TOP ACTIVATIONS
MAX = 12.402

that the usual Elect rom agnetic field
somewhere : REF LECT _ CLASS _ ST ART
. Elect a Draper : 303 -
е е о� ь и н
- born Turk named Ali Kent . The two had taken
, and her mom is Cant ones e . And she
AP G - 83 Active Elect ron ically Sc anned Array
о� е е ),
oub 2005 Jason Bat eman 2005 Zach
at your first stop , Kent uck Kn ob in rural
copying , or redistribution ( elect ronic or otherwise , including
с о о� и е с
pass statues of champions Betty C uth bert , Don
? A : Fort y years ago , 40
1995 Boots Pharmaceutical s pressures Betty Dong to withdraw a paper
. A US 14 Jonathan Cant well ( Team Sax o
squirrel s would gen uf lect before the nut , she
child is transgender , society inst ills in them rules about
Baldwin 2013 Jason Bat eman 2013 Louis
what he calls elect oral itis .

MIN ACTIVATIONS
MIN = -12.144

matter . <|endoftext|> R amon Hare wood met with
down with Gohan ? <|endoftext|> R ents still have the potential
dirty . <|endoftext|> R USE LL : What I
First posted <|endoftext|> R aj k ot : In
the End Around . <|endoftext|> R ape by fraud : What
more <|endoftext|> About R acing Apex is a fast
16 , violence erupted in Roh t ak city which continued
Senior advocate Muk ul Roh at gi appearing for Gh
Sen . Jeff Flake ( R - Ari z .) after
( SD ) R SS ( HD ) |
by blocking national highway connecting Roh t ak to Delhi .
att u and C K Pr as ad also pulled up
a long time ." <|endoftext|> Oil from a wrecked tanker is
. <|endoftext|> Name : MSI R 78 70 Hawk
started at Sam pl a Roh t ak by blocking national
flagged off between Sar ai Roh illa station in Delhi to
, Senator Ted Cruz ( R - TX ), who apparently
economic recovery . R ates were expected to rise
multiplayer mayhem . R acing Apex is targeting Windows
K lim enty ev / R IA Nov ost i /

INTERVAL 6.265 - 12.402
CONTAINS 0.623%

Oak sterdam , a how - to about opening and running
how I had failed to realize this in the very beginning
-, five -, and ten - cent pieces of an alloy
; the Vin cci La Plant aci ón del Sur on
For more information on O VD - Info , read this

INTERVAL 0.129 - 6.265
CONTAINS 46.040%

create a reason for her termination .
is that the documents may reveal the kinds of pressure the
We pay for your stories ! Do you have a story
[ feel ] a little bit like a spinning cup at
a little fir mer in texture . Sun flower

INTERVAL -6.008 - 0.129
CONTAINS 52.708%

isn t just full of Typh on . There
to say Yes to life , no
a sc uffle , with Hew ett getting hit in the
Things started to become confusing here for two reasons .
exceptions , public reaction was swift and harsh . The D

INTERVAL -12.144 - -6.008
CONTAINS 0.629%

M asure , R . H ., Al lee
rest ants . Par le pr és ent act e ,
city . This series of blog posts is an introduction to
ort ic otrop in - re leasing factor ( CR F
I refer to R alph , the
Token that
Token ID326
Feature activation+4.99e-01

Pos logit contributions
lehem+2.736
RON+2.583
rans+2.547
rons+2.489
enance+2.460
Neg logit contributions
jriwal-2.405
kefeller-2.213
 impulse-2.103
 turmoil-1.960
 reaction-1.913
Token the
Token ID262
Feature activation+4.09e-01

Pos logit contributions
lehem+0.491
RON+0.461
rans+0.452
rons+0.441
enance+0.438
Neg logit contributions
jriwal-0.430
kefeller-0.394
 impulse-0.381
 turmoil-0.359
 reaction-0.352
Token usual
Token ID6678
Feature activation+1.97e+00

Pos logit contributions
lehem+0.435
RON+0.411
rans+0.403
rons+0.395
enance+0.392
Neg logit contributions
jriwal-0.321
kefeller-0.291
 impulse-0.280
 turmoil-0.262
 reaction-0.256
Token
Token ID564
Feature activation+5.09e+00

Pos logit contributions
lehem+2.014
RON+1.910
rans+1.870
rons+1.845
enance+1.821
Neg logit contributions
jriwal-1.603
kefeller-1.471
 impulse-1.388
 turmoil-1.306
 reaction-1.261
Token
Token ID246
Feature activation-2.95e+00

Pos logit contributions
lehem+3.086
RON+2.887
rans+2.827
rons+2.662
enance+2.654
Neg logit contributions
jriwal-6.150
kefeller-5.844
 impulse-5.612
 turmoil-5.420
 reaction-5.299
TokenElect
Token ID19453
Feature activation+1.24e+01

Pos logit contributions
jriwal+2.918
kefeller+2.687
 impulse+2.666
 turmoil+2.536
 reaction+2.510
Neg logit contributions
lehem-2.478
RON-2.284
rans-2.201
rons-2.164
enance-2.153
Tokenrom
Token ID398
Feature activation-2.90e+00

Pos logit contributions
lehem+10.653
RON+10.292
rons+9.973
rans+9.854
enance+9.348
Neg logit contributions
jriwal-10.804
kefeller-10.555
 impulse-9.769
 turmoil-9.242
senal-9.124
Tokenagnetic
Token ID25145
Feature activation-1.64e+00

Pos logit contributions
jriwal+2.718
kefeller+2.507
 impulse+2.472
 turmoil+2.340
 reaction+2.296
Neg logit contributions
lehem-2.596
RON-2.422
rans-2.341
rons-2.297
enance-2.294
Token field
Token ID2214
Feature activation+2.47e+00

Pos logit contributions
jriwal+1.307
kefeller+1.187
 impulse+1.154
 turmoil+1.083
 reaction+1.058
Neg logit contributions
lehem-1.727
RON-1.629
rans-1.594
rons-1.562
enance-1.550
Token
Token ID447
Feature activation-1.75e+00

Pos logit contributions
lehem+2.411
RON+2.271
rans+2.237
rons+2.197
enance+2.172
Neg logit contributions
jriwal-2.127
kefeller-1.963
 impulse-1.860
 turmoil-1.752
 reaction-1.696
Token
Token ID247
Feature activation-1.26e+00

Pos logit contributions
jriwal+2.033
kefeller+1.899
 impulse+1.875
 turmoil+1.797
 reaction+1.774
Neg logit contributions
lehem-1.199
RON-1.085
rans-1.048
rons-1.018
enance-0.998
Token somewhere
Token ID7382
Feature activation+3.88e+00

Pos logit contributions
lehem+0.762
RON+0.718
rans+0.704
rons+0.690
enance+0.682
Neg logit contributions
jriwal-0.605
kefeller-0.556
 impulse-0.535
 turmoil-0.506
 reaction-0.490
Token:
Token ID25
Feature activation+1.15e+00

Pos logit contributions
lehem+3.847
RON+3.602
rans+3.566
rons+3.437
enance+3.398
Neg logit contributions
jriwal-3.229
kefeller-3.039
 impulse-2.864
 turmoil-2.716
 reaction-2.624
Token
Token ID198
Feature activation+3.45e-01

Pos logit contributions
lehem+1.055
RON+0.985
rans+0.962
rons+0.936
enance+0.927
Neg logit contributions
jriwal-1.071
kefeller-0.989
 impulse-0.959
 turmoil-0.913
 reaction-0.891
Token
Token ID198
Feature activation+5.09e-01

Pos logit contributions
lehem+0.310
RON+0.293
rans+0.285
rons+0.278
enance+0.276
Neg logit contributions
jriwal-0.328
kefeller-0.302
 impulse-0.293
 turmoil-0.278
 reaction-0.271
TokenREF
Token ID31688
Feature activation-3.23e+00

Pos logit contributions
lehem+0.436
RON+0.407
rans+0.397
rons+0.384
enance+0.380
Neg logit contributions
jriwal-0.505
kefeller-0.470
 impulse-0.458
 turmoil-0.436
 reaction-0.427
TokenLECT
Token ID16779
Feature activation+1.21e+01

Pos logit contributions
jriwal+3.288
kefeller+3.037
 impulse+3.016
 turmoil+2.855
 reaction+2.817
Neg logit contributions
lehem-2.620
RON-2.405
rans-2.341
rons-2.294
enance-2.281
Token_
Token ID62
Feature activation+1.85e+00

Pos logit contributions
RON+10.382
lehem+10.236
rons+9.468
rans+9.443
enance+9.151
Neg logit contributions
jriwal-10.707
kefeller-10.098
 impulse-9.279
 turmoil-9.070
inki-8.868
TokenCLASS
Token ID31631
Feature activation+7.23e+00

Pos logit contributions
lehem+1.642
RON+1.545
rans+1.496
rons+1.456
enance+1.438
Neg logit contributions
jriwal-1.785
kefeller-1.647
 impulse-1.603
 turmoil-1.528
 reaction-1.490
Token_
Token ID62
Feature activation+1.72e+00

Pos logit contributions
lehem+6.190
RON+5.956
rans+5.728
rons+5.619
enance+5.400
Neg logit contributions
jriwal-6.817
kefeller-6.369
 impulse-5.965
 turmoil-5.745
senal-5.611
TokenST
Token ID2257
Feature activation+2.68e+00

Pos logit contributions
lehem+1.519
RON+1.430
rans+1.385
rons+1.347
enance+1.331
Neg logit contributions
jriwal-1.658
kefeller-1.533
 impulse-1.492
 turmoil-1.420
 reaction-1.388
TokenART
Token ID7227
Feature activation+3.20e+00

Pos logit contributions
lehem+2.241
RON+2.112
rans+2.053
rons+1.990
enance+1.957
Neg logit contributions
jriwal-2.710
kefeller-2.513
 impulse-2.437
 turmoil-2.328
 reaction-2.282
Token.
Token ID13
Feature activation+3.40e-01

Pos logit contributions
jriwal+0.783
kefeller+0.711
 impulse+0.693
 turmoil+0.650
 reaction+0.636
Neg logit contributions
lehem-1.008
RON-0.951
rans-0.930
rons-0.911
enance-0.904
Token
Token ID447
Feature activation-1.90e+00

Pos logit contributions
lehem+0.314
RON+0.294
rans+0.287
rons+0.280
enance+0.278
Neg logit contributions
jriwal-0.314
kefeller-0.290
 impulse-0.282
 turmoil-0.267
 reaction-0.261
Token
Token ID251
Feature activation+4.12e+00

Pos logit contributions
jriwal+2.094
kefeller+1.952
 impulse+1.923
 turmoil+1.843
 reaction+1.815
Neg logit contributions
lehem-1.408
RON-1.289
rans-1.250
rons-1.222
enance-1.196
Token
Token ID198
Feature activation+1.63e-02

Pos logit contributions
lehem+3.578
RON+3.382
rans+3.279
rons+3.186
enance+3.171
Neg logit contributions
jriwal-3.940
kefeller-3.693
 impulse-3.532
 turmoil-3.339
 reaction-3.248
Token
Token ID198
Feature activation+1.36e-01

Pos logit contributions
lehem+0.015
RON+0.014
rans+0.014
rons+0.013
enance+0.013
Neg logit contributions
jriwal-0.015
kefeller-0.014
 impulse-0.014
 turmoil-0.013
 reaction-0.013
TokenElect
Token ID19453
Feature activation+1.20e+01

Pos logit contributions
lehem+0.118
RON+0.111
rans+0.107
rons+0.105
enance+0.104
Neg logit contributions
jriwal-0.133
kefeller-0.123
 impulse-0.120
 turmoil-0.114
 reaction-0.112
Tokena
Token ID64
Feature activation+1.50e+00

Pos logit contributions
lehem+9.610
RON+9.432
rons+9.023
rans+8.948
enance+8.437
Neg logit contributions
jriwal-11.224
kefeller-10.888
 impulse-10.308
senal-9.681
 turmoil-9.633
Token Draper
Token ID48575
Feature activation+3.93e-01

Pos logit contributions
lehem+1.425
RON+1.335
rans+1.303
rons+1.274
enance+1.261
Neg logit contributions
jriwal-1.346
kefeller-1.237
 impulse-1.204
 turmoil-1.134
 reaction-1.109
Token:
Token ID25
Feature activation+5.13e-01

Pos logit contributions
lehem+0.389
RON+0.366
rans+0.358
rons+0.350
enance+0.347
Neg logit contributions
jriwal-0.336
kefeller-0.308
 impulse-0.299
 turmoil-0.281
 reaction-0.275
Token 303
Token ID30727
Feature activation-1.50e+00

Pos logit contributions
lehem+0.478
RON+0.450
rans+0.440
rons+0.429
enance+0.424
Neg logit contributions
jriwal-0.466
kefeller-0.430
 impulse-0.417
 turmoil-0.392
 reaction-0.383
Token-
Token ID12
Feature activation+5.83e+00

Pos logit contributions
jriwal+1.087
kefeller+0.976
 impulse+0.945
 turmoil+0.878
 reaction+0.852
Neg logit contributions
lehem-1.672
RON-1.592
rans-1.560
rons-1.531
enance-1.517
Tokenе
Token ID16843
Feature activation-7.08e-01

Pos logit contributions
lehem+3.291
RON+3.021
rans+2.917
rons+2.817
enance+2.764
Neg logit contributions
jriwal-6.326
kefeller-5.946
 impulse-5.710
 turmoil-5.503
 reaction-5.397
Tokenе
Token ID16843
Feature activation-6.70e-01

Pos logit contributions
jriwal+0.705
kefeller+0.650
 impulse+0.641
 turmoil+0.610
 reaction+0.601
Neg logit contributions
lehem-0.599
RON-0.557
rans-0.541
rons-0.528
enance-0.525
Token
Token ID12466
Feature activation+4.64e-01

Pos logit contributions
jriwal+0.652
kefeller+0.601
 impulse+0.592
 turmoil+0.562
 reaction+0.553
Neg logit contributions
lehem-0.582
RON-0.542
rans-0.527
rons-0.514
enance-0.511
Token
Token ID109
Feature activation+5.49e+00

Pos logit contributions
lehem+0.389
RON+0.362
rans+0.353
rons+0.343
enance+0.339
Neg logit contributions
jriwal-0.468
kefeller-0.436
 impulse-0.424
 turmoil-0.404
 reaction-0.396
Tokenо�
Token ID25443
Feature activation-4.07e+00

Pos logit contributions
lehem+2.993
RON+2.697
rans+2.628
rons+2.493
enance+2.402
Neg logit contributions
jriwal-7.063
kefeller-6.662
 impulse-6.497
 turmoil-6.250
 reaction-6.159
Token
Token ID119
Feature activation+1.16e+01

Pos logit contributions
jriwal+4.571
kefeller+4.237
 impulse+4.222
 turmoil+4.066
 reaction+3.997
Neg logit contributions
lehem-2.820
RON-2.581
rans-2.481
rons-2.427
enance-2.394
Tokenь
Token ID45367
Feature activation+1.07e+00

Pos logit contributions
lehem+6.037
RON+5.362
rans+5.233
rons+4.894
enance+4.853
Neg logit contributions
jriwal-14.259
kefeller-13.499
 impulse-13.077
 turmoil-12.476
 reaction-12.277
Token
Token ID141
Feature activation+2.73e+00

Pos logit contributions
lehem+0.734
RON+0.668
rans+0.647
rons+0.622
enance+0.614
Neg logit contributions
jriwal-1.249
kefeller-1.173
 impulse-1.145
 turmoil-1.096
 reaction-1.079
Token
Token ID230
Feature activation+4.10e-01

Pos logit contributions
lehem+1.953
RON+1.799
rans+1.742
rons+1.686
enance+1.670
Neg logit contributions
jriwal-3.082
kefeller-2.887
 impulse-2.809
 turmoil-2.687
 reaction-2.652
Tokenи
Token ID18849
Feature activation-6.70e+00

Pos logit contributions
lehem+0.263
RON+0.238
rans+0.230
rons+0.222
enance+0.219
Neg logit contributions
jriwal-0.494
kefeller-0.464
 impulse-0.456
 turmoil-0.438
 reaction-0.432
Tokenн
Token ID22177
Feature activation+1.61e+00

Pos logit contributions
jriwal+7.253
 impulse+6.742
kefeller+6.683
 turmoil+6.502
 reaction+6.433
Neg logit contributions
lehem-4.761
RON-4.327
enance-4.100
rans-4.096
rons-4.017
Token-
Token ID12
Feature activation+6.70e+00

Pos logit contributions
jriwal+1.988
kefeller+1.805
 impulse+1.766
 turmoil+1.655
 reaction+1.625
Neg logit contributions
lehem-2.697
RON-2.548
rans-2.487
rons-2.453
enance-2.428
Tokenborn
Token ID6286
Feature activation+3.61e+00

Pos logit contributions
lehem+5.976
rans+5.693
RON+5.575
rons+5.245
enance+5.174
Neg logit contributions
jriwal-6.286
kefeller-5.702
 impulse-5.583
 turmoil-5.252
 reaction-5.074
Token Turk
Token ID8484
Feature activation-7.91e-01

Pos logit contributions
lehem+3.633
RON+3.416
rans+3.379
enance+3.284
rons+3.249
Neg logit contributions
jriwal-2.995
kefeller-2.732
 impulse-2.563
 turmoil-2.410
senal-2.360
Token named
Token ID3706
Feature activation+1.53e+00

Pos logit contributions
jriwal+0.681
kefeller+0.623
 impulse+0.606
 turmoil+0.572
 reaction+0.559
Neg logit contributions
lehem-0.779
RON-0.731
rans-0.717
rons-0.699
enance-0.693
Token Ali
Token ID12104
Feature activation-2.28e-01

Pos logit contributions
lehem+1.427
RON+1.334
rans+1.301
rons+1.269
enance+1.263
Neg logit contributions
jriwal-1.409
kefeller-1.294
 impulse-1.259
 turmoil-1.191
 reaction-1.161
Token Kent
Token ID8758
Feature activation+1.14e+01

Pos logit contributions
jriwal+0.206
kefeller+0.189
 impulse+0.185
 turmoil+0.175
 reaction+0.171
Neg logit contributions
lehem-0.215
RON-0.201
rans-0.196
rons-0.192
enance-0.190
Token.
Token ID13
Feature activation+5.07e-01

Pos logit contributions
lehem+10.091
rans+9.650
RON+9.270
rons+9.184
enance+9.042
Neg logit contributions
jriwal-9.725
kefeller-9.080
 impulse-9.042
 turmoil-8.419
senal-8.246
Token The
Token ID383
Feature activation+1.76e-01

Pos logit contributions
lehem+0.456
RON+0.426
rans+0.415
rons+0.406
enance+0.402
Neg logit contributions
jriwal-0.477
kefeller-0.440
 impulse-0.431
 turmoil-0.410
 reaction-0.403
Token two
Token ID734
Feature activation+7.35e-01

Pos logit contributions
lehem+0.181
RON+0.171
rans+0.168
rons+0.164
enance+0.163
Neg logit contributions
jriwal-0.143
kefeller-0.130
 impulse-0.126
 turmoil-0.118
 reaction-0.115
Token had
Token ID550
Feature activation+2.16e+00

Pos logit contributions
lehem+0.718
RON+0.675
rans+0.661
rons+0.646
enance+0.640
Neg logit contributions
jriwal-0.638
kefeller-0.584
 impulse-0.568
 turmoil-0.536
 reaction-0.524
Token taken
Token ID2077
Feature activation-2.17e+00

Pos logit contributions
lehem+2.197
RON+2.089
rans+2.057
rons+2.019
enance+2.000
Neg logit contributions
jriwal-1.756
kefeller-1.596
 impulse-1.522
 turmoil-1.432
 reaction-1.392
Token,
Token ID11
Feature activation+2.24e-01

Pos logit contributions
jriwal+2.342
kefeller+2.126
 impulse+2.080
 turmoil+1.960
 reaction+1.923
Neg logit contributions
lehem-3.002
RON-2.825
rans-2.755
rons-2.708
enance-2.688
Token and
Token ID290
Feature activation-2.47e+00

Pos logit contributions
lehem+0.227
RON+0.214
rans+0.211
rons+0.205
enance+0.203
Neg logit contributions
jriwal-0.187
kefeller-0.170
 impulse-0.164
 turmoil-0.154
 reaction-0.150
Token her
Token ID607
Feature activation+8.00e-01

Pos logit contributions
jriwal+2.008
kefeller+1.825
 impulse+1.793
 turmoil+1.691
 reaction+1.658
Neg logit contributions
lehem-2.541
RON-2.391
rans-2.324
rons-2.283
enance-2.270
Token mom
Token ID1995
Feature activation-9.10e-01

Pos logit contributions
lehem+0.893
RON+0.852
rans+0.836
rons+0.819
enance+0.813
Neg logit contributions
jriwal-0.581
kefeller-0.525
 impulse-0.496
 turmoil-0.462
 reaction-0.445
Token is
Token ID318
Feature activation-1.82e+00

Pos logit contributions
jriwal+0.726
kefeller+0.658
 impulse+0.641
 turmoil+0.602
 reaction+0.589
Neg logit contributions
lehem-0.954
RON-0.899
rans-0.879
rons-0.862
enance-0.855
Token Cant
Token ID16821
Feature activation+1.13e+01

Pos logit contributions
jriwal+1.569
kefeller+1.435
 impulse+1.402
 turmoil+1.322
 reaction+1.296
Neg logit contributions
lehem-1.797
RON-1.688
rans-1.646
rons-1.612
enance-1.599
Tokenones
Token ID1952
Feature activation-7.75e-01

