
acco-1.782
2020-1.774
-1.760
GGGGGGGG-1.734
Tokenrose
Token ID13698
Feature activation+2.14e-01

Pos logit contributions
 Brune+0.370
worthiness+0.362
 Haas+0.361
 Dustin+0.351
 NYU+0.347
Neg logit contributions
 corrid-0.299
-0.244
acco-0.244
GGGGGGGG-0.242
2020-0.239
Token has
Token ID468
Feature activation+2.86e-01

Pos logit contributions
 corrid+0.378
acco+0.335
+0.334
2020+0.333
GGGGGGGG+0.327
Neg logit contributions
 Brune-0.263
 Haas-0.253
worthiness-0.250
 Dustin-0.246
 NYU-0.241
Token housed
Token ID23707
Feature activation+4.04e-01

Pos logit contributions
 corrid+0.480
+0.424
2020+0.424
acco+0.423
GGGGGGGG+0.414
Neg logit contributions
 Brune-0.378
 Haas-0.367
worthiness-0.361
 Dustin-0.355
 NYU-0.349
Token some
Token ID617
Feature activation+2.04e-01

Pos logit contributions
 corrid+0.683
acco+0.609
2020+0.605
+0.603
 retri+0.590
Neg logit contributions
 Brune-0.526
 Haas-0.507
worthiness-0.499
 Dustin-0.493
 NYU-0.483
Token exceptional
Token ID15313
Feature activation-4.28e-01

Pos logit contributions
 corrid+0.340
acco+0.300
+0.298
2020+0.298
 retri+0.293
Neg logit contributions
 Brune-0.269
 Haas-0.259
worthiness-0.258
 Dustin-0.251
 NYU-0.246
Token talent
Token ID7401
Feature activation-1.11e-01

Pos logit contributions
 Brune+0.565
 Haas+0.548
worthiness+0.533
 Dustin+0.529
 NYU+0.523
Neg logit contributions
 corrid-0.711
acco-0.640
2020-0.639
-0.636
GGGGGGGG-0.625
Token in
Token ID287
Feature activation+9.47e-02

Pos logit contributions
 Brune+0.137
 Haas+0.133
worthiness+0.131
 Dustin+0.128
 NYU+0.125
Neg logit contributions
 corrid-0.198
acco-0.175
-0.175
2020-0.174
GGGGGGGG-0.171
Token the
Token ID262
Feature activation+7.09e-02

Pos logit contributions
 corrid+0.158
acco+0.140
+0.139
2020+0.139
 retri+0.136
Neg logit contributions
 Brune-0.126
 Haas-0.121
worthiness-0.119
 Dustin-0.117
 NYU-0.115
Token past
Token ID1613
Feature activation+1.65e+00

Pos logit contributions
 corrid+0.105
acco+0.092
+0.091
2020+0.091
GGGGGGGG+0.089
Neg logit contributions
 Brune-0.107
 Haas-0.104
worthiness-0.102
 Dustin-0.101
 NYU-0.100
Token,
Token ID11
Feature activation+7.48e-02

Pos logit contributions
 corrid+2.755
acco+2.436
2020+2.416
+2.414
 retri+2.383
Neg logit contributions
 Brune-2.149
 Haas-2.070
worthiness-2.061
 Dustin-2.005
 NYU-1.971
Token including
Token ID1390
Feature activation+4.46e-01

Pos logit contributions
 corrid+0.120
acco+0.106
+0.105
2020+0.105
GGGGGGGG+0.102
Neg logit contributions
 Brune-0.105
 Haas-0.101
worthiness-0.100
 Dustin-0.099
 NYU-0.097
Token on
Token ID319
Feature activation-2.00e-01

Pos logit contributions
 corrid+0.649
acco+0.562
+0.557
2020+0.556
 retri+0.548
Neg logit contributions
 Brune-0.671
 Haas-0.650
worthiness-0.649
 Dustin-0.630
 NYU-0.623
Token that
Token ID326
Feature activation-8.87e-03

Pos logit contributions
 Brune+0.247
 Haas+0.238
worthiness+0.235
 Dustin+0.231
 NYU+0.226
Neg logit contributions
 corrid-0.353
acco-0.312
2020-0.311
-0.310
GGGGGGGG-0.304
Token program
Token ID1430
Feature activation+6.36e-01