Pos logit contributions
rans+5.402
lehem+5.366
RON+4.889
rons+4.870
enance+4.343
Neg logit contributions
jriwal-14.261
kefeller-13.464
 impulse-12.908
senal-12.779
 indictment-12.506
Tokene
Token ID68
Feature activation-1.14e+00

Pos logit contributions
jriwal+1.039
kefeller+0.981
 impulse+0.968
 turmoil+0.935
 reaction+0.924
Neg logit contributions
lehem-0.390
RON-0.344
rans-0.325
rons-0.312
enance-0.305
Token.
Token ID13
Feature activation+4.51e-01

Pos logit contributions
jriwal+0.945
kefeller+0.862
 impulse+0.839
 turmoil+0.788
 reaction+0.770
Neg logit contributions
lehem-1.151
RON-1.084
rans-1.061
rons-1.038
enance-1.030
Token And
Token ID843
Feature activation+6.39e-01

Pos logit contributions
lehem+0.423
RON+0.397
rans+0.387
rons+0.378
enance+0.375
Neg logit contributions
jriwal-0.408
kefeller-0.375
 impulse-0.366
 turmoil-0.346
 reaction-0.340
Token she
Token ID673
Feature activation+2.94e+00

Pos logit contributions
lehem+0.630
RON+0.593
rans+0.583
rons+0.570
enance+0.563
Neg logit contributions
jriwal-0.551
kefeller-0.505
 impulse-0.486
 turmoil-0.457
 reaction-0.446
Token AP
Token ID3486
Feature activation-1.90e+00

Pos logit contributions
jriwal+2.075
kefeller+1.910
 impulse+1.871
 turmoil+1.772
 reaction+1.739
Neg logit contributions
lehem-2.072
RON-1.934
rans-1.890
rons-1.842
enance-1.830
TokenG
Token ID38
Feature activation-1.57e+00

Pos logit contributions
jriwal+1.736
kefeller+1.595
 impulse+1.551
 turmoil+1.470
 reaction+1.440
Neg logit contributions
lehem-1.774
RON-1.666
rans-1.620
rons-1.588
enance-1.568
Token-
Token ID12
Feature activation+4.57e+00

Pos logit contributions
jriwal+1.260
kefeller+1.146
 impulse+1.119
 turmoil+1.049
 reaction+1.027
Neg logit contributions
lehem-1.629
RON-1.532
rans-1.500
rons-1.467
enance-1.461
Token83
Token ID5999
Feature activation+3.79e+00

Pos logit contributions
lehem+3.455
RON+3.321
rans+3.146
rons+3.084
enance+3.000
Neg logit contributions
jriwal-4.882
kefeller-4.594
 impulse-4.430
 turmoil-4.258
 reaction-4.158
Token Active
Token ID14199
Feature activation+1.35e+00

Pos logit contributions
lehem+3.602
RON+3.496
rans+3.349
rons+3.332
enance+3.200
Neg logit contributions
jriwal-3.322
kefeller-3.043
 impulse-2.844
 turmoil-2.739
 reaction-2.637
Token Elect
Token ID5903
Feature activation+1.13e+01

Pos logit contributions
lehem+1.299
RON+1.246
rans+1.200
rons+1.188
enance+1.163
Neg logit contributions
jriwal-1.198
kefeller-1.098
 impulse-1.045
 turmoil-1.000
 reaction-0.965
Tokenron
Token ID1313
Feature activation-2.15e+00

Pos logit contributions
lehem+7.585
rons+7.556
RON+7.514
rans+7.048
enance+6.601
Neg logit contributions
jriwal-11.985
kefeller-11.939
 impulse-11.197
 turmoil-10.855
 indictment-10.761
Tokenically
Token ID1146
Feature activation-1.37e+00

Pos logit contributions
jriwal+1.908
kefeller+1.750
 impulse+1.715
 turmoil+1.618
 reaction+1.590
Neg logit contributions
lehem-2.052
RON-1.919
rans-1.876
rons-1.830
enance-1.820
Token Sc
Token ID1446
Feature activation-5.13e-01

Pos logit contributions
jriwal+1.248
kefeller+1.148
 impulse+1.122
 turmoil+1.062
 reaction+1.042
Neg logit contributions
lehem-1.277
RON-1.194
rans-1.165
rons-1.139
enance-1.130
Tokenanned
Token ID3577
Feature activation+5.29e-01

Pos logit contributions
jriwal+0.524
kefeller+0.486
 impulse+0.476
 turmoil+0.453
 reaction+0.446
Neg logit contributions
lehem-0.423
RON-0.392
rans-0.380
rons-0.370
enance-0.367
Token Array
Token ID15690
Feature activation+2.47e+00

Pos logit contributions
lehem+0.500
RON+0.476
rans+0.464
rons+0.457
enance+0.449
Neg logit contributions
jriwal-0.477
kefeller-0.438
 impulse-0.418
 turmoil-0.399
 reaction-0.386
Token
Token ID12466
Feature activation+3.56e-01

Pos logit contributions
lehem+0.518
RON+0.481
rans+0.468
rons+0.456
enance+0.450
Neg logit contributions
jriwal-0.636
kefeller-0.592
 impulse-0.576
 turmoil-0.548
 reaction-0.539
Token
Token ID116
Feature activation-2.40e+00

Pos logit contributions
lehem+0.306
RON+0.285
rans+0.278
rons+0.271
enance+0.268
Neg logit contributions
jriwal-0.352
kefeller-0.326
 impulse-0.318
 turmoil-0.302
 reaction-0.297
Token
Token ID12466
Feature activation+3.45e-01

Pos logit contributions
jriwal+2.458
kefeller+2.278
 impulse+2.246
 turmoil+2.143
 reaction+2.109
Neg logit contributions
lehem-1.964
RON-1.811
rans-1.759
rons-1.714
enance-1.700
Token
Token ID109
Feature activation+5.10e+00

Pos logit contributions
lehem+0.280
RON+0.260
rans+0.253
rons+0.246
enance+0.243
Neg logit contributions
jriwal-0.357
kefeller-0.332
 impulse-0.324
 turmoil-0.309
 reaction-0.303
Tokenо�
Token ID25443
Feature activation-4.32e+00

Pos logit contributions
lehem+2.977
RON+2.708
rans+2.632
rons+2.527
enance+2.451
Neg logit contributions
jriwal-6.393
kefeller-6.012
 impulse-5.847
 turmoil-5.609
 reaction-5.534
Token
Token ID119
Feature activation+1.12e+01

Pos logit contributions
jriwal+4.500
 impulse+4.160
kefeller+4.147
 turmoil+3.994
 reaction+3.923
Neg logit contributions
lehem-3.306
RON-3.031
rans-2.937
rons-2.876
enance-2.842
Tokenе
Token ID16843
Feature activation-1.00e+00

Pos logit contributions
lehem+6.349
RON+5.977
rans+5.789
rons+5.511
enance+5.275
Neg logit contributions
jriwal-13.437
kefeller-12.695
 impulse-12.171
 turmoil-11.517
senal-11.426
Tokenе
Token ID16843
Feature activation-9.10e-01

Pos logit contributions
jriwal+1.111
kefeller+1.036
 impulse+1.021
 turmoil+0.978
 reaction+0.964
Neg logit contributions
lehem-0.729
RON-0.668
rans-0.647
rons-0.628
enance-0.624
Token),
Token ID828
Feature activation+2.29e+00

Pos logit contributions
jriwal+0.962
kefeller+0.893
 impulse+0.879
 turmoil+0.840
 reaction+0.827
Neg logit contributions
lehem-0.715
RON-0.659
rans-0.640
rons-0.622
enance-0.618
Token
Token ID12466
Feature activation+4.32e-01

Pos logit contributions
lehem+1.947
RON+1.812
rans+1.774
rons+1.718
enance+1.693
Neg logit contributions
jriwal-2.289
kefeller-2.130
 impulse-2.049
 turmoil-1.952
 reaction-1.907
Token
Token ID121
Feature activation+7.13e+00

Pos logit contributions
lehem+0.362
RON+0.337
rans+0.329
rons+0.319
enance+0.315
Neg logit contributions
jriwal-0.435
kefeller-0.405
 impulse-0.394
 turmoil-0.375
 reaction-0.368
Tokenoub
Token ID12944
Feature activation+7.10e-01

Pos logit contributions
jriwal+1.361
kefeller+1.241
 impulse+1.209
 turmoil+1.138
 reaction+1.114
Neg logit contributions
lehem-1.621
RON-1.525
rans-1.488
rons-1.459
enance-1.446
Token
Token ID198
Feature activation-3.90e-01

Pos logit contributions
lehem+0.626
RON+0.593
rans+0.578
rons+0.563
enance+0.560
Neg logit contributions
jriwal-0.685
kefeller-0.632
 impulse-0.611
 turmoil-0.578
senal-0.568
Token
Token ID198
Feature activation-2.07e-01

Pos logit contributions
jriwal+0.360
kefeller+0.331
 impulse+0.323
 turmoil+0.306
 reaction+0.300
Neg logit contributions
lehem-0.361
RON-0.338
rans-0.330
rons-0.322
enance-0.320
Token2005
Token ID14315
Feature activation+1.52e+00

Pos logit contributions
jriwal+0.240
kefeller+0.226
 impulse+0.221
 turmoil+0.212
 reaction+0.209
Neg logit contributions
lehem-0.142
RON-0.131
rans-0.126
rons-0.121
enance-0.120
Token Jason
Token ID8982
Feature activation+5.23e-01

Pos logit contributions
lehem+1.500
RON+1.415
rans+1.376
rons+1.353
enance+1.337
Neg logit contributions
jriwal-1.307
kefeller-1.191
 impulse-1.155
 turmoil-1.083
 reaction-1.057
Token Bat
Token ID6577
Feature activation+1.10e+01

Pos logit contributions
lehem+0.473
RON+0.444
rans+0.436
rons+0.425
enance+0.419
Neg logit contributions
jriwal-0.493
kefeller-0.451
 impulse-0.438
 turmoil-0.414
 reaction-0.405
Tokeneman
Token ID8463
Feature activation+3.95e-01

Pos logit contributions
lehem+9.883
rans+9.468
rons+9.412
RON+9.184
enance+9.155
Neg logit contributions
jriwal-9.358
kefeller-8.672
 impulse-8.478
senal-7.737
 turmoil-7.732
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
lehem+0.363
RON+0.339
rans+0.332
rons+0.323
enance+0.321
Neg logit contributions
jriwal-0.367
kefeller-0.338
 impulse-0.329
 turmoil-0.311
 reaction-0.305
Token
Token ID198
Feature activation-1.90e-01

Pos logit contributions
jriwal+0.296
kefeller+0.272
 impulse+0.265
 turmoil+0.251
 reaction+0.246
Neg logit contributions
lehem-0.291
RON-0.274
rans-0.267
rons-0.260
enance-0.258
Token2005
Token ID14315
Feature activation+1.32e+00

Pos logit contributions
jriwal+0.218
kefeller+0.204
 impulse+0.200
 turmoil+0.192
 reaction+0.189
Neg logit contributions
lehem-0.133
RON-0.121
rans-0.117
rons-0.113
enance-0.112
Token Zach
Token ID18825
Feature activation+7.94e+00

Pos logit contributions
lehem+1.291
RON+1.216
rans+1.181
rons+1.161
enance+1.147
Neg logit contributions
jriwal-1.151
kefeller-1.049
 impulse-1.018
 turmoil-0.955
 reaction-0.931
Token at
Token ID379
Feature activation+1.30e+00

Pos logit contributions
lehem+1.634
RON+1.528
rans+1.505
rons+1.473
enance+1.450
Neg logit contributions
jriwal-1.439
kefeller-1.318
 impulse-1.277
 turmoil-1.211
 reaction-1.174
Token your
Token ID534
Feature activation-4.25e-01

Pos logit contributions
lehem+1.263
RON+1.186
rans+1.160
rons+1.135
enance+1.122
Neg logit contributions
jriwal-1.129
kefeller-1.030
 impulse-1.001
 turmoil-0.948
 reaction-0.924
Token first
Token ID717
Feature activation-3.56e+00

Pos logit contributions
jriwal+0.318
kefeller+0.287
 impulse+0.276
 turmoil+0.259
 reaction+0.252
Neg logit contributions
lehem-0.466
RON-0.442
rans-0.432
rons-0.425
enance-0.421
Token stop
Token ID2245
Feature activation+3.10e-01

Pos logit contributions
jriwal+3.179
 impulse+2.968
kefeller+2.952
 reaction+2.751
 turmoil+2.748
Neg logit contributions
lehem-3.306
RON-3.084
rans-3.005
rons-2.938
enance-2.921
Token,
Token ID11
Feature activation-8.46e-01

Pos logit contributions
lehem+0.317
RON+0.298
rans+0.292
rons+0.286
enance+0.283
Neg logit contributions
jriwal-0.257
kefeller-0.234
 impulse-0.227
 turmoil-0.214
 reaction-0.209
Token Kent
Token ID8758
Feature activation+1.09e+01

Pos logit contributions
jriwal+0.723
kefeller+0.663
 impulse+0.646
 turmoil+0.609
 reaction+0.597
Neg logit contributions
lehem-0.836
RON-0.786
rans-0.768
rons-0.751
enance-0.746
Tokenuck
Token ID1347
Feature activation+1.45e+00

Pos logit contributions
lehem+9.911
rans+9.233
RON+9.109
rons+8.999
enance+8.655
Neg logit contributions
jriwal-9.686
kefeller-8.779
 impulse-8.473
 turmoil-8.065
 reaction-7.730
Token Kn
Token ID6102
Feature activation-2.01e+00

Pos logit contributions
lehem+1.137
RON+1.051
rans+1.027
rons+0.993
enance+0.987
Neg logit contributions
jriwal-1.534
kefeller-1.432
 impulse-1.394
 turmoil-1.330
 reaction-1.305
Tokenob
Token ID672
Feature activation-9.47e-01

Pos logit contributions
jriwal+1.816
kefeller+1.671
 impulse+1.628
 turmoil+1.540
 reaction+1.511
Neg logit contributions
lehem-1.888
RON-1.768
rans-1.722
rons-1.683
enance-1.672
Token in
Token ID287
Feature activation-4.09e+00

Pos logit contributions
jriwal+0.816
kefeller+0.747
 impulse+0.728
 turmoil+0.687
 reaction+0.673
Neg logit contributions
lehem-0.932
RON-0.876
rans-0.855
rons-0.837
enance-0.830
Token rural
Token ID10016
Feature activation-2.19e+00

Pos logit contributions
jriwal+3.607
kefeller+3.346
 impulse+3.285
 turmoil+3.118
 reaction+3.073
Neg logit contributions
lehem-3.841
RON-3.620
rans-3.525
rons-3.430
enance-3.418
Token copying
Token ID23345
Feature activation-2.09e+00

Pos logit contributions
jriwal+0.451
kefeller+0.409
 impulse+0.389
 turmoil+0.363
 reaction+0.351
Neg logit contributions
lehem-0.669
RON-0.633
rans-0.624
rons-0.605
enance-0.604
Token,
Token ID11
Feature activation-6.23e-01

Pos logit contributions
jriwal+1.711
kefeller+1.548
 impulse+1.533
 turmoil+1.440
 reaction+1.414
Neg logit contributions
lehem-2.125
RON-2.003
rans-1.954
rons-1.921
enance-1.897
Token or
Token ID393
Feature activation-2.65e+00

Pos logit contributions
jriwal+0.508
kefeller+0.464
 impulse+0.446
 turmoil+0.420
 reaction+0.410
Neg logit contributions
lehem-0.644
RON-0.607
rans-0.596
rons-0.579
enance-0.576
Token redistribution
Token ID41425
Feature activation-2.12e+00

Pos logit contributions
jriwal+1.982
kefeller+1.786
 impulse+1.743
 turmoil+1.628
 reaction+1.588
Neg logit contributions
lehem-2.901
RON-2.742
rans-2.680
rons-2.639
enance-2.616
Token (
Token ID357
Feature activation+1.90e+00

Pos logit contributions
jriwal+1.747
kefeller+1.578
 impulse+1.560
 turmoil+1.465
 reaction+1.440
Neg logit contributions
lehem-2.159
RON-2.030
rans-1.976
rons-1.945
enance-1.921
Tokenelect
Token ID9509
Feature activation+1.09e+01

Pos logit contributions
lehem+1.445
RON+1.342
rans+1.303
rons+1.253
enance+1.242
Neg logit contributions
jriwal-2.063
kefeller-1.929
 impulse-1.882
 turmoil-1.799
 reaction-1.765
Tokenronic
Token ID4565
Feature activation-9.94e-01

Pos logit contributions
lehem+5.886
RON+5.727
rans+5.305
rons+5.159
enance+4.795
Neg logit contributions
jriwal-13.320
kefeller-13.042
 impulse-12.421
 turmoil-11.981
senal-11.869
Token or
Token ID393
Feature activation-2.41e+00

Pos logit contributions
jriwal+0.870
kefeller+0.797
 impulse+0.778
 turmoil+0.734
 reaction+0.720
Neg logit contributions
lehem-0.964
RON-0.905
rans-0.884
rons-0.865
enance-0.858
Token otherwise
Token ID4306
Feature activation-4.28e-01

Pos logit contributions
jriwal+2.122
kefeller+1.946
 impulse+1.905
 turmoil+1.796
 reaction+1.763
Neg logit contributions
lehem-2.320
RON-2.175
rans-2.122
rons-2.080
enance-2.059
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
jriwal+0.407
kefeller+0.376
 impulse+0.367
 turmoil+0.348
 reaction+0.341
Neg logit contributions
lehem-0.383
RON-0.358
rans-0.349
rons-0.340
enance-0.338
Token including
Token ID1390
Feature activation+3.12e+00

Pos logit contributions
jriwal+0.229
kefeller+0.208
 impulse+0.201
 turmoil+0.189
 reaction+0.184
Neg logit contributions
lehem-0.297
RON-0.280
rans-0.275
rons-0.268
enance-0.267
Tokenс
Token ID21727
Feature activation-1.14e+00

Pos logit contributions
lehem+0.606
RON+0.561
rans+0.542
rons+0.524
enance+0.519
Neg logit contributions
jriwal-0.920
kefeller-0.860
 impulse-0.840
 turmoil-0.804
 reaction-0.789
Tokenо
Token ID15166
Feature activation-3.46e+00

Pos logit contributions
jriwal+1.347
kefeller+1.264
 impulse+1.244
 turmoil+1.197
 reaction+1.181
Neg logit contributions
lehem-0.744
RON-0.675
rans-0.652
rons-0.631
enance-0.625
Token
Token ID12466
Feature activation-3.13e-01

Pos logit contributions
jriwal+3.942
kefeller+3.662
 impulse+3.660
 turmoil+3.510
 reaction+3.478
Neg logit contributions
lehem-2.358
RON-2.150
rans-2.052
enance-2.011
rons-2.004
Token
Token ID118
Feature activation-1.29e+00

Pos logit contributions
jriwal+0.313
kefeller+0.291
 impulse+0.284
 turmoil+0.270
 reaction+0.265
Neg logit contributions
lehem-0.265
RON-0.246
rans-0.240
rons-0.234
enance-0.231
Tokenо�
Token ID25443
Feature activation-4.71e+00

Pos logit contributions
jriwal+1.651
kefeller+1.557
 impulse+1.538
 turmoil+1.480
 reaction+1.465
Neg logit contributions
lehem-0.718
RON-0.636
rans-0.609
rons-0.584
enance-0.576
Token
Token ID119
Feature activation+1.08e+01

Pos logit contributions
jriwal+4.753
 impulse+4.399
kefeller+4.364
 turmoil+4.187
 reaction+4.123
Neg logit contributions
lehem-3.777
RON-3.485
rans-3.358
rons-3.290
enance-3.259
Tokenи
Token ID18849
Feature activation-7.44e+00

Pos logit contributions
lehem+6.253
RON+5.989
rans+5.692
rons+5.474
enance+5.309
Neg logit contributions
jriwal-12.942
kefeller-12.150
 impulse-11.558
 turmoil-10.972
senal-10.878
Token
Token ID141
Feature activation+2.06e+00

Pos logit contributions
jriwal+7.764
 impulse+7.336
kefeller+7.225
 turmoil+7.013
 reaction+6.983
Neg logit contributions
lehem-5.351
RON-4.839
rans-4.664
enance-4.606
rons-4.556
Token
Token ID229
Feature activation+1.88e+00

Pos logit contributions
lehem+1.366
RON+1.245
rans+1.202
rons+1.161
enance+1.145
Neg logit contributions
jriwal-2.446
kefeller-2.295
 impulse-2.238
 turmoil-2.150
 reaction-2.118
Tokenе
Token ID16843
Feature activation-1.53e+00

Pos logit contributions
lehem+1.247
RON+1.142
rans+1.107
rons+1.071
enance+1.053
Neg logit contributions
jriwal-2.236
kefeller-2.093
 impulse-2.037
 turmoil-1.960
 reaction-1.927
Tokenс
Token ID21727
Feature activation-9.18e-01

Pos logit contributions
jriwal+1.443
kefeller+1.322
 impulse+1.312
 turmoil+1.245
 reaction+1.227
Neg logit contributions
lehem-1.375
RON-1.279
rans-1.244
rons-1.212
enance-1.209
Token pass
Token ID1208
Feature activation-3.94e-01

Pos logit contributions
lehem+3.206
RON+3.025
rans+2.969
rons+2.907
enance+2.879
Neg logit contributions
jriwal-2.900
kefeller-2.667
 impulse-2.581
 turmoil-2.443
 reaction-2.373
Token statues
Token ID25827
Feature activation+7.88e-02

Pos logit contributions
jriwal+0.316
kefeller+0.287
 impulse+0.279
 turmoil+0.262
 reaction+0.255
Neg logit contributions
lehem-0.410
RON-0.387
rans-0.379
rons-0.371
enance-0.369
Token of
Token ID286
Feature activation+1.44e+00

Pos logit contributions
lehem+0.077
RON+0.072
rans+0.070
rons+0.069
enance+0.068
Neg logit contributions
jriwal-0.069
kefeller-0.063
 impulse-0.061
 turmoil-0.058
 reaction-0.057
Token champions
Token ID7827
Feature activation+3.95e+00

Pos logit contributions
lehem+1.456
RON+1.376
rans+1.344
rons+1.316
enance+1.309
Neg logit contributions
jriwal-1.202
kefeller-1.097
 impulse-1.061
 turmoil-0.996
 reaction-0.973
Token
Token ID784
Feature activation+1.71e+00

Pos logit contributions
lehem+3.982
RON+3.749
rans+3.688
rons+3.619
enance+3.604
Neg logit contributions
jriwal-3.251
kefeller-3.015
 impulse-2.872
 turmoil-2.665
 reaction-2.590
Token Betty
Token ID29504
Feature activation+1.07e+01

Pos logit contributions
lehem+1.728
RON+1.630
rans+1.592
rons+1.559
enance+1.545
Neg logit contributions
jriwal-1.428
kefeller-1.303
 impulse-1.260
 turmoil-1.180
 reaction-1.152
Token C
Token ID327
Feature activation+1.01e+00

Pos logit contributions
lehem+9.970
RON+9.212
rans+9.106
rons+9.065
enance+8.826
Neg logit contributions
jriwal-9.356
kefeller-8.396
 impulse-8.160
senal-7.679
 turmoil-7.581
Tokenuth
Token ID1071
Feature activation+3.26e+00

Pos logit contributions
lehem+0.941
RON+0.876
rans+0.857
rons+0.839
enance+0.834
Neg logit contributions
jriwal-0.932
kefeller-0.858
 impulse-0.837
 turmoil-0.792
 reaction-0.771
Tokenbert
Token ID4835
Feature activation+4.86e+00

Pos logit contributions
lehem+3.516
RON+3.329
rans+3.302
rons+3.226
enance+3.193
Neg logit contributions
jriwal-2.502
kefeller-2.244
 impulse-2.181
 turmoil-2.044
 reaction-1.985
Token,
Token ID11
Feature activation-6.61e-01

Pos logit contributions
lehem+4.692
RON+4.389
rans+4.323
rons+4.238
enance+4.215
Neg logit contributions
jriwal-4.228
kefeller-3.859
 impulse-3.763
 turmoil-3.500
 reaction-3.403
Token Don
Token ID2094
Feature activation-7.94e-01

Pos logit contributions
jriwal+0.584
kefeller+0.535
 impulse+0.522
 turmoil+0.493
 reaction+0.483
Neg logit contributions
lehem-0.637
RON-0.598
rans-0.584
rons-0.571
enance-0.566
Token?
Token ID30
Feature activation+1.26e-01

Pos logit contributions
lehem+1.832
RON+1.720
rans+1.697
rons+1.645
enance+1.634
Neg logit contributions
jriwal-2.080
kefeller-1.938
 impulse-1.877
 turmoil-1.763
 reaction-1.727
Token
Token ID198
Feature activation+5.11e-02

Pos logit contributions
lehem+0.115
RON+0.108
rans+0.105
rons+0.103
enance+0.102
Neg logit contributions
jriwal-0.117
kefeller-0.108
 impulse-0.105
 turmoil-0.100
 reaction-0.098
Token
Token ID198
Feature activation+1.68e-01

Pos logit contributions
lehem+0.047
RON+0.044
rans+0.043
rons+0.042
enance+0.041
Neg logit contributions
jriwal-0.048
kefeller-0.044
 impulse-0.043
 turmoil-0.041
 reaction-0.040
TokenA
Token ID32
Feature activation+1.37e+00

Pos logit contributions
lehem+0.129
RON+0.119
rans+0.116
rons+0.113
enance+0.111
Neg logit contributions
jriwal-0.180
kefeller-0.168
 impulse-0.165
 turmoil-0.158
 reaction-0.155
Token:
Token ID25
Feature activation+9.31e-01

Pos logit contributions
lehem+1.221
RON+1.159
rans+1.129
rons+1.091
enance+1.087
Neg logit contributions
jriwal-1.303
kefeller-1.206
 impulse-1.168
 turmoil-1.103
senal-1.083
TokenFort
Token ID21926
Feature activation+1.07e+01

Pos logit contributions
lehem+0.791
RON+0.742
rans+0.720
rons+0.699
enance+0.692
Neg logit contributions
jriwal-0.929
kefeller-0.862
 impulse-0.840
 turmoil-0.797
 reaction-0.783
Tokeny
Token ID88
Feature activation+3.22e+00

Pos logit contributions
lehem+8.539
rans+8.457
RON+8.045
rons+7.797
enance+7.746
Neg logit contributions
jriwal-10.094
kefeller-9.229
 impulse-8.826
 turmoil-8.469
senal-8.410
Token years
Token ID812
Feature activation+2.09e+00

Pos logit contributions
lehem+3.205
RON+3.053
rans+3.000
rons+2.923
enance+2.844
Neg logit contributions
jriwal-2.692
kefeller-2.469
 impulse-2.347
 turmoil-2.192
 reaction-2.122
Token ago
Token ID2084
Feature activation+2.71e+00

Pos logit contributions
lehem+1.889
RON+1.754
rans+1.716
rons+1.673
enance+1.655
Neg logit contributions
jriwal-1.967
kefeller-1.838
 impulse-1.761
 turmoil-1.666
 reaction-1.633
Token,
Token ID11
Feature activation+4.40e-02

Pos logit contributions
lehem+2.587
RON+2.458
rans+2.400
rons+2.335
enance+2.319
Neg logit contributions
jriwal-2.396
kefeller-2.211
 impulse-2.101
 turmoil-1.968
 reaction-1.920
Token 40
Token ID2319
Feature activation+5.51e+00

Pos logit contributions
lehem+0.045
RON+0.043
rans+0.042
rons+0.041
enance+0.041
Neg logit contributions
jriwal-0.036
kefeller-0.033
 impulse-0.032
 turmoil-0.030
 reaction-0.029
Token1995
Token ID21908
Feature activation+3.35e+00

Pos logit contributions
jriwal+0.047
kefeller+0.044
 impulse+0.043
 turmoil+0.041
 reaction+0.040
Neg logit contributions
lehem-0.032
RON-0.030
rans-0.029
rons-0.028
enance-0.028
Token Boots
Token ID28807
Feature activation+1.74e+00

Pos logit contributions
lehem+3.016
RON+2.865
rans+2.774
rons+2.713
enance+2.670
Neg logit contributions
jriwal-3.154
kefeller-2.859
 impulse-2.790
 turmoil-2.612
 reaction-2.566
Token Pharmaceutical
Token ID37175
Feature activation-4.19e+00

Pos logit contributions
lehem+1.723
RON+1.635
rans+1.612
rons+1.581
enance+1.545
Neg logit contributions
jriwal-1.474
kefeller-1.339
 impulse-1.299
 turmoil-1.196
 reaction-1.152
Tokens
Token ID82
Feature activation-2.94e+00

Pos logit contributions
jriwal+4.850
kefeller+4.553
 impulse+4.490
 turmoil+4.320
 reaction+4.283
Neg logit contributions
lehem-2.854
RON-2.533
rans-2.469
enance-2.352
rons-2.351
Token pressures
Token ID18895
Feature activation-4.35e+00

Pos logit contributions
jriwal+2.446
kefeller+2.239
 impulse+2.193
 turmoil+2.074
 reaction+2.030
Neg logit contributions
lehem-2.976
RON-2.780
rans-2.719
rons-2.651
enance-2.638
Token Betty
Token ID29504
Feature activation+1.07e+01

Pos logit contributions
jriwal+3.431
kefeller+3.137
 impulse+3.084
 turmoil+2.900
 reaction+2.849
Neg logit contributions
lehem-4.557
RON-4.275
rans-4.164
rons-4.096
enance-4.050
Token Dong
Token ID28831
Feature activation+7.70e-01

Pos logit contributions
lehem+9.558
RON+8.790
rans+8.768
rons+8.689
enance+8.290
Neg logit contributions
jriwal-9.721
kefeller-8.640
 impulse-8.336
senal-7.855
 turmoil-7.823
Token to
Token ID284
Feature activation+7.43e-01

Pos logit contributions
lehem+0.803
RON+0.761
rans+0.750
rons+0.734
enance+0.723
Neg logit contributions
jriwal-0.619
kefeller-0.559
 impulse-0.544
 turmoil-0.510
 reaction-0.493
Token withdraw
Token ID8399
Feature activation+2.51e+00

Pos logit contributions
lehem+0.732
RON+0.694
rans+0.680
rons+0.666
enance+0.659
Neg logit contributions
jriwal-0.635
kefeller-0.579
 impulse-0.558
 turmoil-0.526
 reaction-0.514
Token a
Token ID257
Feature activation+6.24e-01

Pos logit contributions
lehem+2.727
RON+2.614
rans+2.562
enance+2.530
rons+2.510
Neg logit contributions
jriwal-1.864
kefeller-1.678
 impulse-1.582
 turmoil-1.469
inki-1.418
Token paper
Token ID3348
Feature activation-1.46e+00

Pos logit contributions
lehem+0.704
RON+0.672
rans+0.659
rons+0.645
enance+0.641
Neg logit contributions
jriwal-0.446
kefeller-0.398
 impulse-0.381
 turmoil-0.353
 reaction-0.340
Token.
Token ID13
Feature activation+9.07e-01

Pos logit contributions
lehem+3.528
RON+3.434
rans+3.355
enance+3.251
rons+3.237
Neg logit contributions
jriwal-3.648
kefeller-3.312
senal-3.196
 impulse-3.180
 tiss-3.066
Token A
Token ID317
Feature activation+1.39e+00

Pos logit contributions
lehem+0.776
RON+0.725
rans+0.704
rons+0.686
enance+0.678
Neg logit contributions
jriwal-0.904
kefeller-0.835
 impulse-0.812
 turmoil-0.771
 reaction-0.756
TokenUS
Token ID2937
Feature activation+6.26e-01

Pos logit contributions
lehem+1.290
RON+1.230
rans+1.189
rons+1.157
enance+1.146
Neg logit contributions
jriwal-1.270
kefeller-1.166
 impulse-1.135
 turmoil-1.071
 reaction-1.048
Token 14
Token ID1478
Feature activation+1.18e+00

Pos logit contributions
lehem+0.530
RON+0.493
rans+0.480
rons+0.467
enance+0.463
Neg logit contributions
jriwal-0.626
kefeller-0.581
 impulse-0.567
 turmoil-0.538
 reaction-0.529
Token Jonathan
Token ID11232
Feature activation-2.54e+00

Pos logit contributions
lehem+1.119
RON+1.058
rans+1.025
rons+1.004
enance+0.994
Neg logit contributions
jriwal-1.066
kefeller-0.973
 impulse-0.942
 turmoil-0.886
 reaction-0.862
Token Cant
Token ID16821
Feature activation+1.07e+01

Pos logit contributions
jriwal+2.278
kefeller+2.083
 impulse+2.035
 turmoil+1.921
 reaction+1.881
Neg logit contributions
lehem-2.416
RON-2.265
rans-2.216
rons-2.166
enance-2.145
Tokenwell
Token ID4053
Feature activation+2.54e+00

Pos logit contributions
lehem+8.384
rans+7.863
rons+7.689
enance+7.582
uate+7.524
Neg logit contributions
jriwal-10.758
kefeller-9.812
 impulse-9.540
senal-9.297
 turmoil-8.994
Token (
Token ID357
Feature activation+1.54e+00

Pos logit contributions
lehem+2.186
RON+2.037
rans+1.983
rons+1.938
enance+1.918
Neg logit contributions
jriwal-2.499
kefeller-2.309
 impulse-2.261
 turmoil-2.146
 reaction-2.097
TokenTeam
Token ID15592
Feature activation+3.02e+00

Pos logit contributions
lehem+1.228
RON+1.161
rans+1.117
rons+1.084
enance+1.068
Neg logit contributions
jriwal-1.618
kefeller-1.498
 impulse-1.463
 turmoil-1.392
 reaction-1.362
Token Sax
Token ID29242
Feature activation+4.13e+00

Pos logit contributions
lehem+2.819
RON+2.669
rans+2.602
rons+2.539
enance+2.503
Neg logit contributions
jriwal-2.767
kefeller-2.536
 impulse-2.448
 turmoil-2.307
 reaction-2.240
Tokeno
Token ID78
Feature activation-4.35e+00

Pos logit contributions
lehem+2.527
RON+2.385
rans+2.378
enance+2.215
rons+2.203
Neg logit contributions
jriwal-5.064
kefeller-4.704
 impulse-4.487
 turmoil-4.314
 reaction-4.237
Token squirrel
Token ID33039
Feature activation+2.53e+00

Pos logit contributions
lehem+0.243
RON+0.229
rans+0.224
rons+0.220
enance+0.218
Neg logit contributions
jriwal-0.183
kefeller-0.166
 impulse-0.161
 turmoil-0.151
 reaction-0.147
Tokens
Token ID82
Feature activation-8.79e-01

Pos logit contributions
lehem+2.084
RON+1.945
rans+1.890
rons+1.858
enance+1.830
Neg logit contributions
jriwal-2.562
kefeller-2.385
 impulse-2.294
 turmoil-2.194
 reaction-2.142
Token would
Token ID561
Feature activation-2.82e-01

Pos logit contributions
jriwal+0.777
kefeller+0.712
 impulse+0.704
 turmoil+0.664
 reaction+0.654
Neg logit contributions
lehem-0.842
RON-0.788
rans-0.766
rons-0.748
enance-0.738
Token gen
Token ID2429
Feature activation+3.52e+00

Pos logit contributions
jriwal+0.238
kefeller+0.216
 impulse+0.214
 turmoil+0.201
 reaction+0.197
Neg logit contributions
lehem-0.283
RON-0.265
rans-0.258
rons-0.253
enance-0.251
Tokenuf
Token ID3046
Feature activation+5.16e+00

Pos logit contributions
lehem+2.938
rans+2.755
RON+2.742
rons+2.635
enance+2.605
Neg logit contributions
jriwal-3.491
kefeller-3.246
 impulse-3.126
 turmoil-3.007
 reaction-2.908
Tokenlect
Token ID801
Feature activation+1.06e+01

Pos logit contributions
lehem+3.800
RON+3.662
rans+3.617
rons+3.507
enance+3.449
Neg logit contributions
jriwal-5.505
kefeller-5.110
 impulse-4.991
 turmoil-4.797
senal-4.775
Token before
Token ID878
Feature activation-1.62e-01

Pos logit contributions
lehem+9.858
enance+9.487
RON+9.399
rons+9.274
rans+9.216
Neg logit contributions
jriwal-8.657
kefeller-7.960
senal-7.314
 impulse-7.009
inki-6.906
Token the
Token ID262
Feature activation+2.14e-01

Pos logit contributions
jriwal+0.126
kefeller+0.115
 impulse+0.112
 turmoil+0.104
 reaction+0.102
Neg logit contributions
lehem-0.172
RON-0.162
rans-0.159
rons-0.155
enance-0.154
Token nut
Token ID6701
Feature activation+2.53e+00

Pos logit contributions
lehem+0.235
RON+0.222
rans+0.218
rons+0.214
enance+0.212
Neg logit contributions
jriwal-0.161
kefeller-0.145
 impulse-0.140
 turmoil-0.131
 reaction-0.128
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
lehem+2.513
RON+2.378
rans+2.328
rons+2.301
enance+2.253
Neg logit contributions
jriwal-2.152
kefeller-1.964
 impulse-1.884
 turmoil-1.779
 reaction-1.727
Token she
Token ID673
Feature activation+3.36e+00

Pos logit contributions
jriwal+0.149
kefeller+0.136
 impulse+0.132
 turmoil+0.124
 reaction+0.121
Neg logit contributions
lehem-0.174
RON-0.163
rans-0.160
rons-0.156
enance-0.155
Token child
Token ID1200
Feature activation+6.07e+00

Pos logit contributions
lehem+0.199
RON+0.189
rans+0.186
rons+0.182
enance+0.181
Neg logit contributions
jriwal-0.123
kefeller-0.111
 impulse-0.106
 turmoil-0.098
 reaction-0.095
Token is
Token ID318
Feature activation-1.83e+00

Pos logit contributions
lehem+5.225
rans+4.951
RON+4.932
rons+4.754
enance+4.685
Neg logit contributions
jriwal-5.821
kefeller-5.429
 impulse-5.012
senal-4.866
 turmoil-4.753
Token transgender
Token ID10637
Feature activation-1.71e+00

Pos logit contributions
jriwal+1.427
kefeller+1.293
 impulse+1.257
 turmoil+1.177
 reaction+1.150
Neg logit contributions
lehem-1.945
RON-1.836
rans-1.797
rons-1.762
enance-1.748
Token,
Token ID11
Feature activation-2.91e-01

Pos logit contributions
jriwal+1.424
kefeller+1.295
 impulse+1.274
 turmoil+1.203
 reaction+1.178
Neg logit contributions
lehem-1.716
RON-1.617
rans-1.572
rons-1.540
enance-1.533
Token society
Token ID3592
Feature activation+1.44e+00

Pos logit contributions
jriwal+0.247
kefeller+0.226
 impulse+0.219
 turmoil+0.207
 reaction+0.202
Neg logit contributions
lehem-0.291
RON-0.274
rans-0.268
rons-0.262
enance-0.260
Token inst
Token ID916
Feature activation+1.06e+01

Pos logit contributions
lehem+1.418
RON+1.337
rans+1.314
rons+1.285
enance+1.275
Neg logit contributions
jriwal-1.242
kefeller-1.139
 impulse-1.093
 turmoil-1.031
 reaction-1.004
Tokenills
Token ID2171
Feature activation-1.77e-01

Pos logit contributions
lehem+8.913
rans+8.776
rons+8.420
RON+8.382
enance+8.358
Neg logit contributions
jriwal-9.506
kefeller-8.927
 impulse-8.657
 turmoil-8.015
senal-7.989
Token in
Token ID287
Feature activation-2.87e+00

Pos logit contributions
jriwal+0.136
kefeller+0.123
 impulse+0.120
 turmoil+0.112
 reaction+0.110
Neg logit contributions
lehem-0.191
RON-0.180
rans-0.177
rons-0.173
enance-0.172
Token them
Token ID606
Feature activation+2.76e+00

Pos logit contributions
jriwal+2.548
kefeller+2.343
 impulse+2.324
 turmoil+2.194
 reaction+2.167
Neg logit contributions
lehem-2.728
RON-2.544
rans-2.454
rons-2.411
enance-2.388
Token rules
Token ID3173
Feature activation-1.99e+00

Pos logit contributions
lehem+2.834
RON+2.687
rans+2.656
rons+2.591
enance+2.576
Neg logit contributions
jriwal-2.231
kefeller-2.035
 impulse-1.900
 turmoil-1.781
senal-1.758
Token about
Token ID546
Feature activation+1.47e+00

Pos logit contributions
jriwal+1.532
kefeller+1.385
 impulse+1.349
 turmoil+1.263
 reaction+1.234
Neg logit contributions
lehem-2.131
RON-2.012
rans-1.968
rons-1.930
enance-1.915
Token Baldwin
Token ID26402
Feature activation+6.66e+00

Pos logit contributions
lehem+2.542
RON+2.273
rans+2.133
enance+2.020
rons+1.983
Neg logit contributions
jriwal-9.152
kefeller-8.551
 impulse-8.476
senal-8.333
 tiss-8.202
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
lehem+4.887
RON+4.816
rans+4.688
rons+4.542
enance+4.523
Neg logit contributions
jriwal-7.001
kefeller-6.527
senal-6.316
 impulse-6.157
 tiss-6.141
Token
Token ID198
Feature activation-2.96e-02

Pos logit contributions
jriwal+0.124
kefeller+0.114
 impulse+0.111
 turmoil+0.105
 reaction+0.103
Neg logit contributions
lehem-0.121
RON-0.114
rans-0.111
rons-0.109
enance-0.108
Token2013
Token ID6390
Feature activation-6.89e-01

Pos logit contributions
jriwal+0.028
kefeller+0.026
 impulse+0.026
 turmoil+0.024
 reaction+0.024
Neg logit contributions
lehem-0.026
RON-0.025
rans-0.024
rons-0.024
enance-0.023
Token Jason
Token ID8982
Feature activation+3.02e-01

Pos logit contributions
jriwal+0.597
kefeller+0.545
 impulse+0.531
 turmoil+0.501
 reaction+0.490
Neg logit contributions
lehem-0.677
RON-0.636
rans-0.621
rons-0.608
enance-0.603
Token Bat
Token ID6577
Feature activation+1.06e+01

Pos logit contributions
lehem+0.311
RON+0.293
rans+0.287
rons+0.281
enance+0.279
Neg logit contributions
jriwal-0.247
kefeller-0.225
 impulse-0.219
 turmoil-0.205
 reaction-0.200
Tokeneman
Token ID8463
Feature activation+4.17e-01

Pos logit contributions
lehem+8.949
rans+8.764
rons+8.685
RON+8.636
enance+8.564
Neg logit contributions
jriwal-9.086
senal-8.878
 impulse-8.486
kefeller-8.437
 tiss-8.340
Token
Token ID198
Feature activation-2.33e-01

Pos logit contributions
lehem+0.393
RON+0.368
rans+0.360
rons+0.351
enance+0.349
Neg logit contributions
jriwal-0.377
kefeller-0.347
 impulse-0.338
 turmoil-0.319
 reaction-0.312
Token
Token ID198
Feature activation-1.23e-01