Pos logit contributions
 Brune+0.011
 Haas+0.010
worthiness+0.010
 Dustin+0.010
 NYU+0.010
Neg logit contributions
 corrid-0.016
acco-0.014
2020-0.014
-0.014
GGGGGGGG-0.014
Token by
Token ID416
Feature activation-2.42e-02

Pos logit contributions
 corrid+1.003
acco+0.877
+0.871
2020+0.870
 retri+0.854
Neg logit contributions
 Brune-0.899
 Haas-0.869
worthiness-0.865
 Dustin-0.844
 NYU-0.830
Token Katie
Token ID24721
Feature activation-6.89e-01

Pos logit contributions
 Brune+0.028
 Haas+0.027
worthiness+0.027
 Dustin+0.026
 NYU+0.026
Neg logit contributions
 corrid-0.044
acco-0.039
-0.039
2020-0.039
 retri-0.038
Token Leigh
Token ID37907
Feature activation-2.01e+00

Pos logit contributions
 Brune+0.941
 Haas+0.912
worthiness+0.898
 Dustin+0.881
 NYU+0.865
Neg logit contributions
 corrid-1.132
acco-0.987
-0.984
2020-0.980
 retri-0.964
Token.
Token ID13
Feature activation-9.40e-02

Pos logit contributions
 Brune+2.599
 Haas+2.540
worthiness+2.442
 Dustin+2.427
 NYU+2.331
Neg logit contributions
 corrid-3.498
-3.042
acco-3.001
GGGGGGGG-2.998
2020-2.994
Token
Token ID198
Feature activation-5.42e-02

Pos logit contributions
 Brune+0.111
 Haas+0.108
worthiness+0.106
 Dustin+0.104
 NYU+0.102
Neg logit contributions
 corrid-0.174
acco-0.153
-0.151
2020-0.150
 retri-0.149
Token
Token ID198
Feature activation-4.62e-02

Pos logit contributions
 Brune+0.064
 Haas+0.061
worthiness+0.061
 Dustin+0.059
 NYU+0.058
Neg logit contributions
 corrid-0.099
acco-0.088
-0.087
2020-0.087
 retri-0.086
TokenJim
Token ID18050
Feature activation-2.71e-01

Pos logit contributions
 Brune+0.070
worthiness+0.068
 Haas+0.068
 Dustin+0.066
 NYU+0.065
Neg logit contributions
 corrid-0.069
acco-0.059
-0.058
2020-0.057
 retri-0.057
Token H
Token ID367
Feature activation+2.81e-01

Pos logit contributions
 Brune+0.345
 Haas+0.334
worthiness+0.331
 Dustin+0.322
 NYU+0.315
Neg logit contributions
 corrid-0.470
acco-0.411
-0.411
2020-0.409
GGGGGGGG-0.403
Token rescue
Token ID9992
Feature activation-1.86e-01

Pos logit contributions
 Brune+0.529
worthiness+0.518
 Haas+0.515
 Dustin+0.500
 NYU+0.493
Neg logit contributions
 corrid-0.616
acco-0.540
-0.535
GGGGGGGG-0.535
2020-0.529
Token mission
Token ID4365
Feature activation-8.42e-02

Pos logit contributions
 Brune+0.268
 Haas+0.261
worthiness+0.259
 Dustin+0.252
 NYU+0.248
Neg logit contributions
 corrid-0.289
acco-0.253
-0.251
2020-0.249
GGGGGGGG-0.247
Token that
Token ID326
Feature activation+1.23e-02

Pos logit contributions
 Brune+0.110
 Haas+0.107
worthiness+0.105
 Dustin+0.104
 NYU+0.102
Neg logit contributions
 corrid-0.144
acco-0.126
-0.125
2020-0.125
GGGGGGGG-0.123
Token ended
Token ID4444
Feature activation+3.90e-01

Pos logit contributions
 corrid+0.021
acco+0.018
+0.018
2020+0.018
GGGGGGGG+0.018
Neg logit contributions
 Brune-0.016
 Haas-0.016
worthiness-0.015
 Dustin-0.015
 NYU-0.015
Token with
Token ID351
Feature activation+2.37e-01