Pos logit contributions
jriwal+0.217
kefeller+0.200
 impulse+0.195
 turmoil+0.184
 reaction+0.180
Neg logit contributions
lehem-0.213
RON-0.200
rans-0.195
rons-0.191
enance-0.189
Token2013
Token ID6390
Feature activation-7.67e-01

Pos logit contributions
jriwal+0.118
kefeller+0.109
 impulse+0.106
 turmoil+0.100
 reaction+0.098
Neg logit contributions
lehem-0.109
RON-0.103
rans-0.100
rons-0.097
enance-0.097
Token Louis
Token ID5593
Feature activation+7.58e-01

Pos logit contributions
jriwal+0.648
kefeller+0.591
 impulse+0.576
 turmoil+0.542
 reaction+0.530
Neg logit contributions
lehem-0.768
RON-0.723
rans-0.706
rons-0.691
enance-0.686
Token what
Token ID644
Feature activation-1.79e+00

Pos logit contributions
jriwal+0.699
kefeller+0.636
 impulse+0.618
 turmoil+0.581
 reaction+0.567
Neg logit contributions
lehem-0.889
RON-0.838
rans-0.820
rons-0.803
enance-0.798
Token he
Token ID339
Feature activation+2.50e+00

Pos logit contributions
jriwal+1.555
kefeller+1.426
 impulse+1.393
 turmoil+1.314
 reaction+1.288
Neg logit contributions
lehem-1.750
RON-1.642
rans-1.601
rons-1.569
enance-1.555
Token calls
Token ID3848
Feature activation-1.68e+00

Pos logit contributions
lehem+2.379
RON+2.243
rans+2.223
rons+2.158
enance+2.138
Neg logit contributions
jriwal-2.214
kefeller-2.038
 impulse-1.951
 turmoil-1.847
 reaction-1.800
Token
Token ID564
Feature activation+4.14e+00

Pos logit contributions
jriwal+1.364
kefeller+1.242
 impulse+1.210
 turmoil+1.136
 reaction+1.112
Neg logit contributions
lehem-1.735
RON-1.634
rans-1.599
rons-1.568
enance-1.553
Token
Token ID250
Feature activation+1.99e+00

Pos logit contributions
lehem+2.511
RON+2.316
rans+2.238
enance+2.114
rons+2.094
Neg logit contributions
jriwal-5.075
kefeller-4.786
 impulse-4.654
 turmoil-4.483
 reaction-4.415
Tokenelect
Token ID9509
Feature activation+1.06e+01

Pos logit contributions
lehem+1.720
RON+1.617
rans+1.577
rons+1.524
enance+1.515
Neg logit contributions
jriwal-1.945
kefeller-1.800
 impulse-1.757
 turmoil-1.669
 reaction-1.637
Tokenoral
Token ID6864
Feature activation-1.69e+00

Pos logit contributions
lehem+8.754
RON+8.557
rans+8.177
rons+8.081
enance+7.791
Neg logit contributions
jriwal-9.733
kefeller-9.346
 impulse-8.818
senal-8.321
 turmoil-8.313
Tokenitis
Token ID11815
Feature activation-9.27e-01

Pos logit contributions
jriwal+1.160
kefeller+1.036
 impulse+1.006
 turmoil+0.933
 reaction+0.908
Neg logit contributions
lehem-1.963
RON-1.858
rans-1.824
rons-1.792
enance-1.779
Token.
Token ID13
Feature activation-9.78e-02

Pos logit contributions
jriwal+0.824
kefeller+0.756
 impulse+0.737
 turmoil+0.696
 reaction+0.681
Neg logit contributions
lehem-0.887
RON-0.831
rans-0.812
rons-0.794
enance-0.788
Token
Token ID447
Feature activation-1.73e+00

Pos logit contributions
jriwal+0.091
kefeller+0.084
 impulse+0.082
 turmoil+0.078
 reaction+0.076
Neg logit contributions
lehem-0.089
RON-0.083
rans-0.081
rons-0.079
enance-0.079
Token
Token ID251
Feature activation+4.46e+00

Pos logit contributions
jriwal+1.815
kefeller+1.685
 impulse+1.658
 turmoil+1.587
 reaction+1.560
Neg logit contributions
lehem-1.377
RON-1.270
rans-1.231
rons-1.208
enance-1.185
Token matter
Token ID2300
Feature activation+1.36e+00

Pos logit contributions
lehem+1.483
RON+1.427
rans+1.407
rons+1.381
enance+1.378
Neg logit contributions
jriwal-0.571
kefeller-0.491
 impulse-0.442
 turmoil-0.389
senal-0.379
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
lehem+1.351
RON+1.273
rans+1.249
rons+1.220
enance+1.218
Neg logit contributions
jriwal-1.165
kefeller-1.070
 impulse-1.034
 turmoil-0.968
 reaction-0.946
Token
Token ID447
Feature activation-1.55e+00

Pos logit contributions
lehem+0.185
RON+0.174
rans+0.169
rons+0.166
enance+0.164
Neg logit contributions
jriwal-0.182
kefeller-0.167
 impulse-0.163
 turmoil-0.155
 reaction-0.152
Token
Token ID251
Feature activation+4.22e+00

Pos logit contributions
jriwal+1.723
kefeller+1.610
 impulse+1.584
 turmoil+1.521
 reaction+1.497
Neg logit contributions
lehem-1.126
RON-1.031
rans-0.999
rons-0.975
enance-0.954
Token<|endoftext|>
Token ID50256
Feature activation-1.92e+00

Pos logit contributions
lehem+3.676
RON+3.462
rans+3.349
rons+3.271
enance+3.254
Neg logit contributions
jriwal-4.090
kefeller-3.764
 impulse-3.680
 turmoil-3.458
 reaction-3.383
TokenR
Token ID49
Feature activation-1.21e+01

Pos logit contributions
jriwal+1.881
kefeller+1.740
 impulse+1.701
 turmoil+1.618
 reaction+1.591
Neg logit contributions
lehem-1.659
RON-1.538
rans-1.502
rons-1.467
enance-1.454
Tokenamon
Token ID16487
Feature activation+1.65e+00

Pos logit contributions
jriwal+11.859
kefeller+10.964
 impulse+10.706
 reaction+10.204
 turmoil+10.146
Neg logit contributions
lehem-9.335
RON-8.606
rans-8.169
rons-7.974
enance-7.767
Token Hare
Token ID42285
Feature activation-2.66e+00

Pos logit contributions
lehem+1.543
RON+1.446
rans+1.414
rons+1.383
enance+1.365
Neg logit contributions
jriwal-1.507
kefeller-1.372
 impulse-1.344
 turmoil-1.270
 reaction-1.244
Tokenwood
Token ID3822
Feature activation+7.08e-01

Pos logit contributions
jriwal+2.360
kefeller+2.160
 impulse+2.110
 turmoil+1.996
 reaction+1.963
Neg logit contributions
lehem-2.535
RON-2.379
rans-2.313
rons-2.265
enance-2.255
Token met
Token ID1138
Feature activation+4.48e+00

Pos logit contributions
lehem+0.692
RON+0.651
rans+0.637
rons+0.623
enance+0.616
Neg logit contributions
jriwal-0.615
kefeller-0.564
 impulse-0.547
 turmoil-0.515
 reaction-0.503
Token with
Token ID351
Feature activation-2.99e-01

Pos logit contributions
lehem+4.521
RON+4.289
rans+4.173
rons+4.109
enance+4.053
Neg logit contributions
jriwal-3.695
kefeller-3.363
 impulse-3.204
 turmoil-2.994
 reaction-2.900
Token down
Token ID866
Feature activation+4.97e-01

Pos logit contributions
jriwal+2.288
kefeller+2.040
 impulse+2.023
 turmoil+1.882
 reaction+1.851
Neg logit contributions
lehem-3.530
RON-3.323
rans-3.242
rons-3.188
enance-3.164
Token with
Token ID351
Feature activation+2.72e-01

Pos logit contributions
lehem+0.559
RON+0.529
rans+0.519
rons+0.511
enance+0.506
Neg logit contributions
jriwal-0.358
kefeller-0.324
 impulse-0.310
 turmoil-0.289
 reaction-0.279
Token Gohan
Token ID45281
Feature activation-2.70e+00

Pos logit contributions
lehem+0.269
RON+0.254
rans+0.249
rons+0.243
enance+0.241
Neg logit contributions
jriwal-0.233
kefeller-0.214
 impulse-0.206
 turmoil-0.194
 reaction-0.190
Token?
Token ID30
Feature activation-1.42e-01

Pos logit contributions
jriwal+2.318
kefeller+2.116
 impulse+2.084
 turmoil+1.976
 reaction+1.946
Neg logit contributions
lehem-2.658
RON-2.482
rans-2.416
rons-2.365
enance-2.347
Token<|endoftext|>
Token ID50256
Feature activation-2.15e+00

Pos logit contributions
jriwal+0.136
kefeller+0.126
 impulse+0.123
 turmoil+0.117
 reaction+0.114
Neg logit contributions
lehem-0.126
RON-0.118
rans-0.115
rons-0.112
enance-0.111
TokenR
Token ID49
Feature activation-1.21e+01

Pos logit contributions
jriwal+2.096
kefeller+1.938
 impulse+1.896
 turmoil+1.803
 reaction+1.773
Neg logit contributions
lehem-1.854
RON-1.714
rans-1.676
rons-1.639
enance-1.624
Tokenents
Token ID658
Feature activation+1.07e+00

Pos logit contributions
jriwal+11.891
kefeller+10.979
 impulse+10.723
 reaction+10.227
 turmoil+10.163
Neg logit contributions
lehem-9.272
RON-8.526
rans-8.102
rons-7.907
enance-7.691
Token still
Token ID991
Feature activation-6.50e-01

Pos logit contributions
lehem+1.067
RON+1.007
rans+0.991
rons+0.969
enance+0.959
Neg logit contributions
jriwal-0.890
kefeller-0.815
 impulse-0.788
 turmoil-0.738
 reaction-0.722
Token have
Token ID423
Feature activation-6.68e-02

Pos logit contributions
jriwal+0.500
kefeller+0.454
 impulse+0.437
 turmoil+0.408
 reaction+0.398
Neg logit contributions
lehem-0.698
RON-0.660
rans-0.648
rons-0.635
enance-0.630
Token the
Token ID262
Feature activation-1.54e+00

Pos logit contributions
jriwal+0.052
kefeller+0.048
 impulse+0.046
 turmoil+0.042
 reaction+0.041
Neg logit contributions
lehem-0.070
RON-0.067
rans-0.066
rons-0.065
enance-0.064
Token potential
Token ID2785
Feature activation-6.73e-01

Pos logit contributions
jriwal+1.065
kefeller+0.950
 impulse+0.926
 turmoil+0.859
 reaction+0.836
Neg logit contributions
lehem-1.785
RON-1.692
rans-1.658
rons-1.628
enance-1.618
Token dirty
Token ID11841
Feature activation-2.84e+00

Pos logit contributions
lehem+0.489
RON+0.464
rans+0.455
rons+0.448
enance+0.445
Neg logit contributions
jriwal-0.333
kefeller-0.302
 impulse-0.286
 turmoil-0.268
 reaction-0.259
Token.
Token ID13
Feature activation+5.89e-01

Pos logit contributions
jriwal+2.287
kefeller+2.071
 impulse+2.037
 turmoil+1.904
 reaction+1.879
Neg logit contributions
lehem-2.949
RON-2.782
rans-2.716
rons-2.660
enance-2.646
Token
Token ID447
Feature activation-1.68e+00

Pos logit contributions
lehem+0.525
RON+0.490
rans+0.477
rons+0.465
enance+0.461
Neg logit contributions
jriwal-0.564
kefeller-0.521
 impulse-0.508
 turmoil-0.481
 reaction-0.472
Token
Token ID251
Feature activation+4.31e+00

Pos logit contributions
jriwal+1.937
kefeller+1.813
 impulse+1.784
 turmoil+1.712
 reaction+1.686
Neg logit contributions
lehem-1.166
RON-1.063
rans-1.027
rons-0.997
enance-0.982
Token<|endoftext|>
Token ID50256
Feature activation-2.16e+00

Pos logit contributions
lehem+3.732
RON+3.505
rans+3.412
rons+3.311
enance+3.288
Neg logit contributions
jriwal-4.176
kefeller-3.883
 impulse-3.711
 turmoil-3.525
 reaction-3.427
TokenR
Token ID49
Feature activation-1.19e+01

Pos logit contributions
jriwal+2.115
kefeller+1.955
 impulse+1.913
 turmoil+1.819
 reaction+1.789
Neg logit contributions
lehem-1.869
RON-1.729
rans-1.690
rons-1.653
enance-1.638
TokenUSE
Token ID19108
Feature activation+1.42e-01

Pos logit contributions
jriwal+11.621
kefeller+10.747
 impulse+10.497
 reaction+9.996
 turmoil+9.942
Neg logit contributions
lehem-9.199
RON-8.487
rans-8.066
rons-7.870
enance-7.669
TokenLL
Token ID3069
Feature activation+4.18e-02

Pos logit contributions
lehem+0.136
RON+0.128
rans+0.125
rons+0.121
enance+0.120
Neg logit contributions
jriwal-0.126
kefeller-0.116
 impulse-0.112
 turmoil-0.106
 reaction-0.103
Token:
Token ID25
Feature activation-6.12e-01

Pos logit contributions
lehem+0.032
RON+0.029
rans+0.028
rons+0.028
enance+0.027
Neg logit contributions
jriwal-0.046
kefeller-0.042
 impulse-0.042
 turmoil-0.040
 reaction-0.039
Token What
Token ID1867
Feature activation-3.35e+00

Pos logit contributions
jriwal+0.575
kefeller+0.530
 impulse+0.518
 turmoil+0.491
 reaction+0.482
Neg logit contributions
lehem-0.555
RON-0.519
rans-0.506
rons-0.494
enance-0.489
Token I
Token ID314
Feature activation+7.87e-01

Pos logit contributions
jriwal+2.973
kefeller+2.716
 impulse+2.696
 turmoil+2.557
 reaction+2.517
Neg logit contributions
lehem-3.198
RON-2.994
rans-2.912
rons-2.843
enance-2.829
Token
Token ID198
Feature activation-2.16e-02

Pos logit contributions
lehem+5.493
RON+5.056
rans+5.029
enance+4.869
rons+4.847
Neg logit contributions
jriwal-6.185
kefeller-5.883
 impulse-5.586
 turmoil-5.260
 reaction-5.167
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
jriwal+0.020
kefeller+0.018
 impulse+0.018
 turmoil+0.017
 reaction+0.017
Neg logit contributions
lehem-0.020
RON-0.019
rans-0.018
rons-0.018
enance-0.018
TokenFirst
Token ID5962
Feature activation-2.82e+00

Pos logit contributions
lehem+0.078
RON+0.072
rans+0.070
rons+0.068
enance+0.067
Neg logit contributions
jriwal-0.114
kefeller-0.107
 impulse-0.105
 turmoil-0.100
 reaction-0.099
Token posted
Token ID4481
Feature activation-1.30e+00

Pos logit contributions
jriwal+2.361
kefeller+2.151
 impulse+2.085
 turmoil+1.964
 reaction+1.916
Neg logit contributions
lehem-2.857
RON-2.692
rans-2.638
rons-2.573
enance-2.555
Token<|endoftext|>
Token ID50256
Feature activation-2.38e+00

Pos logit contributions
jriwal+1.358
kefeller+1.269
 impulse+1.233
 turmoil+1.176
 reaction+1.151
Neg logit contributions
lehem-1.036
RON-0.961
rans-0.937
rons-0.913
enance-0.896
TokenR
Token ID49
Feature activation-1.19e+01

Pos logit contributions
jriwal+2.322
kefeller+2.147
 impulse+2.100
 turmoil+1.997
 reaction+1.964
Neg logit contributions
lehem-2.054
RON-1.898
rans-1.856
rons-1.817
enance-1.800
Tokenaj
Token ID1228
Feature activation-1.31e-01

Pos logit contributions
jriwal+11.610
kefeller+10.735
 impulse+10.501
 reaction+10.005
 turmoil+9.950
Neg logit contributions
lehem-9.168
RON-8.437
rans-8.014
rons-7.826
enance-7.620
Tokenk
Token ID74
Feature activation-8.44e-01

Pos logit contributions
jriwal+0.137
kefeller+0.127
 impulse+0.124
 turmoil+0.119
 reaction+0.117
Neg logit contributions
lehem-0.106
RON-0.098
rans-0.095
rons-0.093
enance-0.092
Tokenot
Token ID313
Feature activation+2.62e+00

Pos logit contributions
jriwal+0.790
kefeller+0.731
 impulse+0.712
 turmoil+0.676
 reaction+0.661
Neg logit contributions
lehem-0.767
RON-0.717
rans-0.703
rons-0.685
enance-0.675
Token:
Token ID25
Feature activation-8.47e-01

Pos logit contributions
lehem+2.526
RON+2.387
rans+2.349
rons+2.283
enance+2.239
Neg logit contributions
jriwal-2.287
kefeller-2.142
 impulse-2.029
 turmoil-1.920
 reaction-1.866
Token In
Token ID554
Feature activation-4.67e+00

Pos logit contributions
jriwal+0.781
kefeller+0.719
 impulse+0.702
 turmoil+0.665
 reaction+0.653
Neg logit contributions
lehem-0.782
RON-0.732
rans-0.714
rons-0.698
enance-0.691
Token the
Token ID262
Feature activation-7.92e-02

Pos logit contributions
jriwal+2.312
kefeller+2.092
 impulse+2.063
 turmoil+1.919
 reaction+1.884
Neg logit contributions
lehem-3.291
RON-3.091
rans-3.032
rons-2.969
enance-2.953
Token End
Token ID5268
Feature activation+3.89e+00

Pos logit contributions
jriwal+0.064
kefeller+0.058
 impulse+0.056
 turmoil+0.053
 reaction+0.051
Neg logit contributions
lehem-0.082
RON-0.078
rans-0.076
rons-0.075
enance-0.074
Token Around
Token ID16824
Feature activation+2.90e+00

Pos logit contributions
lehem+3.456
RON+3.209
rans+3.171
rons+3.090
enance+3.005
Neg logit contributions
jriwal-3.685
kefeller-3.419
 impulse-3.324
 turmoil-3.123
 reaction-3.031
Token.
Token ID13
Feature activation+4.61e-01

Pos logit contributions
lehem+3.002
RON+2.828
rans+2.750
rons+2.724
enance+2.668
Neg logit contributions
jriwal-2.299
kefeller-2.111
 impulse-2.016
 turmoil-1.889
 reaction-1.822
Token<|endoftext|>
Token ID50256
Feature activation-2.67e+00

Pos logit contributions
lehem+0.394
RON+0.368
rans+0.358
rons+0.348
enance+0.345
Neg logit contributions
jriwal-0.457
kefeller-0.423
 impulse-0.414
 turmoil-0.393
 reaction-0.386
TokenR
Token ID49
Feature activation-1.19e+01

Pos logit contributions
jriwal+2.605
kefeller+2.408
 impulse+2.355
 turmoil+2.240
 reaction+2.204
Neg logit contributions
lehem-2.310
RON-2.131
rans-2.087
rons-2.044
enance-2.025
Tokenape
Token ID1758
Feature activation+4.32e-01

Pos logit contributions
jriwal+11.619
kefeller+10.744
 impulse+10.504
 reaction+10.004
 turmoil+9.957
Neg logit contributions
lehem-9.137
RON-8.427
rans-8.011
rons-7.819
enance-7.611
Token by
Token ID416
Feature activation-2.57e+00

Pos logit contributions
lehem+0.443
RON+0.420
rans+0.412
rons+0.402
enance+0.397
Neg logit contributions
jriwal-0.354
kefeller-0.321
 impulse-0.308
 turmoil-0.289
 reaction-0.280
Token fraud
Token ID7394
Feature activation-3.96e+00

Pos logit contributions
jriwal+2.081
kefeller+1.892
 impulse+1.859
 turmoil+1.742
 reaction+1.709
Neg logit contributions
lehem-2.662
RON-2.497
rans-2.441
rons-2.395
enance-2.376
Token:
Token ID25
Feature activation-7.69e-01

Pos logit contributions
jriwal+3.228
kefeller+2.928
 impulse+2.877
 turmoil+2.700
 reaction+2.656
Neg logit contributions
lehem-4.034
RON-3.805
rans-3.713
rons-3.634
enance-3.623
Token What
Token ID1867
Feature activation-3.64e+00

Pos logit contributions
jriwal+0.681
kefeller+0.625
 impulse+0.606
 turmoil+0.572
 reaction+0.559
Neg logit contributions
lehem-0.738
RON-0.693
rans-0.678
rons-0.661
enance-0.656
Token more
Token ID517
Feature activation-4.80e+00

Pos logit contributions
lehem+0.206
RON+0.194
rans+0.189
rons+0.185
enance+0.184
Neg logit contributions
jriwal-0.175
kefeller-0.159
 impulse-0.155
 turmoil-0.147
 reaction-0.143
Token<|endoftext|>
Token ID50256
Feature activation-2.44e+00

Pos logit contributions
jriwal+4.328
 impulse+3.950
 turmoil+3.830
kefeller+3.811
 reaction+3.737
Neg logit contributions
lehem-4.510
RON-4.070
enance-3.890
rans-3.875
rons-3.749
TokenAbout
Token ID8585
Feature activation+1.61e-01

Pos logit contributions
jriwal+2.384
kefeller+2.204
 impulse+2.156
 turmoil+2.050
 reaction+2.017
Neg logit contributions
lehem-2.111
RON-1.949
rans-1.907
rons-1.867
enance-1.849
Token
Token ID198
Feature activation-2.35e+00

Pos logit contributions
lehem+0.148
RON+0.138
rans+0.135
rons+0.132
enance+0.131
Neg logit contributions
jriwal-0.149
kefeller-0.137
 impulse-0.133
 turmoil-0.126
 reaction-0.124
Token
Token ID198
Feature activation-2.16e+00

Pos logit contributions
jriwal+2.029
kefeller+1.859
 impulse+1.832
 turmoil+1.737
 reaction+1.714
Neg logit contributions
lehem-2.280
RON-2.110
rans-2.066
rons-2.030
enance-2.004
TokenR
Token ID49
Feature activation-1.12e+01

Pos logit contributions
jriwal+2.100
kefeller+1.937
 impulse+1.900
 turmoil+1.805
 reaction+1.778
Neg logit contributions
lehem-1.873
RON-1.725
rans-1.693
rons-1.656
enance-1.642
Tokenacing
Token ID4092
Feature activation+1.78e+00

Pos logit contributions
jriwal+10.857
kefeller+10.081
 impulse+9.859
 reaction+9.378
 turmoil+9.343
Neg logit contributions
lehem-8.893
RON-8.158
rans-7.797
rons-7.593
enance-7.393
Token Apex
Token ID49440
Feature activation-6.94e-01

Pos logit contributions
lehem+1.772
RON+1.666
rans+1.634
rons+1.596
enance+1.586
Neg logit contributions
jriwal-1.509
kefeller-1.385
 impulse-1.325
 turmoil-1.241
 reaction-1.215
Token is
Token ID318
Feature activation-4.58e+00

Pos logit contributions
jriwal+0.588
kefeller+0.537
 impulse+0.523
 turmoil+0.492
 reaction+0.482
Neg logit contributions
lehem-0.694
RON-0.653
rans-0.638
rons-0.625
enance-0.620
Token a
Token ID257
Feature activation-7.60e-01

Pos logit contributions
jriwal+3.499
kefeller+3.146
 impulse+3.083
 turmoil+2.887
 reaction+2.833
Neg logit contributions
lehem-4.927
RON-4.639
rans-4.542
rons-4.450
enance-4.419
Token fast
Token ID3049
Feature activation-4.17e+00

Pos logit contributions
jriwal+0.555
kefeller+0.500
 impulse+0.481
 turmoil+0.447
 reaction+0.432
Neg logit contributions
lehem-0.846
RON-0.805
rans-0.787
rons-0.773
enance-0.766
Token16
Token ID1433
Feature activation+1.72e+00

Pos logit contributions
lehem+0.441
RON+0.411
rans+0.399
rons+0.388
enance+0.385
Neg logit contributions
jriwal-0.518
kefeller-0.480
 impulse-0.469
 turmoil-0.446
 reaction-0.438
Token,
Token ID11
Feature activation-2.72e-01

Pos logit contributions
lehem+1.666
RON+1.566
rans+1.531
rons+1.490
enance+1.485
Neg logit contributions
jriwal-1.486
kefeller-1.393
 impulse-1.338
 turmoil-1.249
 reaction-1.218
Token violence
Token ID3685
Feature activation-2.86e+00

Pos logit contributions
jriwal+0.239
kefeller+0.221
 impulse+0.214
 turmoil+0.202
 reaction+0.198
Neg logit contributions
lehem-0.262
RON-0.246
rans-0.240
rons-0.234
enance-0.233
Token erupted
Token ID23681
Feature activation+8.98e-01

Pos logit contributions
jriwal+2.040
kefeller+1.810
 impulse+1.779
 turmoil+1.662
 reaction+1.625
Neg logit contributions
lehem-3.231
RON-3.064
rans-2.989
rons-2.938
enance-2.911
Token in
Token ID287
Feature activation-4.02e+00

Pos logit contributions
lehem+0.934
RON+0.878
rans+0.865
rons+0.847
enance+0.840
Neg logit contributions
jriwal-0.721
kefeller-0.665
 impulse-0.639
 turmoil-0.596
 reaction-0.580
Token Roh
Token ID32694
Feature activation-1.12e+01

Pos logit contributions
jriwal+3.358
kefeller+3.024
 impulse+2.993
 turmoil+2.833
 reaction+2.793
Neg logit contributions
lehem-4.057
RON-3.809
rans-3.692
rons-3.633
enance-3.605
Tokent
Token ID83
Feature activation+3.66e+00

Pos logit contributions
jriwal+10.903
kefeller+9.656
 impulse+9.599
 reaction+9.295
 turmoil+9.277
Neg logit contributions
lehem-8.704
RON-8.110
enance-7.686
rons-7.649
rans-7.471
Tokenak
Token ID461
Feature activation-1.22e+00

Pos logit contributions
lehem+3.009
rans+2.896
RON+2.833
rons+2.723
enance+2.699
Neg logit contributions
jriwal-3.521
kefeller-3.328
 impulse-3.261
senal-3.204
 turmoil-3.128
Token city
Token ID1748
Feature activation+2.66e+00

Pos logit contributions
jriwal+0.987
kefeller+0.902
 impulse+0.875
 turmoil+0.820
 reaction+0.800
Neg logit contributions
lehem-1.259
RON-1.187
rans-1.164
rons-1.138
enance-1.129
Token which
Token ID543
Feature activation+1.11e+00

Pos logit contributions
lehem+2.660
RON+2.500
rans+2.488
rons+2.416
enance+2.410
Neg logit contributions
jriwal-2.175
kefeller-2.042
 impulse-1.941
 turmoil-1.801
 allergy-1.738
Token continued
Token ID3767
Feature activation-2.09e+00

Pos logit contributions
lehem+1.168
RON+1.097
rans+1.085
rons+1.057
enance+1.052
Neg logit contributions
jriwal-0.879
kefeller-0.814
 impulse-0.777
 turmoil-0.723
 reaction-0.704
Token
Token ID198
Feature activation-4.14e-01

Pos logit contributions
jriwal+0.507
kefeller+0.466
 impulse+0.456
 turmoil+0.432
 reaction+0.423
Neg logit contributions
lehem-0.519
RON-0.486
rans-0.474
rons-0.463
enance-0.459
TokenSenior
Token ID31224
Feature activation-1.49e+00

Pos logit contributions
jriwal+0.400
kefeller+0.370
 impulse+0.362
 turmoil+0.344
 reaction+0.337
Neg logit contributions
lehem-0.364
RON-0.339
rans-0.330
rons-0.322
enance-0.319
Token advocate
Token ID12811
Feature activation-5.16e-01

Pos logit contributions
jriwal+1.133
kefeller+1.020
 impulse+0.995
 turmoil+0.930
 reaction+0.908
Neg logit contributions
lehem-1.625
RON-1.534
rans-1.503
rons-1.473
enance-1.464
Token Muk
Token ID31509
Feature activation-5.07e+00

Pos logit contributions
jriwal+0.468
kefeller+0.435
 impulse+0.420
 turmoil+0.397
 reaction+0.388
Neg logit contributions
lehem-0.483
RON-0.453
rans-0.443
rons-0.434
enance-0.429
Tokenul
Token ID377
Feature activation-2.75e+00

Pos logit contributions
jriwal+4.795
kefeller+4.300
 impulse+4.208
 turmoil+4.001
 reaction+3.958
Neg logit contributions
lehem-4.446
RON-4.180
rans-4.018
enance-3.952
rons-3.898
Token Roh
Token ID32694
Feature activation-1.09e+01

Pos logit contributions
jriwal+2.349
kefeller+2.145
 impulse+2.092
 turmoil+1.975
 reaction+1.937
Neg logit contributions
lehem-2.722
RON-2.565
rans-2.499
rons-2.447
enance-2.436
Tokenat
Token ID265
Feature activation+2.83e+00

Pos logit contributions
jriwal+10.127
 impulse+9.002
kefeller+8.840
 reaction+8.777
inki+8.661
Neg logit contributions
lehem-8.992
RON-8.431
────────-7.819
enance-7.669
rons-7.629
Tokengi
Token ID12397
Feature activation-4.64e+00

Pos logit contributions
lehem+3.146
RON+2.970
rans+2.964
rons+2.883
enance+2.757
Neg logit contributions
jriwal-2.064
kefeller-1.872
 impulse-1.780
 turmoil-1.670
 reaction-1.590
Token appearing
Token ID12655
Feature activation+2.85e+00

Pos logit contributions
jriwal+3.905
kefeller+3.490
 impulse+3.456
 turmoil+3.265
 reaction+3.225
Neg logit contributions
lehem-4.635
RON-4.336
rans-4.231
rons-4.154
enance-4.121
Token for
Token ID329
Feature activation-1.64e+00

Pos logit contributions
lehem+3.137
RON+2.975
rans+2.909
enance+2.869
rons+2.854
Neg logit contributions
jriwal-2.051
kefeller-1.932
 impulse-1.800
 turmoil-1.638
senal-1.616
Token Gh
Token ID11972
Feature activation-1.80e+00

Pos logit contributions
jriwal+1.367
kefeller+1.246
 impulse+1.214
 turmoil+1.143
 reaction+1.119
Neg logit contributions
lehem-1.656
RON-1.558
rans-1.523
rons-1.491
enance-1.480
Token Sen
Token ID2311
Feature activation-1.82e+00

Pos logit contributions
lehem+0.578
RON+0.545
rans+0.538
rons+0.522
enance+0.522
Neg logit contributions
jriwal-0.476
kefeller-0.436
 impulse-0.412
 turmoil-0.385
 reaction-0.375
Token.
Token ID13
Feature activation+9.88e-01

Pos logit contributions
jriwal+1.494
kefeller+1.361
 impulse+1.324
 turmoil+1.244
 reaction+1.216
Neg logit contributions
lehem-1.874
RON-1.767
rans-1.728
rons-1.692
enance-1.679
TokenJeff
Token ID19139
Feature activation+4.07e-01

Pos logit contributions
lehem+0.935
RON+0.891
rans+0.863
enance+0.843
rons+0.843
Neg logit contributions
jriwal-0.888
kefeller-0.815
 impulse-0.783
 turmoil-0.730
senal-0.719
Token Flake
Token ID39727
Feature activation-3.13e+00

Pos logit contributions
lehem+0.346
RON+0.323
rans+0.313
rons+0.306
enance+0.303
Neg logit contributions
jriwal-0.404
kefeller-0.375
 impulse-0.368
 turmoil-0.349
 reaction-0.342
Token(
Token ID7
Feature activation-5.62e-02

Pos logit contributions
jriwal+2.790
kefeller+2.549
 impulse+2.508
 turmoil+2.376
 reaction+2.335
Neg logit contributions
lehem-2.968
RON-2.769
rans-2.712
rons-2.644
enance-2.628
TokenR
Token ID49
Feature activation-1.09e+01

Pos logit contributions
jriwal+0.059
kefeller+0.055
 impulse+0.054
 turmoil+0.051
 reaction+0.050
Neg logit contributions
lehem-0.045
RON-0.041
rans-0.040
rons-0.039
enance-0.039
Token-
Token ID12
Feature activation+4.69e+00

Pos logit contributions
jriwal+6.220
kefeller+5.729
 impulse+5.617
 reaction+5.265
 turmoil+5.160
Neg logit contributions
lehem-12.648
RON-11.768
rans-11.459
enance-11.382
rons-11.324
TokenAri
Token ID26529
Feature activation-1.63e+00

Pos logit contributions
lehem+3.810
RON+3.637
rans+3.485
enance+3.374
rons+3.357
Neg logit contributions
jriwal-4.868
kefeller-4.474
 impulse-4.338
 turmoil-4.117
 reaction-4.014
Tokenz
Token ID89
Feature activation-2.44e+00

Pos logit contributions
jriwal+1.434
kefeller+1.314
 impulse+1.273
 turmoil+1.199
 reaction+1.170
Neg logit contributions
lehem-1.581
RON-1.490
rans-1.456
rons-1.428
enance-1.408
Token.)
Token ID2014
Feature activation+4.97e-01

Pos logit contributions
jriwal+2.334
kefeller+2.158
 impulse+2.115
 turmoil+2.005
 reaction+1.982
Neg logit contributions
lehem-2.155
RON-2.010
rans-1.949
rons-1.910
enance-1.890
Token after
Token ID706
Feature activation-1.14e+00

Pos logit contributions
lehem+0.549
RON+0.521
rans+0.510
rons+0.501
enance+0.498
Neg logit contributions
jriwal-0.367
kefeller-0.332
 impulse-0.318
 turmoil-0.295
 reaction-0.286
Token (
Token ID357
Feature activation+2.47e-01

Pos logit contributions
lehem+0.080
RON+0.075
rans+0.073
rons+0.071
enance+0.071
Neg logit contributions
jriwal-0.079
kefeller-0.072
 impulse-0.070
 turmoil-0.067
 reaction-0.065
TokenSD
Token ID10305
Feature activation+1.01e+00

Pos logit contributions
lehem+0.214
RON+0.200
rans+0.194
rons+0.190
enance+0.188
Neg logit contributions
jriwal-0.242
kefeller-0.224
 impulse-0.219
 turmoil-0.209
 reaction-0.205
Token)
Token ID8
Feature activation-3.43e-01

Pos logit contributions
lehem+0.911
RON+0.853
rans+0.831
rons+0.811
enance+0.804
Neg logit contributions
jriwal-0.957
kefeller-0.883
 impulse-0.861
 turmoil-0.818
 reaction-0.801
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
jriwal+0.302
kefeller+0.277
 impulse+0.270
 turmoil+0.255
 reaction+0.249
Neg logit contributions
lehem-0.331
RON-0.311
rans-0.304
rons-0.297
enance-0.294
Token
Token ID198
Feature activation-1.47e+00

Pos logit contributions
jriwal+1.418
kefeller+1.302
 impulse+1.277
 turmoil+1.209
 reaction+1.189
Neg logit contributions
lehem-1.513
RON-1.408
rans-1.376
rons-1.348
enance-1.332
TokenR
Token ID49
Feature activation-1.09e+01

Pos logit contributions
jriwal+1.441
kefeller+1.333
 impulse+1.304
 turmoil+1.239
 reaction+1.218
Neg logit contributions
lehem-1.273
RON-1.184
rans-1.153
rons-1.125
enance-1.114
TokenSS
Token ID5432
Feature activation-7.89e-01

Pos logit contributions
jriwal+9.894
kefeller+9.065
 impulse+9.002
 reaction+8.432
 turmoil+8.363
Neg logit contributions
lehem-9.247
RON-8.698
rans-8.180
rons-8.122
enance-7.897
Token (
Token ID357
Feature activation+4.50e-02

Pos logit contributions
jriwal+0.812
kefeller+0.754
 impulse+0.732
 turmoil+0.703
 reaction+0.683
Neg logit contributions
lehem-0.643
RON-0.605
rans-0.583
rons-0.572
enance-0.564
TokenHD
Token ID10227
Feature activation+1.42e+00

Pos logit contributions
lehem+0.043
RON+0.040
rans+0.039
rons+0.038
enance+0.038
Neg logit contributions
jriwal-0.040
kefeller-0.037
 impulse-0.036
 turmoil-0.034
 reaction-0.034
Token)
Token ID8
Feature activation-2.63e-01

Pos logit contributions
lehem+1.264
RON+1.184
rans+1.155
rons+1.125
enance+1.112
Neg logit contributions
jriwal-1.347
kefeller-1.243
 impulse-1.212
 turmoil-1.151
 reaction-1.128
Token |
Token ID930
Feature activation-3.58e+00

Pos logit contributions
jriwal+0.227
kefeller+0.207
 impulse+0.202
 turmoil+0.190
 reaction+0.186
Neg logit contributions
lehem-0.258
RON-0.243
rans-0.237
rons-0.232
enance-0.230
Token by
Token ID416
Feature activation-7.77e-01

Pos logit contributions
jriwal+0.943
kefeller+0.864
 impulse+0.841
 turmoil+0.794
 reaction+0.776
Neg logit contributions
lehem-1.076
RON-1.011
rans-0.989
rons-0.966
enance-0.958
Token blocking
Token ID12013
Feature activation-2.63e+00

Pos logit contributions
jriwal+0.632
kefeller+0.571
 impulse+0.560
 turmoil+0.526
 reaction+0.515
Neg logit contributions
lehem-0.803
RON-0.757
rans-0.739
rons-0.725
enance-0.719
Token national
Token ID2260
Feature activation-1.16e+00

Pos logit contributions
jriwal+2.244
kefeller+2.035
 impulse+2.003
 turmoil+1.881
 reaction+1.852
Neg logit contributions
lehem-2.616
RON-2.466
rans-2.388
rons-2.354
enance-2.323
Token highway
Token ID12763
Feature activation-8.68e-01

Pos logit contributions
jriwal+0.882
kefeller+0.798
 impulse+0.772
 turmoil+0.722
 reaction+0.704
Neg logit contributions
lehem-1.266
RON-1.196
rans-1.173
rons-1.149
enance-1.141
Token connecting
Token ID14320
Feature activation+1.56e+00

Pos logit contributions
jriwal+0.734
kefeller+0.672
 impulse+0.653
 turmoil+0.615
 reaction+0.602
Neg logit contributions
lehem-0.868
RON-0.817
rans-0.799
rons-0.782
enance-0.775
Token Roh
Token ID32694
Feature activation-1.07e+01

Pos logit contributions
lehem+1.520
RON+1.423
rans+1.397
rons+1.366
enance+1.352
Neg logit contributions
jriwal-1.353
kefeller-1.252
 impulse-1.207
 turmoil-1.138
 reaction-1.106
Tokent
Token ID83
Feature activation+3.47e+00

Pos logit contributions
jriwal+10.410
kefeller+9.340
 impulse+9.229
inki+8.970
 turmoil+8.817
Neg logit contributions
lehem-8.232
RON-7.743
enance-7.356
rons-7.213
rans-7.011
Tokenak
Token ID461
Feature activation-1.27e+00

Pos logit contributions
lehem+3.062
rans+2.895
RON+2.849
rons+2.745
enance+2.716
Neg logit contributions
jriwal-3.196
kefeller-2.985
 impulse-2.906
 turmoil-2.811
senal-2.770
Token to
Token ID284
Feature activation+9.91e-01

Pos logit contributions
jriwal+0.981
kefeller+0.891
 impulse+0.864
 turmoil+0.809
 reaction+0.788
Neg logit contributions
lehem-1.359
RON-1.284
rans-1.259
rons-1.232
enance-1.222
Token Delhi
Token ID12517
Feature activation-5.57e-01

Pos logit contributions
lehem+0.951
RON+0.891
rans+0.873
rons+0.851
enance+0.843
Neg logit contributions
jriwal-0.874
kefeller-0.809
 impulse-0.781
 turmoil-0.735
 reaction-0.717
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
jriwal+0.465
kefeller+0.426
 impulse+0.415
 turmoil+0.389
 reaction+0.380
Neg logit contributions
lehem-0.563
RON-0.529
rans-0.519
rons-0.506
enance-0.502
Tokenatt
Token ID1078
Feature activation+7.80e-01

Pos logit contributions
lehem+2.127
RON+2.023
rans+1.997
rons+1.955
enance+1.939
Neg logit contributions
jriwal-1.383
kefeller-1.259
 impulse-1.217
 turmoil-1.137
 reaction-1.096
Tokenu
Token ID84
Feature activation-2.71e+00

Pos logit contributions
lehem+0.839
RON+0.786
rans+0.784
rons+0.761
enance+0.753
Neg logit contributions
jriwal-0.598
kefeller-0.545
 impulse-0.530
 turmoil-0.496
 reaction-0.485
Token and
Token ID290
Feature activation-4.52e+00

Pos logit contributions
jriwal+2.230
kefeller+2.021
 impulse+1.975
 turmoil+1.857
 reaction+1.821
Neg logit contributions
lehem-2.761
RON-2.601
rans-2.541
rons-2.490
enance-2.474
Token C
Token ID327
Feature activation-6.53e-02

Pos logit contributions
jriwal+4.080
kefeller+3.726
 impulse+3.707
 turmoil+3.518
 reaction+3.482
Neg logit contributions
lehem-4.182
RON-3.876
rans-3.795
rons-3.694
enance-3.672
Token K
Token ID509
Feature activation-1.06e+00

Pos logit contributions
jriwal+0.061
kefeller+0.056
 impulse+0.055
 turmoil+0.052
 reaction+0.051
Neg logit contributions
lehem-0.060
RON-0.056
rans-0.054
rons-0.053
enance-0.053
Token Pr
Token ID1736
Feature activation-1.06e+01

Pos logit contributions
jriwal+0.941
kefeller+0.862
 impulse+0.841
 turmoil+0.794
 reaction+0.780
Neg logit contributions
lehem-1.015
RON-0.953
rans-0.929
rons-0.908
enance-0.902
Tokenas
Token ID292
Feature activation-8.53e-01

Pos logit contributions
jriwal+10.564
kefeller+9.583
 impulse+9.278
inki+8.866
 turmoil+8.838
Neg logit contributions
lehem-8.268
RON-7.897
────────-7.186
rans-7.053
enance-7.002
Tokenad
Token ID324
Feature activation+8.98e-01

Pos logit contributions
jriwal+0.874
kefeller+0.811
 impulse+0.794
 turmoil+0.756
 reaction+0.744
Neg logit contributions
lehem-0.700
RON-0.650
rans-0.630
rons-0.614
enance-0.609
Token also
Token ID635
Feature activation-1.30e+00

Pos logit contributions
lehem+0.890
RON+0.840
rans+0.823
rons+0.805
enance+0.796
Neg logit contributions
jriwal-0.763
kefeller-0.706
 impulse-0.679
 turmoil-0.640
 reaction-0.623
Token pulled
Token ID5954
Feature activation-4.09e+00