Pos logit contributions
 corrid+0.667
acco+0.590
+0.583
2020+0.583
 retri+0.572
Neg logit contributions
 Brune-0.505
 Haas-0.485
worthiness-0.482
 Dustin-0.473
 NYU-0.464
Token ign
Token ID3627
Feature activation-1.94e+00

Pos logit contributions
 corrid+0.420
acco+0.372
2020+0.370
+0.369
GGGGGGGG+0.362
Neg logit contributions
 Brune-0.294
 Haas-0.282
worthiness-0.278
 Dustin-0.274
 NYU-0.268
Tokenomin
Token ID6351
Feature activation+9.23e-01

Pos logit contributions
 Brune+1.814
worthiness+1.759
 Haas+1.693
 NYU+1.657
 Dustin+1.642
Neg logit contributions
 corrid-4.095
-3.563
龍喚士-3.561
GGGGGGGG-3.517
acco-3.487
Tokenious
Token ID699
Feature activation-2.81e-01

Pos logit contributions
 corrid+1.013
2020+0.874
acco+0.868
+0.849
 retri+0.833
Neg logit contributions
 Brune-1.703
 Haas-1.666
worthiness-1.647
 Dustin-1.623
 NYU-1.602
Token failure
Token ID5287
Feature activation-8.09e-02

Pos logit contributions
 Brune+0.391
 Haas+0.375
worthiness+0.374
 Dustin+0.367
 NYU+0.362
Neg logit contributions
 corrid-0.453
acco-0.397
2020-0.394
-0.394
GGGGGGGG-0.386
Token in
Token ID287
Feature activation-1.60e-01

Pos logit contributions
 Brune+0.088
worthiness+0.084
 Haas+0.084
 Dustin+0.081
 NYU+0.079
Neg logit contributions
 corrid-0.156
acco-0.138
2020-0.138
-0.137
GGGGGGGG-0.136
Token the
Token ID262
Feature activation-5.63e-02

Pos logit contributions
 Brune+0.181
 Haas+0.172
worthiness+0.169
 Dustin+0.166
 NYU+0.163
Neg logit contributions
 corrid-0.305
acco-0.271
-0.268
2020-0.268
GGGGGGGG-0.266
Token;
Token ID26
Feature activation-1.39e-01

Pos logit contributions
 Brune+1.814
 Haas+1.716
worthiness+1.700
 Dustin+1.658
 NYU+1.623
Neg logit contributions
 corrid-3.319
acco-2.951
-2.948
GGGGGGGG-2.910
2020-2.907
Token $
Token ID720
Feature activation+4.62e-01

Pos logit contributions
 Brune+0.129
 Haas+0.122
worthiness+0.121
 Dustin+0.117
 NYU+0.114
Neg logit contributions
 corrid-0.289
acco-0.261
-0.260
2020-0.259
 retri-0.256
Token30
Token ID1270
Feature activation+1.47e-01

Pos logit contributions
 corrid+0.596
acco+0.502
+0.495
2020+0.492
 retri+0.486
Neg logit contributions
 Brune-0.790
 Haas-0.768
worthiness-0.766
 Dustin-0.750
 NYU-0.740
Token for
Token ID329
Feature activation-1.18e-01

Pos logit contributions
 corrid+0.248
acco+0.218
+0.217
2020+0.216
GGGGGGGG+0.213
Neg logit contributions
 Brune-0.194
 Haas-0.186
worthiness-0.185
 Dustin-0.181
 NYU-0.178
Token shorter
Token ID12238
Feature activation-1.42e-01

Pos logit contributions
 Brune+0.159
 Haas+0.153
worthiness+0.151
 Dustin+0.149
 NYU+0.147
Neg logit contributions
 corrid-0.195
-0.172
acco-0.172
2020-0.171
GGGGGGGG-0.168
Token tours
Token ID21284
Feature activation-2.14e+00

Pos logit contributions
 Brune+0.099
 Haas+0.092
worthiness+0.091
 Dustin+0.087
 NYU+0.083
Neg logit contributions
 corrid-0.325
acco-0.297
-0.295
2020-0.295
 retri-0.292
Token throughout
Token ID3690
Feature activation-1.14e-01