Pos logit contributions
jriwal+1.050
kefeller+0.954
 impulse+0.929
 turmoil+0.872
 reaction+0.853
Neg logit contributions
lehem-1.349
RON-1.272
rans-1.244
rons-1.219
enance-1.210
Token up
Token ID510
Feature activation+2.30e-01

Pos logit contributions
jriwal+2.989
kefeller+2.663
 impulse+2.609
 turmoil+2.434
 reaction+2.386
Neg logit contributions
lehem-4.547
RON-4.319
rans-4.206
rons-4.145
enance-4.070
Token a
Token ID257
Feature activation+6.07e-01

Pos logit contributions
jriwal+1.533
kefeller+1.394
 impulse+1.366
 turmoil+1.282
 reaction+1.255
Neg logit contributions
lehem-1.983
RON-1.866
rans-1.825
rons-1.786
enance-1.772
Token long
Token ID890
Feature activation-1.62e+00

Pos logit contributions
lehem+0.614
RON+0.580
rans+0.567
rons+0.555
enance+0.551
Neg logit contributions
jriwal-0.506
kefeller-0.461
 impulse-0.444
 turmoil-0.418
 reaction-0.407
Token time
Token ID640
Feature activation+1.55e+00

Pos logit contributions
jriwal+1.034
kefeller+0.913
 impulse+0.892
 turmoil+0.821
 reaction+0.799
Neg logit contributions
lehem-1.944
RON-1.848
rans-1.813
rons-1.783
enance-1.767
Token."
Token ID526
Feature activation-8.94e-01

Pos logit contributions
lehem+1.548
RON+1.459
rans+1.427
rons+1.399
enance+1.389
Neg logit contributions
jriwal-1.307
kefeller-1.199
 impulse-1.144
 turmoil-1.081
 reaction-1.050
Token<|endoftext|>
Token ID50256
Feature activation-2.77e+00

Pos logit contributions
jriwal+0.801
kefeller+0.741
 impulse+0.722
 turmoil+0.685
 reaction+0.673
Neg logit contributions
lehem-0.844
RON-0.787
rans-0.770
rons-0.752
enance-0.744
TokenOil
Token ID44142
Feature activation-1.06e+01

Pos logit contributions
jriwal+2.693
kefeller+2.488
 impulse+2.434
 turmoil+2.314
 reaction+2.277
Neg logit contributions
lehem-2.391
RON-2.203
rans-2.158
rons-2.116
enance-2.096
Token from
Token ID422
Feature activation-1.40e+00

Pos logit contributions
jriwal+8.219
kefeller+7.380
 impulse+7.283
 turmoil+7.148
 reaction+6.929
Neg logit contributions
lehem-10.538
RON-10.054
enance-9.719
rans-9.681
rons-9.657
Token a
Token ID257
Feature activation-7.87e-01

Pos logit contributions
jriwal+1.110
kefeller+1.008
 impulse+0.979
 turmoil+0.918
 reaction+0.897
Neg logit contributions
lehem-1.466
RON-1.383
rans-1.353
rons-1.326
enance-1.316
Token wrecked
Token ID44770
Feature activation-3.86e-01

Pos logit contributions
jriwal+0.609
kefeller+0.551
 impulse+0.535
 turmoil+0.501
 reaction+0.489
Neg logit contributions
lehem-0.844
RON-0.797
rans-0.780
rons-0.765
enance-0.759
Token tanker
Token ID46335
Feature activation-2.44e+00

Pos logit contributions
jriwal+0.304
kefeller+0.276
 impulse+0.267
 turmoil+0.250
 reaction+0.244
Neg logit contributions
lehem-0.408
RON-0.385
rans-0.377
rons-0.369
enance-0.366
Token is
Token ID318
Feature activation-4.31e+00

Pos logit contributions
jriwal+1.937
kefeller+1.753
 impulse+1.733
 turmoil+1.626
 reaction+1.592
Neg logit contributions
lehem-2.550
RON-2.408
rans-2.354
rons-2.297
enance-2.284
Token.
Token ID13
Feature activation-5.33e-02

Pos logit contributions
lehem+1.733
RON+1.628
rans+1.604
rons+1.566
enance+1.560
Neg logit contributions
jriwal-1.312
kefeller-1.214
 impulse-1.155
 turmoil-1.080
 reaction-1.052
Token<|endoftext|>
Token ID50256
Feature activation-2.01e+00

Pos logit contributions
jriwal+0.050
kefeller+0.046
 impulse+0.045
 turmoil+0.043
 reaction+0.042
Neg logit contributions
lehem-0.048
RON-0.045
rans-0.044
rons-0.043
enance-0.043
TokenName
Token ID5376
Feature activation-1.77e+00

Pos logit contributions
jriwal+1.965
kefeller+1.817
 impulse+1.777
 turmoil+1.690
 reaction+1.662
Neg logit contributions
lehem-1.733
RON-1.606
rans-1.568
rons-1.533
enance-1.518
Token:
Token ID25
Feature activation+2.57e-02

Pos logit contributions
jriwal+1.586
kefeller+1.453
 impulse+1.422
 turmoil+1.346
 reaction+1.322
Neg logit contributions
lehem-1.685
RON-1.576
rans-1.540
rons-1.507
enance-1.492
Token MSI
Token ID30781
Feature activation-4.42e+00

Pos logit contributions
lehem+0.024
RON+0.023
rans+0.022
rons+0.022
enance+0.021
Neg logit contributions
jriwal-0.023
kefeller-0.021
 impulse-0.021
 turmoil-0.020
 reaction-0.019
Token R
Token ID371
Feature activation-1.05e+01

Pos logit contributions
jriwal+3.938
kefeller+3.607
 impulse+3.588
 turmoil+3.397
 reaction+3.355
Neg logit contributions
lehem-4.126
RON-3.810
rans-3.756
rons-3.665
enance-3.630
Token78
Token ID3695
Feature activation+1.53e+00

Pos logit contributions
jriwal+9.487
 impulse+8.794
kefeller+8.743
 reaction+8.257
 turmoil+8.257
Neg logit contributions
lehem-9.077
RON-8.105
enance-7.843
rans-7.774
rons-7.564
Token70
Token ID2154
Feature activation+3.35e+00

Pos logit contributions
lehem+1.463
RON+1.383
rans+1.346
rons+1.315
enance+1.301
Neg logit contributions
jriwal-1.366
kefeller-1.244
 impulse-1.206
 turmoil-1.140
 reaction-1.115
Token Hawk
Token ID26698
Feature activation-5.59e-01

Pos logit contributions
lehem+3.017
RON+2.895
rans+2.798
rons+2.705
enance+2.657
Neg logit contributions
jriwal-3.146
kefeller-2.883
 impulse-2.742
 turmoil-2.615
 reaction-2.556
Token
Token ID198
Feature activation-1.97e+00

Pos logit contributions
jriwal+0.510
kefeller+0.468
 impulse+0.455
 turmoil+0.432
 reaction+0.422
Neg logit contributions
lehem-0.523
RON-0.491
rans-0.479
rons-0.469
enance-0.463
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
jriwal+1.716
kefeller+1.577
 impulse+1.548
 turmoil+1.465
 reaction+1.443
Neg logit contributions
lehem-1.890
RON-1.750
rans-1.722
rons-1.690
enance-1.671
Token started
Token ID2067
Feature activation-1.33e+00

Pos logit contributions
jriwal+0.667
kefeller+0.610
 impulse+0.594
 turmoil+0.560
 reaction+0.548
Neg logit contributions
lehem-0.786
RON-0.739
rans-0.722
rons-0.707
enance-0.701
Token at
Token ID379
Feature activation+2.30e+00

Pos logit contributions
jriwal+1.054
kefeller+0.950
 impulse+0.927
 turmoil+0.870
 reaction+0.852
Neg logit contributions
lehem-1.406
RON-1.328
rans-1.298
rons-1.272
enance-1.264
Token Sam
Token ID3409
Feature activation+1.64e+00

Pos logit contributions
lehem+2.221
RON+2.076
rans+2.045
rons+1.991
enance+1.967
Neg logit contributions
jriwal-2.012
kefeller-1.865
 impulse-1.795
 turmoil-1.692
 reaction-1.648
Tokenpl
Token ID489
Feature activation+1.41e+00

Pos logit contributions
lehem+1.517
RON+1.410
rans+1.392
rons+1.353
enance+1.335
Neg logit contributions
jriwal-1.499
kefeller-1.390
 impulse-1.359
 turmoil-1.288
 reaction-1.262
Tokena
Token ID64
Feature activation+1.30e+00

Pos logit contributions
lehem+1.084
RON+0.995
rans+0.983
rons+0.945
enance+0.932
Neg logit contributions
jriwal-1.517
kefeller-1.429
 impulse-1.385
 turmoil-1.325
 reaction-1.298
Token Roh
Token ID32694
Feature activation-1.05e+01

Pos logit contributions
lehem+1.269
RON+1.182
rans+1.166
rons+1.132
enance+1.119
Neg logit contributions
jriwal-1.130
kefeller-1.045
 impulse-1.011
 turmoil-0.952
 reaction-0.929
Tokent
Token ID83
Feature activation+3.97e+00

Pos logit contributions
jriwal+10.716
 impulse+9.608
kefeller+9.601
inki+9.196
 reaction+9.182
Neg logit contributions
lehem-7.877
RON-7.292
enance-6.763
rons-6.755
rans-6.647
Tokenak
Token ID461
Feature activation-1.09e+00

Pos logit contributions
lehem+3.524
RON+3.260
rans+3.259
rons+3.113
enance+3.081
Neg logit contributions
jriwal-3.723
kefeller-3.485
 impulse-3.371
 turmoil-3.239
 reaction-3.149
Token by
Token ID416
Feature activation-7.77e-01

Pos logit contributions
jriwal+0.943
kefeller+0.864
 impulse+0.841
 turmoil+0.794
 reaction+0.776
Neg logit contributions
lehem-1.076
RON-1.011
rans-0.989
rons-0.966
enance-0.958
Token blocking
Token ID12013
Feature activation-2.63e+00

Pos logit contributions
jriwal+0.632
kefeller+0.571
 impulse+0.560
 turmoil+0.526
 reaction+0.515
Neg logit contributions
lehem-0.803
RON-0.757
rans-0.739
rons-0.725
enance-0.719
Token national
Token ID2260
Feature activation-1.16e+00

Pos logit contributions
jriwal+2.244
kefeller+2.035
 impulse+2.003
 turmoil+1.881
 reaction+1.852
Neg logit contributions
lehem-2.616
RON-2.466
rans-2.388
rons-2.354
enance-2.323
Token flagged
Token ID34060
Feature activation+3.72e-01

Pos logit contributions
lehem+0.979
RON+0.925
rans+0.910
rons+0.891
enance+0.882
Neg logit contributions
jriwal-0.758
kefeller-0.689
 impulse-0.658
 turmoil-0.616
 reaction-0.603
Token off
Token ID572
Feature activation+7.15e-01

Pos logit contributions
lehem+0.414
RON+0.392
rans+0.386
rons+0.378
enance+0.376
Neg logit contributions
jriwal-0.272
kefeller-0.246
 impulse-0.236
 turmoil-0.219
 reaction-0.213
Token between
Token ID1022
Feature activation+1.56e+00

Pos logit contributions
lehem+0.749
RON+0.708
rans+0.694
rons+0.682
enance+0.673
Neg logit contributions
jriwal-0.569
kefeller-0.519
 impulse-0.499
 turmoil-0.469
 reaction-0.457
Token Sar
Token ID6866
Feature activation+6.90e-03

Pos logit contributions
lehem+1.505
RON+1.415
rans+1.385
rons+1.360
enance+1.337
Neg logit contributions
jriwal-1.373
kefeller-1.260
 impulse-1.212
 turmoil-1.146
 reaction-1.116
Tokenai
Token ID1872
Feature activation+2.75e-01

Pos logit contributions
lehem+0.006
RON+0.006
rans+0.006
rons+0.006
enance+0.006
Neg logit contributions
jriwal-0.006
kefeller-0.006
 impulse-0.006
 turmoil-0.005
 reaction-0.005
Token Roh
Token ID32694
Feature activation-1.05e+01

Pos logit contributions
lehem+0.279
RON+0.262
rans+0.258
rons+0.251
enance+0.249
Neg logit contributions
jriwal-0.229
kefeller-0.210
 impulse-0.203
 turmoil-0.192
 reaction-0.187
Tokenilla
Token ID5049
Feature activation+1.41e+00

Pos logit contributions
jriwal+10.753
kefeller+9.706
 impulse+9.617
inki+9.278
 turmoil+9.199
Neg logit contributions
lehem-7.656
RON-7.180
────────-6.616
enance-6.557
rons-6.546
Token station
Token ID4429
Feature activation+5.25e+00

Pos logit contributions
lehem+1.417
RON+1.331
rans+1.308
rons+1.278
enance+1.263
Neg logit contributions
jriwal-1.187
kefeller-1.090
 impulse-1.051
 turmoil-0.995
 reaction-0.968
Token in
Token ID287
Feature activation-3.79e+00

Pos logit contributions
lehem+4.986
RON+4.697
rans+4.604
rons+4.492
enance+4.440
Neg logit contributions
jriwal-4.492
kefeller-4.204
 impulse-3.987
 turmoil-3.827
senal-3.681
Token Delhi
Token ID12517
Feature activation-5.81e-01

Pos logit contributions
jriwal+3.298
kefeller+3.000
 impulse+2.948
 turmoil+2.786
 reaction+2.739
Neg logit contributions
lehem-3.687
RON-3.466
rans-3.377
rons-3.304
enance-3.284
Token to
Token ID284
Feature activation+1.38e+00

Pos logit contributions
jriwal+0.479
kefeller+0.440
 impulse+0.426
 turmoil+0.401
 reaction+0.391
Neg logit contributions
lehem-0.592
RON-0.557
rans-0.545
rons-0.532
enance-0.528
Token,
Token ID11
Feature activation-1.16e+00

Pos logit contributions
jriwal+1.344
kefeller+1.214
 impulse+1.190
 turmoil+1.117
 reaction+1.091
Neg logit contributions
lehem-1.931
RON-1.824
rans-1.789
rons-1.749
enance-1.739
Token Senator
Token ID8962
Feature activation+3.82e+00

Pos logit contributions
jriwal+1.004
kefeller+0.919
 impulse+0.895
 turmoil+0.844
 reaction+0.827
Neg logit contributions
lehem-1.133
RON-1.064
rans-1.040
rons-1.017
enance-1.008
Token Ted
Token ID11396
Feature activation+3.38e+00

Pos logit contributions
lehem+3.515
RON+3.341
rans+3.253
enance+3.198
rons+3.188
Neg logit contributions
jriwal-3.491
kefeller-3.188
 impulse-3.046
 turmoil-2.856
senal-2.834
Token Cruz
Token ID8742
Feature activation-2.85e+00

Pos logit contributions
lehem+2.744
RON+2.568
rans+2.502
rons+2.459
enance+2.436
Neg logit contributions
jriwal-3.455
kefeller-3.206
 impulse-3.123
 turmoil-2.977
 reaction-2.913
Token (
Token ID357
Feature activation+9.18e-01

Pos logit contributions
jriwal+2.456
kefeller+2.248
 impulse+2.215
 turmoil+2.101
 reaction+2.068
Neg logit contributions
lehem-2.772
RON-2.592
rans-2.529
rons-2.468
enance-2.450
TokenR
Token ID49
Feature activation-1.04e+01

Pos logit contributions
lehem+0.716
RON+0.667
rans+0.645
rons+0.625
enance+0.619
Neg logit contributions
jriwal-0.979
kefeller-0.910
 impulse-0.893
 turmoil-0.852
 reaction-0.836
Token-
Token ID12
Feature activation+5.19e+00

Pos logit contributions
jriwal+5.981
kefeller+5.600
 impulse+5.383
 reaction+5.106
 turmoil+4.966
Neg logit contributions
lehem-12.047
RON-11.295
rans-10.973
enance-10.892
rons-10.826
TokenTX
Token ID29551
Feature activation-2.19e+00

Pos logit contributions
lehem+4.909
RON+4.737
rans+4.578
rons+4.414
enance+4.407
Neg logit contributions
jriwal-4.682
kefeller-4.197
 impulse-4.146
 turmoil-3.867
 reaction-3.738
Token),
Token ID828
Feature activation+2.11e-01

Pos logit contributions
jriwal+1.983
kefeller+1.839
 impulse+1.788
 turmoil+1.699
 reaction+1.672
Neg logit contributions
lehem-2.030
RON-1.900
rans-1.851
rons-1.816
enance-1.797
Token who
Token ID508
Feature activation+1.34e+00

Pos logit contributions
lehem+0.212
RON+0.200
rans+0.195
rons+0.191
enance+0.190
Neg logit contributions
jriwal-0.178
kefeller-0.162
 impulse-0.156
 turmoil-0.147
 reaction-0.143
Token apparently
Token ID5729
Feature activation+4.10e+00

Pos logit contributions
lehem+1.318
RON+1.241
rans+1.219
rons+1.192
enance+1.183
Neg logit contributions
jriwal-1.158
kefeller-1.062
 impulse-1.026
 turmoil-0.963
 reaction-0.943
Token economic
Token ID3034
Feature activation-3.98e+00

Pos logit contributions
jriwal+2.511
kefeller+2.281
 impulse+2.260
 turmoil+2.119
 reaction+2.074
Neg logit contributions
lehem-3.521
RON-3.322
rans-3.227
rons-3.167
enance-3.148
Token recovery
Token ID7628
Feature activation-2.43e+00

Pos logit contributions
jriwal+2.522
 impulse+2.219
kefeller+2.213
 turmoil+2.075
 reaction+1.996
Neg logit contributions
lehem-4.810
RON-4.551
rans-4.435
enance-4.361
rons-4.360
Token.
Token ID13
Feature activation-6.92e-01

Pos logit contributions
jriwal+1.931
kefeller+1.736
 impulse+1.712
 turmoil+1.608
 reaction+1.571
Neg logit contributions
lehem-2.558
RON-2.417
rans-2.350
rons-2.308
enance-2.289
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
jriwal+0.608
kefeller+0.560
 impulse+0.546
 turmoil+0.520
 reaction+0.511
Neg logit contributions
lehem-0.663
RON-0.622
rans-0.607
rons-0.595
enance-0.587
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
jriwal+1.051
kefeller+0.966
 impulse+0.945
 turmoil+0.896
 reaction+0.880
Neg logit contributions
lehem-1.103
RON-1.029
rans-1.005
rons-0.983
enance-0.973
TokenR
Token ID49
Feature activation-1.04e+01

Pos logit contributions
jriwal+1.022
kefeller+0.944
 impulse+0.925
 turmoil+0.881
 reaction+0.866
Neg logit contributions
lehem-0.961
RON-0.887
rans-0.870
rons-0.851
enance-0.840
Tokenates
Token ID689
Feature activation-1.83e-01

Pos logit contributions
jriwal+8.646
kefeller+7.880
 impulse+7.773
 reaction+7.410
 turmoil+7.392
Neg logit contributions
lehem-9.654
RON-9.231
rans-8.690
rons-8.526
enance-8.502
Token were
Token ID547
Feature activation-9.62e-01

Pos logit contributions
jriwal+0.168
kefeller+0.154
 impulse+0.150
 turmoil+0.142
 reaction+0.139
Neg logit contributions
lehem-0.169
RON-0.159
rans-0.155
rons-0.152
enance-0.151
Token expected
Token ID2938
Feature activation+1.08e+00

Pos logit contributions
jriwal+0.804
kefeller+0.733
 impulse+0.710
 turmoil+0.666
 reaction+0.651
Neg logit contributions
lehem-0.969
RON-0.915
rans-0.897
rons-0.878
enance-0.872
Token to
Token ID284
Feature activation+8.62e-01

Pos logit contributions
lehem+1.264
RON+1.207
rans+1.190
rons+1.170
enance+1.156
Neg logit contributions
jriwal-0.712
kefeller-0.629
 impulse-0.608
 turmoil-0.554
 reaction-0.536
Token rise
Token ID4485
Feature activation-2.80e+00

Pos logit contributions
lehem+0.939
RON+0.891
rans+0.878
rons+0.859
enance+0.851
Neg logit contributions
jriwal-0.647
kefeller-0.584
 impulse-0.560
 turmoil-0.522
 reaction-0.509
Token multiplayer
Token ID16913
Feature activation-2.08e+00

Pos logit contributions
jriwal+2.939
kefeller+2.644
 impulse+2.615
 turmoil+2.428
 reaction+2.390
Neg logit contributions
lehem-4.659
RON-4.398
rans-4.322
rons-4.230
enance-4.204
Token mayhem
Token ID43744
Feature activation-2.25e+00

Pos logit contributions
jriwal+1.632
kefeller+1.476
 impulse+1.426
 turmoil+1.334
 reaction+1.301
Neg logit contributions
lehem-2.212
RON-2.092
rans-2.047
rons-2.011
enance-1.994
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
jriwal+1.772
kefeller+1.607
 impulse+1.563
 turmoil+1.465
 reaction+1.432
Neg logit contributions
lehem-2.374
RON-2.240
rans-2.192
rons-2.148
enance-2.132
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
jriwal+1.300
kefeller+1.199
 impulse+1.177
 turmoil+1.116
 reaction+1.099
Neg logit contributions
lehem-1.341
RON-1.244
rans-1.219
rons-1.191
enance-1.184
Token
Token ID198
Feature activation-1.52e+00

Pos logit contributions
jriwal+1.485
kefeller+1.364
 impulse+1.338
 turmoil+1.268
 reaction+1.247
Neg logit contributions
lehem-1.598
RON-1.486
rans-1.452
rons-1.423
enance-1.407
TokenR
Token ID49
Feature activation-1.03e+01