Pos logit contributions
 Brune+2.332
worthiness+2.231
 Haas+2.204
 Dustin+2.183
 NYU+2.139
Neg logit contributions
 corrid-4.042
-3.579
acco-3.560
2020-3.526
GGGGGGGG-3.526
Token the
Token ID262
Feature activation-2.15e-02

Pos logit contributions
 Brune+0.148
 Haas+0.142
worthiness+0.142
 Dustin+0.138
 NYU+0.135
Neg logit contributions
 corrid-0.191
acco-0.169
2020-0.168
-0.168
 retri-0.165
Token day
Token ID1110
Feature activation-1.50e-01

Pos logit contributions
 Brune+0.033
 Haas+0.032
worthiness+0.032
 Dustin+0.031
 NYU+0.031
Neg logit contributions
 corrid-0.031
acco-0.027
-0.027
2020-0.027
 retri-0.026
Token).
Token ID737
Feature activation-5.49e-01

Pos logit contributions
 Brune+0.132
 Haas+0.124
worthiness+0.124
 Dustin+0.119
 NYU+0.116
Neg logit contributions
 corrid-0.317
acco-0.287
-0.286
2020-0.285
GGGGGGGG-0.281
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
 Brune+0.644
 Haas+0.621
worthiness+0.606
 Dustin+0.602
 NYU+0.588
Neg logit contributions
 corrid-1.026
acco-0.903
-0.893
 retri-0.887
2020-0.886
Token by
Token ID416
Feature activation+1.36e-01

Pos logit contributions
 corrid+0.608
acco+0.528
+0.523
2020+0.523
 retri+0.514
Neg logit contributions
 Brune-0.608
 Haas-0.589
worthiness-0.586
 Dustin-0.573
 NYU-0.564
Token Quake
Token ID42901
Feature activation-1.61e+00

Pos logit contributions
 corrid+0.239
acco+0.212
+0.211
2020+0.211
 retri+0.207
Neg logit contributions
 Brune-0.168
 Haas-0.162
worthiness-0.159
 Dustin-0.157
 NYU-0.153
TokenD
Token ID35
Feature activation-1.38e-01

Pos logit contributions
 Brune+2.257
 Haas+2.196
worthiness+2.178
 Dustin+2.124
 NYU+2.084
Neg logit contributions
 corrid-2.536
acco-2.173
-2.137
 retri-2.128
GGGGGGGG-2.119
Tokenude
Token ID2507
Feature activation-9.40e-01

Pos logit contributions
 Brune+0.178
 Haas+0.172
worthiness+0.170
 Dustin+0.167
 NYU+0.163
Neg logit contributions
 corrid-0.236
-0.206
acco-0.206
2020-0.204
 retri-0.203
Token from
Token ID422
Feature activation-2.25e-01

Pos logit contributions
 Brune+1.136
 Haas+1.092
worthiness+1.084
 Dustin+1.060
 NYU+1.037
Neg logit contributions
 corrid-1.681
acco-1.481
-1.457
 retri-1.450
龍喚士-1.441
Token Explosive
Token ID48178
Feature activation-1.84e+00

Pos logit contributions
 Brune+0.289
 Haas+0.278
worthiness+0.277
 Dustin+0.273
 NYU+0.265
Neg logit contributions
 corrid-0.386
acco-0.343
-0.340
2020-0.338
 retri-0.332
Token!!!!!!!!
Token ID34635
Feature activation+1.07e+00

Pos logit contributions
 Brune+2.280
 Haas+2.196
worthiness+2.162
 Dustin+2.146
 NYU+2.081
Neg logit contributions
 corrid-3.163
acco-2.802
-2.784
2020-2.754
-2.729
Token If
Token ID1002
Feature activation-2.13e-01

Pos logit contributions
 corrid+1.625
acco+1.415
+1.402
2020+1.401
 retri+1.377
Neg logit contributions
 Brune-1.571
 Haas-1.521
worthiness-1.514
 Dustin-1.480
 NYU-1.456
Token you
Token ID345
Feature activation+3.08e-02

Pos logit contributions
 Brune+0.246
 Haas+0.236
worthiness+0.234
 Dustin+0.231
 NYU+0.223
Neg logit contributions
 corrid-0.389
-0.348
acco-0.347
2020-0.345
 retri-0.340
Token give
Token ID1577
Feature activation-3.55e-01