Pos logit contributions
jriwal+1.504
kefeller+1.391
 impulse+1.363
 turmoil+1.297
 reaction+1.275
Neg logit contributions
lehem-1.294
RON-1.195
rans-1.167
rons-1.138
enance-1.128
Tokenacing
Token ID4092
Feature activation+1.92e+00

Pos logit contributions
jriwal+7.355
kefeller+6.732
 impulse+6.556
 turmoil+6.083
 reaction+6.065
Neg logit contributions
lehem-10.836
RON-10.150
rans-9.860
rons-9.620
enance-9.445
Token Apex
Token ID49440
Feature activation-6.80e-01

Pos logit contributions
lehem+1.701
RON+1.593
rans+1.554
rons+1.524
enance+1.512
Neg logit contributions
jriwal-1.820
kefeller-1.698
 impulse-1.628
 turmoil-1.546
 reaction-1.518
Token is
Token ID318
Feature activation-3.82e+00

Pos logit contributions
jriwal+0.563
kefeller+0.513
 impulse+0.498
 turmoil+0.468
 reaction+0.457
Neg logit contributions
lehem-0.692
RON-0.653
rans-0.638
rons-0.625
enance-0.620
Token targeting
Token ID10822
Feature activation+1.00e+00

Pos logit contributions
jriwal+2.975
kefeller+2.690
 impulse+2.639
 turmoil+2.470
 reaction+2.420
Neg logit contributions
lehem-4.067
RON-3.823
rans-3.737
rons-3.668
enance-3.638
Token Windows
Token ID3964
Feature activation+1.85e+00

Pos logit contributions
lehem+1.025
RON+0.977
rans+0.958
rons+0.936
enance+0.928
Neg logit contributions
jriwal-0.818
kefeller-0.739
 impulse-0.704
 turmoil-0.666
 reaction-0.643
Token K
Token ID509
Feature activation-4.56e-01

Pos logit contributions
jriwal+3.133
kefeller+2.961
 impulse+2.865
 turmoil+2.761
 reaction+2.732
Neg logit contributions
lehem-1.921
RON-1.760
rans-1.700
enance-1.643
rons-1.626
Tokenlim
Token ID2475
Feature activation-4.12e+00

Pos logit contributions
jriwal+0.562
kefeller+0.529
 impulse+0.522
 turmoil+0.501
 reaction+0.493
Neg logit contributions
lehem-0.282
RON-0.252
rans-0.245
rons-0.238
enance-0.230
Tokenenty
Token ID3787
Feature activation-2.07e-01

Pos logit contributions
jriwal+2.725
kefeller+2.439
 impulse+2.331
 turmoil+2.170
 reaction+2.159
Neg logit contributions
lehem-4.751
RON-4.548
rans-4.389
enance-4.354
rons-4.328
Tokenev
Token ID1990
Feature activation+4.81e+00

Pos logit contributions
jriwal+0.263
kefeller+0.246
 impulse+0.244
 turmoil+0.235
 reaction+0.233
Neg logit contributions
lehem-0.119
RON-0.107
rans-0.101
enance-0.097
rons-0.097
Token/
Token ID14
Feature activation-1.06e+00

Pos logit contributions
lehem+4.859
RON+4.610
rans+4.495
rons+4.442
enance+4.377
Neg logit contributions
jriwal-3.953
kefeller-3.568
 impulse-3.497
 turmoil-3.235
 reaction-3.154
TokenR
Token ID49
Feature activation-1.03e+01

Pos logit contributions
jriwal+0.984
kefeller+0.908
 impulse+0.885
 turmoil+0.839
 reaction+0.826
Neg logit contributions
lehem-0.963
RON-0.897
rans-0.877
rons-0.857
enance-0.851
TokenIA
Token ID3539
Feature activation-1.89e-01

Pos logit contributions
jriwal+9.707
kefeller+9.086
 impulse+8.648
 reaction+8.360
 turmoil+8.308
Neg logit contributions
lehem-8.695
RON-7.988
rons-7.615
rans-7.552
enance-7.457
Token Nov
Token ID5267
Feature activation+7.00e-01

Pos logit contributions
jriwal+0.186
kefeller+0.169
 impulse+0.165
 turmoil+0.157
 reaction+0.153
Neg logit contributions
lehem-0.166
RON-0.155
rans-0.153
rons-0.146
enance-0.144
Tokenost
Token ID455
Feature activation+1.22e+00

Pos logit contributions
lehem+0.561
RON+0.519
rans+0.506
rons+0.491
enance+0.485
Neg logit contributions
jriwal-0.732
kefeller-0.679
 impulse-0.662
 turmoil-0.634
 reaction-0.622
Tokeni
Token ID72
Feature activation-3.72e+00

Pos logit contributions
lehem+0.938
rans+0.882
RON+0.875
rons+0.830
enance+0.814
Neg logit contributions
jriwal-1.294
kefeller-1.202
 impulse-1.152
senal-1.114
 turmoil-1.109
Token/
Token ID14
Feature activation-1.16e+00

Pos logit contributions
jriwal+2.598
kefeller+2.369
 impulse+2.280
 turmoil+2.143
 reaction+2.086
Neg logit contributions
lehem-4.210
RON-3.975
rans-3.892
rons-3.841
enance-3.809
Token Oak
Token ID9121
Feature activation+1.91e+00

Pos logit contributions
lehem+1.916
RON+1.811
rans+1.776
rons+1.736
enance+1.704
Neg logit contributions
jriwal-1.647
kefeller-1.508
 impulse-1.445
 turmoil-1.361
 reaction-1.319
Tokensterdam
Token ID22506
Feature activation+1.09e-01

Pos logit contributions
lehem+1.814
RON+1.698
rans+1.669
rons+1.622
enance+1.581
Neg logit contributions
jriwal-1.713
kefeller-1.568
 impulse-1.529
 turmoil-1.445
 reaction-1.414
Token,
Token ID11
Feature activation-8.45e-01

Pos logit contributions
lehem+0.103
RON+0.097
rans+0.095
rons+0.093
enance+0.092
Neg logit contributions
jriwal-0.098
kefeller-0.090
 impulse-0.087
 turmoil-0.082
 reaction-0.081
Token a
Token ID257
Feature activation+4.67e-01

Pos logit contributions
jriwal+0.704
kefeller+0.642
 impulse+0.624
 turmoil+0.586
 reaction+0.573
Neg logit contributions
lehem-0.857
RON-0.807
rans-0.789
rons-0.772
enance-0.765
Token how
Token ID703
Feature activation-2.46e+00

Pos logit contributions
lehem+0.529
RON+0.503
rans+0.494
rons+0.484
enance+0.478
Neg logit contributions
jriwal-0.334
kefeller-0.297
 impulse-0.285
 turmoil-0.263
 reaction-0.254
Token-
Token ID12
Feature activation+6.28e+00

Pos logit contributions
jriwal+2.093
kefeller+1.911
 impulse+1.865
 turmoil+1.759
 reaction+1.733
Neg logit contributions
lehem-2.441
RON-2.290
rans-2.223
rons-2.185
enance-2.182
Tokento
Token ID1462
Feature activation+2.38e+00

Pos logit contributions
lehem+4.613
rans+4.344
RON+4.252
rons+4.099
enance+3.957
Neg logit contributions
jriwal-6.749
kefeller-6.326
 impulse-6.181
 turmoil-5.883
 earthquake-5.732
Token about
Token ID546
Feature activation+6.27e-01

Pos logit contributions
lehem+2.653
RON+2.532
rans+2.484
rons+2.448
enance+2.405
Neg logit contributions
jriwal-1.702
kefeller-1.555
 impulse-1.421
 turmoil-1.314
 reaction-1.267
Token opening
Token ID4756
Feature activation-1.87e+00

Pos logit contributions
lehem+0.694
RON+0.665
rans+0.652
rons+0.638
enance+0.635
Neg logit contributions
jriwal-0.457
kefeller-0.413
 impulse-0.391
 turmoil-0.365
 reaction-0.353
Token and
Token ID290
Feature activation-3.25e+00

Pos logit contributions
jriwal+1.360
kefeller+1.224
 impulse+1.185
 turmoil+1.104
 reaction+1.076
Neg logit contributions
lehem-2.084
RON-1.974
rans-1.935
rons-1.898
enance-1.885
Token running
Token ID2491
Feature activation-2.00e+00

Pos logit contributions
jriwal+1.999
kefeller+1.751
 impulse+1.710
 turmoil+1.581
 reaction+1.536
Neg logit contributions
lehem-3.997
RON-3.788
rans-3.711
rons-3.651
enance-3.626
Token how
Token ID703
Feature activation-2.28e+00

Pos logit contributions
jriwal+0.852
kefeller+0.774
 impulse+0.754
 turmoil+0.707
 reaction+0.691
Neg logit contributions
lehem-1.125
RON-1.061
rans-1.038
rons-1.017
enance-1.009
Token I
Token ID314
Feature activation+2.43e+00

Pos logit contributions
jriwal+1.665
kefeller+1.491
 impulse+1.475
 turmoil+1.376
 reaction+1.343
Neg logit contributions
lehem-2.529
RON-2.390
rans-2.337
rons-2.294
enance-2.270
Token had
Token ID550
Feature activation+1.56e+00

Pos logit contributions
lehem+2.222
RON+2.081
rans+2.041
rons+1.994
enance+1.979
Neg logit contributions
jriwal-2.259
kefeller-2.084
 impulse-2.012
 turmoil-1.909
 reaction-1.866
Token failed
Token ID4054
Feature activation-1.11e+00

Pos logit contributions
lehem+1.569
RON+1.482
rans+1.456
rons+1.428
enance+1.421
Neg logit contributions
jriwal-1.308
kefeller-1.197
 impulse-1.141
 turmoil-1.079
 reaction-1.048
Token to
Token ID284
Feature activation+1.48e+00

Pos logit contributions
jriwal+0.791
kefeller+0.709
 impulse+0.690
 turmoil+0.641
 reaction+0.625
Neg logit contributions
lehem-1.252
RON-1.186
rans-1.163
rons-1.141
enance-1.132
Token realize
Token ID6537
Feature activation+6.89e+00

Pos logit contributions
lehem+1.371
RON+1.286
rans+1.259
rons+1.230
enance+1.221
Neg logit contributions
jriwal-1.361
kefeller-1.256
 impulse-1.208
 turmoil-1.148
 reaction-1.122
Token this
Token ID428
Feature activation-1.68e+00

Pos logit contributions
lehem+6.441
RON+6.065
enance+6.019
rans+5.988
rons+5.860
Neg logit contributions
jriwal-5.991
kefeller-5.531
 impulse-4.965
senal-4.955
inki-4.798
Token in
Token ID287
Feature activation-3.63e+00

Pos logit contributions
jriwal+1.254
kefeller+1.130
 impulse+1.101
 turmoil+1.027
 reaction+1.002
Neg logit contributions
lehem-1.845
RON-1.745
rans-1.709
rons-1.677
enance-1.663
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
jriwal+2.639
kefeller+2.364
 impulse+2.359
 turmoil+2.200
 reaction+2.159
Neg logit contributions
lehem-4.013
RON-3.794
rans-3.718
rons-3.638
enance-3.619
Token very
Token ID845
Feature activation-2.92e+00

Pos logit contributions
jriwal+0.165
kefeller+0.150
 impulse+0.144
 turmoil+0.134
 reaction+0.131
Neg logit contributions
lehem-0.219
RON-0.206
rans-0.202
rons-0.198
enance-0.197
Token beginning
Token ID3726
Feature activation+2.18e+00

Pos logit contributions
jriwal+2.252
kefeller+2.028
 impulse+2.007
 turmoil+1.880
 reaction+1.837
Neg logit contributions
lehem-3.117
RON-2.948
rans-2.885
rons-2.823
enance-2.799
Token-,
Token ID20995
Feature activation+4.49e+00

Pos logit contributions
lehem+1.645
RON+1.553
rans+1.520
rons+1.491
enance+1.474
Neg logit contributions
jriwal-1.277
kefeller-1.154
 impulse-1.123
 turmoil-1.056
 reaction-1.029
Token five
Token ID1936
Feature activation+1.59e+00

Pos logit contributions
lehem+4.386
RON+4.079
rans+4.038
rons+3.958
enance+3.881
Neg logit contributions
jriwal-3.828
kefeller-3.505
 impulse-3.316
 turmoil-3.172
 reaction-3.082
Token-,
Token ID20995
Feature activation+4.24e+00

Pos logit contributions
lehem+1.616
RON+1.524
rans+1.493
rons+1.464
enance+1.444
Neg logit contributions
jriwal-1.324
kefeller-1.202
 impulse-1.168
 turmoil-1.101
 reaction-1.074
Token and
Token ID290
Feature activation-2.08e+00

Pos logit contributions
lehem+4.190
RON+3.937
rans+3.905
rons+3.787
enance+3.711
Neg logit contributions
jriwal-3.613
kefeller-3.278
 impulse-3.105
 turmoil-2.965
 reaction-2.855
Token ten
Token ID3478
Feature activation+3.21e+00

Pos logit contributions
jriwal+1.613
kefeller+1.465
 impulse+1.437
 turmoil+1.345
 reaction+1.321
Neg logit contributions
lehem-2.211
RON-2.084
rans-2.030
rons-1.996
enance-1.985
Token-
Token ID12
Feature activation+7.07e+00

Pos logit contributions
lehem+3.376
RON+3.200
rans+3.149
rons+3.102
enance+3.034
Neg logit contributions
jriwal-2.530
kefeller-2.260
 impulse-2.183
 turmoil-2.059
 reaction-1.992
Tokencent
Token ID1087
Feature activation+4.85e+00

Pos logit contributions
lehem+6.428
rans+5.980
RON+5.975
rons+5.834
enance+5.568
Neg logit contributions
jriwal-6.437
kefeller-5.806
 impulse-5.692
 turmoil-5.452
 reaction-5.255
Token pieces
Token ID5207
Feature activation-9.47e-01

Pos logit contributions
lehem+5.047
RON+4.790
rans+4.752
rons+4.739
enance+4.592
Neg logit contributions
jriwal-3.775
kefeller-3.408
 impulse-3.183
 turmoil-3.004
senal-2.950
Token of
Token ID286
Feature activation+1.98e+00

Pos logit contributions
jriwal+0.769
kefeller+0.700
 impulse+0.683
 turmoil+0.642
 reaction+0.628
Neg logit contributions
lehem-0.978
RON-0.920
rans-0.899
rons-0.880
enance-0.873
Token an
Token ID281
Feature activation+8.75e-01

Pos logit contributions
lehem+2.044
RON+1.937
rans+1.906
rons+1.868
enance+1.854
Neg logit contributions
jriwal-1.591
kefeller-1.422
 impulse-1.365
 turmoil-1.287
 reaction-1.247
Token alloy
Token ID36186
Feature activation+3.71e+00

Pos logit contributions
lehem+0.973
RON+0.927
rans+0.913
rons+0.893
enance+0.886
Neg logit contributions
jriwal-0.638
kefeller-0.572
 impulse-0.545
 turmoil-0.515
 reaction-0.499
Token;
Token ID26
Feature activation+1.72e+00

Pos logit contributions
jriwal+0.211
kefeller+0.193
 impulse+0.187
 turmoil+0.176
 reaction+0.172
Neg logit contributions
lehem-0.258
RON-0.243
rans-0.238
rons-0.232
enance-0.231
Token the
Token ID262
Feature activation+1.51e-03

Pos logit contributions
lehem+1.714
RON+1.615
rans+1.587
rons+1.550
enance+1.541
Neg logit contributions
jriwal-1.450
kefeller-1.317
 impulse-1.269
 turmoil-1.202
 reaction-1.173
Token Vin
Token ID11820
Feature activation+2.31e+00

Pos logit contributions
lehem+0.001
RON+0.001
rans+0.001
rons+0.001
enance+0.001
Neg logit contributions
jriwal-0.001
kefeller-0.001
 impulse-0.001
 turmoil-0.001
 reaction-0.001
Tokencci
Token ID35764
Feature activation+4.73e-01

Pos logit contributions
lehem+2.265
RON+2.126
rans+2.092
rons+2.045
enance+2.011
Neg logit contributions
jriwal-1.998
kefeller-1.815
 impulse-1.774
 turmoil-1.681
 reaction-1.641
Token La
Token ID4689
Feature activation+2.06e-01

Pos logit contributions
lehem+0.464
RON+0.437
rans+0.428
rons+0.419
enance+0.415
Neg logit contributions
jriwal-0.409
kefeller-0.373
 impulse-0.362
 turmoil-0.342
 reaction-0.335
Token Plant
Token ID16561
Feature activation+6.91e+00

Pos logit contributions
lehem+0.195
RON+0.183
rans+0.178
rons+0.174
enance+0.173
Neg logit contributions
jriwal-0.186
kefeller-0.170
 impulse-0.166
 turmoil-0.157
 reaction-0.154
Tokenaci
Token ID32009
Feature activation+2.43e+00

Pos logit contributions
lehem+5.791
RON+5.448
rans+5.415
rons+5.287
enance+5.211
Neg logit contributions
jriwal-6.706
kefeller-6.192
 impulse-5.960
 turmoil-5.677
 reaction-5.560
Tokenón
Token ID18840
Feature activation+1.01e-01

Pos logit contributions
lehem+2.104
RON+1.975
rans+1.942
rons+1.886
enance+1.873
Neg logit contributions
jriwal-2.380
kefeller-2.183
 impulse-2.120
 turmoil-2.019
 reaction-1.981
Token del
Token ID1619
Feature activation-1.06e+00

Pos logit contributions
lehem+0.107
RON+0.101
rans+0.099
rons+0.097
enance+0.096
Neg logit contributions
jriwal-0.080
kefeller-0.072
 impulse-0.070
 turmoil-0.065
 reaction-0.064
Token Sur
Token ID4198
Feature activation-1.48e+00

Pos logit contributions
jriwal+0.953
kefeller+0.876
 impulse+0.858
 turmoil+0.812
 reaction+0.796
Neg logit contributions
lehem-0.999
RON-0.935
rans-0.913
rons-0.892
enance-0.885
Token on
Token ID319
Feature activation-3.11e+00

Pos logit contributions
jriwal+1.120
kefeller+1.013
 impulse+0.990
 turmoil+0.923
 reaction+0.901
Neg logit contributions
lehem-1.610
RON-1.525
rans-1.486
rons-1.458
enance-1.445
TokenFor
Token ID1890
Feature activation-5.92e-01

Pos logit contributions
lehem+0.134
RON+0.125
rans+0.122
rons+0.119
enance+0.117
Neg logit contributions
jriwal-0.155
kefeller-0.143
 impulse-0.140
 turmoil-0.133
 reaction-0.131
Token more
Token ID517
Feature activation-4.15e+00

Pos logit contributions
jriwal+0.474
kefeller+0.431
 impulse+0.418
 turmoil+0.392
 reaction+0.382
Neg logit contributions
lehem-0.620
RON-0.584
rans-0.572
rons-0.561
enance-0.556
Token information
Token ID1321
Feature activation-1.10e+00

Pos logit contributions
jriwal+2.613
kefeller+2.290
 impulse+2.244
 turmoil+2.077
 reaction+2.033
Neg logit contributions
lehem-5.030
RON-4.773
rans-4.682
rons-4.594
enance-4.569
Token on
Token ID319
Feature activation-2.53e+00

Pos logit contributions
jriwal+0.848
kefeller+0.768
 impulse+0.745
 turmoil+0.696
 reaction+0.678
Neg logit contributions
lehem-1.185
RON-1.119
rans-1.096
rons-1.075
enance-1.067
Token O
Token ID440
Feature activation-6.08e+00

Pos logit contributions
jriwal+1.967
kefeller+1.775
 impulse+1.748
 turmoil+1.644
 reaction+1.610
Neg logit contributions
lehem-2.688
RON-2.530
rans-2.474
rons-2.428
enance-2.412
TokenVD
Token ID8898
Feature activation+7.21e+00

Pos logit contributions
jriwal+5.750
kefeller+5.308
 impulse+5.204
 turmoil+4.951
 reaction+4.873
Neg logit contributions
lehem-5.228
RON-4.830
rans-4.748
enance-4.639
rons-4.572
Token-
Token ID12
Feature activation+6.14e+00

Pos logit contributions
lehem+7.467
RON+7.268
rans+7.099
rons+6.907
enance+6.707
Neg logit contributions
jriwal-5.385
kefeller-4.998
 impulse-4.696
 turmoil-4.236
 earthquake-4.124
TokenInfo
Token ID12360
Feature activation-7.86e-02

Pos logit contributions
lehem+5.424
RON+5.182
rans+5.026
rons+4.868
enance+4.743
Neg logit contributions
jriwal-5.730
kefeller-5.292
 impulse-5.191
 turmoil-4.859
 earthquake-4.762
Token,
Token ID11
Feature activation-4.60e-01

Pos logit contributions
jriwal+0.068
kefeller+0.062
 impulse+0.060
 turmoil+0.056
 reaction+0.055
Neg logit contributions
lehem-0.078
RON-0.073
rans-0.072
rons-0.070
enance-0.069
Token read
Token ID1100
Feature activation-1.53e-01

Pos logit contributions
jriwal+0.410
kefeller+0.377
 impulse+0.367
 turmoil+0.347
 reaction+0.339
Neg logit contributions
lehem-0.439
RON-0.412
rans-0.403
rons-0.394
enance-0.390
Token this
Token ID428
Feature activation-2.16e+00

Pos logit contributions
jriwal+0.127
kefeller+0.116
 impulse+0.112
 turmoil+0.106
 reaction+0.103
Neg logit contributions
lehem-0.156
RON-0.147
rans-0.144
rons-0.141
enance-0.140
Token create
Token ID2251
Feature activation+1.76e+00