Pos logit contributions
 corrid+0.054
+0.048
acco+0.047
2020+0.047
GGGGGGGG+0.047
Neg logit contributions
 Brune-0.039
worthiness-0.037
 Haas-0.037
 Dustin-0.036
 NYU-0.035
Token this
Token ID428
Feature activation-1.77e-01

Pos logit contributions
 Brune+0.440
 Haas+0.423
worthiness+0.422
 Dustin+0.413
 NYU+0.402
Neg logit contributions
 corrid-0.623
acco-0.551
-0.551
2020-0.548
GGGGGGGG-0.539
Token MEM
Token ID35153
Feature activation-1.30e+00

Pos logit contributions
 Brune+1.356
 Haas+1.306
worthiness+1.264
 Dustin+1.260
 NYU+1.239
Neg logit contributions
 corrid-1.997
acco-1.763
-1.752
2020-1.726
 retri-1.716
TokenOR
Token ID1581
Feature activation-8.37e-01

Pos logit contributions
 Brune+1.786
 Haas+1.717
worthiness+1.696
 Dustin+1.668
 NYU+1.650
Neg logit contributions
 corrid-2.152
acco-1.878
-1.834
 retri-1.822
2020-1.804
TokenIAL
Token ID12576
Feature activation-2.47e-01

Pos logit contributions
 Brune+1.234
 Haas+1.193
worthiness+1.175
 Dustin+1.157
 NYU+1.146
Neg logit contributions
 corrid-1.298
acco-1.113
-1.088
 retri-1.083
2020-1.075
Token L
Token ID406
Feature activation+2.35e-01

Pos logit contributions
 Brune+0.309
 Haas+0.298
worthiness+0.293
 Dustin+0.287
 NYU+0.284
Neg logit contributions
 corrid-0.434
acco-0.385
-0.380
2020-0.378
 retri-0.374
TokenECT
Token ID9782
Feature activation-6.14e-01

Pos logit contributions
 corrid+0.325
acco+0.275
+0.273
2020+0.271
 retri+0.270
Neg logit contributions
 Brune-0.381
 Haas-0.370
worthiness-0.367
 Dustin-0.361
 NYU-0.356
TokenURE
Token ID11335
Feature activation-1.86e+00

Pos logit contributions
 Brune+0.647
 Haas+0.615
worthiness+0.608
 Dustin+0.597
 NYU+0.584
Neg logit contributions
 corrid-1.207
acco-1.077
-1.062
2020-1.054
 retri-1.052
Token
Token ID198
Feature activation-4.36e-01

Pos logit contributions
 Brune+2.257
 Haas+2.171
 Dustin+2.104
worthiness+2.100
 NYU+2.080
Neg logit contributions
 corrid-3.343
acco-2.965
-2.920
 retri-2.860
2020-2.848
Token
Token ID198
Feature activation-4.88e-01

Pos logit contributions
 Brune+0.500
 Haas+0.479
worthiness+0.477
 Dustin+0.464
 NYU+0.454
Neg logit contributions
 corrid-0.813
acco-0.720
-0.709
2020-0.708
 retri-0.707
Tokenin
Token ID259
Feature activation-3.60e-01

Pos logit contributions
 Brune+0.712
worthiness+0.689
 Haas+0.687
 Dustin+0.673
 NYU+0.662
Neg logit contributions
 corrid-0.752
acco-0.646
-0.631
 retri-0.629
GGGGGGGG-0.626
Token Mumbai
Token ID22917
Feature activation-1.49e+00

Pos logit contributions
 Brune+0.460
 Haas+0.440
worthiness+0.436
 Dustin+0.428
 NYU+0.419
Neg logit contributions
 corrid-0.620
acco-0.549
-0.546
2020-0.544
 retri-0.536
Token
Token ID5595
Feature activation-6.75e-01

Pos logit contributions
 Brune+1.770
 Haas+1.705
worthiness+1.643
 Dustin+1.639
 NYU+1.619
Neg logit contributions
 corrid-2.698
acco-2.389
-2.369
2020-2.320
 retri-2.317