Pos logit contributions
jriwal+2.161
kefeller+1.960
 impulse+1.915
 turmoil+1.795
 reaction+1.755
Neg logit contributions
lehem-2.917
RON-2.755
rans-2.693
rons-2.637
enance-2.619
Token a
Token ID257
Feature activation+9.90e-01

Pos logit contributions
lehem+1.916
RON+1.801
rans+1.768
rons+1.745
enance+1.726
Neg logit contributions
jriwal-1.330
kefeller-1.200
 impulse-1.139
 turmoil-1.037
senal-1.025
Token reason
Token ID1738
Feature activation-2.30e-01

Pos logit contributions
lehem+1.080
RON+1.020
rans+1.003
rons+0.980
enance+0.968
Neg logit contributions
jriwal-0.749
kefeller-0.671
 impulse-0.641
 turmoil-0.590
 reaction-0.572
Token for
Token ID329
Feature activation-7.20e-01

Pos logit contributions
jriwal+0.153
kefeller+0.137
 impulse+0.131
 turmoil+0.121
 reaction+0.117
Neg logit contributions
lehem-0.272
RON-0.258
rans-0.253
rons-0.249
enance-0.247
Token her
Token ID607
Feature activation+7.75e-01

Pos logit contributions
jriwal+0.539
kefeller+0.489
 impulse+0.469
 turmoil+0.434
 reaction+0.424
Neg logit contributions
lehem-0.789
RON-0.747
rans-0.732
rons-0.720
enance-0.714
Token termination
Token ID19883
Feature activation+2.68e+00

Pos logit contributions
lehem+0.925
RON+0.887
rans+0.869
rons+0.857
enance+0.851
Neg logit contributions
jriwal-0.502
kefeller-0.454
 impulse-0.414
 turmoil-0.377
senal-0.362
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
lehem+2.619
RON+2.465
rans+2.421
rons+2.361
enance+2.347
Neg logit contributions
jriwal-2.308
kefeller-2.139
 impulse-2.032
 turmoil-1.908
senal-1.857
Token
Token ID198
Feature activation-4.10e-01

Pos logit contributions
jriwal+0.203
kefeller+0.187
 impulse+0.183
 turmoil+0.173
 reaction+0.170
Neg logit contributions
lehem-0.205
RON-0.192
rans-0.187
rons-0.183
enance-0.182
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
jriwal+0.377
kefeller+0.347
 impulse+0.338
 turmoil+0.320
 reaction+0.314
Neg logit contributions
lehem-0.381
RON-0.357
rans-0.348
rons-0.340
enance-0.337
Token
Token ID447
Feature activation-1.24e+00

Pos logit contributions
jriwal+0.162
kefeller+0.150
 impulse+0.147
 turmoil+0.139
 reaction+0.137
Neg logit contributions
lehem-0.146
RON-0.136
rans-0.132
rons-0.129
enance-0.128
Token
Token ID250
Feature activation+2.08e+00

Pos logit contributions
jriwal+1.278
kefeller+1.187
 impulse+1.162
 turmoil+1.107
 reaction+1.088
Neg logit contributions
lehem-1.013
RON-0.940
rans-0.914
rons-0.888
enance-0.880
Token is
Token ID318
Feature activation-2.39e+00

Pos logit contributions
lehem+0.035
RON+0.033
rans+0.033
rons+0.032
enance+0.032
Neg logit contributions
jriwal-0.028
kefeller-0.026
 impulse-0.025
 turmoil-0.023
 reaction-0.023
Token that
Token ID326
Feature activation+2.72e-01

Pos logit contributions
jriwal+1.849
kefeller+1.675
 impulse+1.630
 turmoil+1.529
 reaction+1.495
Neg logit contributions
lehem-2.552
RON-2.410
rans-2.358
rons-2.312
enance-2.292
Token the
Token ID262
Feature activation+2.03e-02

Pos logit contributions
lehem+0.282
RON+0.266
rans+0.262
rons+0.256
enance+0.255
Neg logit contributions
jriwal-0.219
kefeller-0.199
 impulse-0.192
 turmoil-0.179
 reaction-0.174
Token documents
Token ID4963
Feature activation+1.55e+00

Pos logit contributions
lehem+0.023
RON+0.022
rans+0.022
rons+0.021
enance+0.021
Neg logit contributions
jriwal-0.014
kefeller-0.013
 impulse-0.012
 turmoil-0.011
 reaction-0.011
Token may
Token ID743
Feature activation+3.67e+00

Pos logit contributions
lehem+1.446
RON+1.355
rans+1.330
rons+1.303
enance+1.294
Neg logit contributions
jriwal-1.416
kefeller-1.298
 impulse-1.253
 turmoil-1.178
 reaction-1.155
Token reveal
Token ID7766
Feature activation+3.08e+00

Pos logit contributions
lehem+3.574
RON+3.364
rans+3.340
rons+3.254
enance+3.213
Neg logit contributions
jriwal-3.135
kefeller-2.887
 impulse-2.691
senal-2.547
 turmoil-2.528
Token the
Token ID262
Feature activation+3.51e-02

Pos logit contributions
lehem+3.419
RON+3.253
rans+3.206
enance+3.141
rons+3.137
Neg logit contributions
jriwal-2.251
kefeller-1.983
 impulse-1.885
senal-1.715
 turmoil-1.699
Token kinds
Token ID6982
Feature activation+3.46e-01

Pos logit contributions
lehem+0.040
RON+0.038
rans+0.037
rons+0.036
enance+0.036
Neg logit contributions
jriwal-0.025
kefeller-0.022
 impulse-0.021
 turmoil-0.020
 reaction-0.019
Token of
Token ID286
Feature activation+2.10e+00

Pos logit contributions
lehem+0.312
RON+0.294
rans+0.287
rons+0.280
enance+0.278
Neg logit contributions
jriwal-0.325
kefeller-0.300
 impulse-0.291
 turmoil-0.275
 reaction-0.269
Token pressure
Token ID3833
Feature activation-4.68e+00

Pos logit contributions
lehem+2.468
RON+2.361
rans+2.325
rons+2.281
enance+2.272
Neg logit contributions
jriwal-1.381
kefeller-1.213
 impulse-1.119
senal-1.020
 turmoil-1.000
Token the
Token ID262
Feature activation+1.14e-01

Pos logit contributions
jriwal+2.720
kefeller+2.388
 impulse+2.344
 turmoil+2.156
 reaction+2.104
Neg logit contributions
lehem-5.869
RON-5.575
rans-5.473
rons-5.352
enance-5.341
TokenWe
Token ID1135
Feature activation+3.11e+00

Pos logit contributions
jriwal+0.069
kefeller+0.064
 impulse+0.062
 turmoil+0.059
 reaction+0.058
Neg logit contributions
lehem-0.061
RON-0.057
rans-0.055
rons-0.054
enance-0.054
Token pay
Token ID1414
Feature activation-3.81e+00

Pos logit contributions
lehem+2.867
RON+2.684
rans+2.630
rons+2.576
enance+2.543
Neg logit contributions
jriwal-2.843
kefeller-2.631
 impulse-2.552
 turmoil-2.420
 reaction-2.358
Token for
Token ID329
Feature activation-1.89e+00

Pos logit contributions
jriwal+2.104
 impulse+1.734
kefeller+1.732
 turmoil+1.596
 reaction+1.590
Neg logit contributions
lehem-4.866
RON-4.633
rans-4.626
rons-4.538
enance-4.408
Token your
Token ID534
Feature activation+3.46e-01

Pos logit contributions
jriwal+1.567
kefeller+1.487
 impulse+1.397
 turmoil+1.301
 reaction+1.271
Neg logit contributions
lehem-1.932
RON-1.801
rans-1.745
rons-1.728
enance-1.709
Token stories
Token ID3923
Feature activation-4.38e+00

Pos logit contributions
lehem+0.335
RON+0.313
rans+0.302
rons+0.297
enance+0.296
Neg logit contributions
jriwal-0.301
kefeller-0.281
 impulse-0.267
 turmoil-0.250
 reaction-0.245
Token!
Token ID0
Feature activation+1.18e+00

Pos logit contributions
jriwal+3.545
kefeller+3.227
 impulse+3.187
 turmoil+3.016
 reaction+2.950
Neg logit contributions
lehem-4.465
RON-4.141
rans-4.071
rons-3.990
enance-3.943
Token Do
Token ID2141
Feature activation+5.09e-01

Pos logit contributions
lehem+0.880
RON+0.811
rans+0.786
rons+0.761
enance+0.759
Neg logit contributions
jriwal-1.308
kefeller-1.221
 impulse-1.193
 turmoil-1.142
 reaction-1.123
Token you
Token ID345
Feature activation+1.81e+00

Pos logit contributions
lehem+0.471
RON+0.442
rans+0.430
rons+0.421
enance+0.416
Neg logit contributions
jriwal-0.469
kefeller-0.430
 impulse-0.420
 turmoil-0.398
 reaction-0.388
Token have
Token ID423
Feature activation+1.40e+00

Pos logit contributions
lehem+1.469
RON+1.365
rans+1.326
rons+1.290
enance+1.277
Neg logit contributions
jriwal-1.867
kefeller-1.737
 impulse-1.695
 turmoil-1.614
 reaction-1.587
Token a
Token ID257
Feature activation+8.19e-01

Pos logit contributions
lehem+1.381
RON+1.314
rans+1.287
enance+1.255
rons+1.244
Neg logit contributions
jriwal-1.183
kefeller-1.091
 impulse-1.035
 turmoil-0.960
 reaction-0.955
Token story
Token ID1621
Feature activation-3.89e+00

Pos logit contributions
lehem+1.009
RON+0.957
rans+0.941
rons+0.926
enance+0.919
Neg logit contributions
jriwal-0.505
kefeller-0.441
 impulse-0.428
 turmoil-0.395
 reaction-0.384
Token [
Token ID685
Feature activation+6.55e-01

Pos logit contributions
lehem+1.549
RON+1.457
rans+1.426
rons+1.397
enance+1.379
Neg logit contributions
jriwal-1.468
kefeller-1.350
 impulse-1.309
 turmoil-1.240
 reaction-1.212
Tokenfeel
Token ID36410
Feature activation-1.72e+00

Pos logit contributions
lehem+0.532
RON+0.494
rans+0.480
rons+0.466
enance+0.462
Neg logit contributions
jriwal-0.677
kefeller-0.630
 impulse-0.616
 turmoil-0.587
 reaction-0.577
Token]
Token ID60
Feature activation+6.12e-01

Pos logit contributions
jriwal+1.717
kefeller+1.588
 impulse+1.563
 turmoil+1.487
 reaction+1.463
Neg logit contributions
lehem-1.463
RON-1.357
rans-1.317
rons-1.284
enance-1.270
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
lehem+0.642
RON+0.608
rans+0.596
rons+0.583
enance+0.579
Neg logit contributions
jriwal-0.485
kefeller-0.441
 impulse-0.425
 turmoil-0.398
 reaction-0.388
Token little
Token ID1310
Feature activation-2.36e+00

Pos logit contributions
lehem+1.198
RON+1.134
rans+1.113
rons+1.083
enance+1.075
Neg logit contributions
jriwal-0.940
kefeller-0.857
 impulse-0.819
 turmoil-0.771
 reaction-0.747
Token bit
Token ID1643
Feature activation+1.97e+00

Pos logit contributions
jriwal+1.783
kefeller+1.601
 impulse+1.582
 turmoil+1.478
 reaction+1.443
Neg logit contributions
lehem-2.579
RON-2.430
rans-2.378
rons-2.333
enance-2.310
Token like
Token ID588
Feature activation+8.34e-02

Pos logit contributions
lehem+2.120
RON+2.014
rans+1.981
rons+1.937
enance+1.935
Neg logit contributions
jriwal-1.494
kefeller-1.365
 impulse-1.288
 turmoil-1.203
 reaction-1.173
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
lehem+0.082
RON+0.078
rans+0.076
rons+0.074
enance+0.074
Neg logit contributions
jriwal-0.071
kefeller-0.065
 impulse-0.064
 turmoil-0.060
 reaction-0.059
Token spinning
Token ID19493
Feature activation-3.19e+00

Pos logit contributions
lehem+1.256
RON+1.192
rans+1.168
rons+1.142
enance+1.135
Neg logit contributions
jriwal-0.848
kefeller-0.767
 impulse-0.730
 turmoil-0.679
 reaction-0.656
Token cup
Token ID6508
Feature activation+4.80e+00

Pos logit contributions
jriwal+2.253
kefeller+2.012
 impulse+1.971
 turmoil+1.830
 reaction+1.787
Neg logit contributions
lehem-3.632
RON-3.439
rans-3.371
rons-3.314
enance-3.289
Token at
Token ID379
Feature activation+2.63e+00

Pos logit contributions
lehem+4.350
RON+4.083
rans+4.051
rons+3.923
enance+3.860
Neg logit contributions
jriwal-4.373
kefeller-4.049
 impulse-3.864
 turmoil-3.666
senal-3.546
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
jriwal+1.695
kefeller+1.527
 impulse+1.487
 turmoil+1.387
 reaction+1.354
Neg logit contributions
lehem-2.544
RON-2.407
rans-2.356
rons-2.312
enance-2.295
Token little
Token ID1310
Feature activation-2.49e+00

Pos logit contributions
lehem+1.279
RON+1.210
rans+1.185
rons+1.163
enance+1.152
Neg logit contributions
jriwal-0.867
kefeller-0.781
 impulse-0.741
 turmoil-0.694
 reaction-0.670
Token fir
Token ID37979
Feature activation+1.66e+00

Pos logit contributions
jriwal+1.891
kefeller+1.709
 impulse+1.654
 turmoil+1.546
 reaction+1.508
Neg logit contributions
lehem-2.704
RON-2.557
rans-2.504
rons-2.457
enance-2.439
Tokenmer
Token ID647
Feature activation-2.04e+00

Pos logit contributions
lehem+1.913
RON+1.810
rans+1.787
rons+1.750
enance+1.735
Neg logit contributions
jriwal-1.147
kefeller-1.024
 impulse-0.984
 turmoil-0.914
 reaction-0.886
Token in
Token ID287
Feature activation-3.48e+00

Pos logit contributions
jriwal+1.630
kefeller+1.481
 impulse+1.437
 turmoil+1.349
 reaction+1.317
Neg logit contributions
lehem-2.128
RON-2.007
rans-1.965
rons-1.925
enance-1.911
Token texture
Token ID11743
Feature activation+1.62e+00

Pos logit contributions
jriwal+2.483
kefeller+2.228
 impulse+2.156
 turmoil+2.004
 reaction+1.951
Neg logit contributions
lehem-3.936
RON-3.728
rans-3.655
rons-3.587
enance-3.563
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
lehem+1.615
RON+1.515
rans+1.494
rons+1.461
enance+1.449
Neg logit contributions
jriwal-1.373
kefeller-1.266
 impulse-1.212
 turmoil-1.139
 reaction-1.101
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
lehem+0.174
RON+0.162
rans+0.158
rons+0.154
enance+0.153
Neg logit contributions
jriwal-0.189
kefeller-0.175
 impulse-0.171
 turmoil-0.162
 reaction-0.159
Token
Token ID198
Feature activation-2.67e-02

Pos logit contributions
jriwal+0.197
kefeller+0.182
 impulse+0.177
 turmoil+0.168
 reaction+0.164
Neg logit contributions
lehem-0.197
RON-0.185
rans-0.180
rons-0.176
enance-0.174
TokenSun
Token ID16012
Feature activation-9.09e-02

Pos logit contributions
jriwal+0.026
kefeller+0.024
 impulse+0.024
 turmoil+0.023
 reaction+0.022
Neg logit contributions
lehem-0.023
RON-0.021
rans-0.021
rons-0.020
enance-0.020
Tokenflower
Token ID25547
Feature activation+2.27e+00

Pos logit contributions
jriwal+0.090
kefeller+0.083
 impulse+0.081
 turmoil+0.077
 reaction+0.076
Neg logit contributions
lehem-0.078
RON-0.073
rans-0.071
rons-0.069
enance-0.068
Token isn
Token ID2125
Feature activation-3.72e+00

Pos logit contributions
jriwal+1.570
kefeller+1.430
 impulse+1.401
 turmoil+1.320
 reaction+1.294
Neg logit contributions
lehem-1.858
RON-1.745
rans-1.703
rons-1.669
enance-1.655
Token
Token ID447
Feature activation-1.41e+00

Pos logit contributions
jriwal+3.357
kefeller+3.103
 impulse+3.046
 turmoil+2.900
 reaction+2.873
Neg logit contributions
lehem-3.448
RON-3.158
rans-3.080
rons-3.042
enance-2.982
Token
Token ID247
Feature activation-1.76e+00

Pos logit contributions
jriwal+1.643
kefeller+1.536
 impulse+1.516
 turmoil+1.455
 reaction+1.434
Neg logit contributions
lehem-0.952
RON-0.862
rans-0.832
rons-0.810
enance-0.793
Tokent
Token ID83
Feature activation+4.28e+00

Pos logit contributions
jriwal+1.956
kefeller+1.819
 impulse+1.788
 turmoil+1.715
 reaction+1.691
Neg logit contributions
lehem-1.297
RON-1.179
rans-1.122
rons-1.104
enance-1.079
Token just
Token ID655
Feature activation+3.33e-01

Pos logit contributions
lehem+4.378
RON+4.168
rans+4.114
rons+4.002
enance+3.946
Neg logit contributions
jriwal-3.417
kefeller-3.113
 impulse-2.911
 turmoil-2.734
 reaction-2.657
Token full
Token ID1336
Feature activation-1.03e+00

Pos logit contributions
lehem+0.353
RON+0.336
rans+0.329
rons+0.322
enance+0.318
Neg logit contributions
jriwal-0.261
kefeller-0.237
 impulse-0.226
 turmoil-0.212
 reaction-0.206
Token of
Token ID286
Feature activation+1.99e+00

Pos logit contributions
jriwal+0.920
kefeller+0.845
 impulse+0.826
 turmoil+0.782
 reaction+0.767
Neg logit contributions
lehem-0.974
RON-0.911
rans-0.889
rons-0.870
enance-0.862
Token Typh
Token ID27282
Feature activation+5.47e+00

Pos logit contributions
lehem+2.298
RON+2.200
rans+2.153
rons+2.122
enance+2.091
Neg logit contributions
jriwal-1.354
kefeller-1.210
 impulse-1.127
 turmoil-1.039
 reaction-1.010
Tokenon
Token ID261
Feature activation-1.58e+00

Pos logit contributions
lehem+2.998
RON+2.742
rons+2.623
rans+2.620
enance+2.479
Neg logit contributions
jriwal-6.998
kefeller-6.517
 impulse-6.393
 turmoil-6.211
 reaction-6.072
Token.
Token ID13
Feature activation+6.00e-01

Pos logit contributions
jriwal+1.191
kefeller+1.075
 impulse+1.043
 turmoil+0.974
 reaction+0.950
Neg logit contributions
lehem-1.723
RON-1.629
rans-1.596
rons-1.565
enance-1.553
Token There
Token ID1318
Feature activation+1.62e+00

Pos logit contributions
lehem+0.530
RON+0.495
rans+0.482
rons+0.470
enance+0.466
Neg logit contributions
jriwal-0.577
kefeller-0.533
 impulse-0.521
 turmoil-0.495
 reaction-0.486
Token to
Token ID284
Feature activation+1.67e+00

Pos logit contributions
lehem+0.112
RON+0.106
rans+0.104
rons+0.101
enance+0.101
Neg logit contributions
jriwal-0.093
kefeller-0.085
 impulse-0.082
 turmoil-0.077
 reaction-0.075
Token say
Token ID910
Feature activation+1.32e+00

Pos logit contributions
lehem+1.682
RON+1.588
rans+1.554
rons+1.520
enance+1.510
Neg logit contributions
jriwal-1.385
kefeller-1.272
 impulse-1.220
 turmoil-1.150
 reaction-1.121
Token
Token ID564
Feature activation+4.54e+00

Pos logit contributions
lehem+1.325
RON+1.248
rans+1.223
rons+1.193
enance+1.189
Neg logit contributions
jriwal-1.102
kefeller-1.016
 impulse-0.977
 turmoil-0.921
 reaction-0.897
Token
Token ID246
Feature activation-3.15e+00

Pos logit contributions
lehem+2.819
RON+2.637
rans+2.565
rons+2.412
enance+2.393
Neg logit contributions
jriwal-5.453
kefeller-5.167
 impulse-5.012
 turmoil-4.823
 reaction-4.748
TokenYes
Token ID5297
Feature activation-5.74e-01

Pos logit contributions
jriwal+2.828
kefeller+2.582
 impulse+2.543
 turmoil+2.403
 reaction+2.373
Neg logit contributions
lehem-2.913
RON-2.709
rans-2.628
rons-2.609
enance-2.580
Token
Token ID447
Feature activation-1.34e+00

Pos logit contributions
jriwal+0.503
kefeller+0.462
 impulse+0.450
 turmoil+0.425
 reaction+0.416
Neg logit contributions
lehem-0.557
RON-0.522
rans-0.510
rons-0.499
enance-0.495
Token
Token ID247
Feature activation-1.27e+00

Pos logit contributions
jriwal+1.554
kefeller+1.452
 impulse+1.431
 turmoil+1.370
 reaction+1.351
Neg logit contributions
lehem-0.923
RON-0.842
rans-0.811
rons-0.787
enance-0.773
Token to
Token ID284
Feature activation+1.83e+00

Pos logit contributions
jriwal+1.124
kefeller+1.028
 impulse+1.009
 turmoil+0.952
 reaction+0.935
Neg logit contributions
lehem-1.219
RON-1.145
rans-1.110
rons-1.088
enance-1.077
Token life
Token ID1204
Feature activation-6.22e-01

Pos logit contributions
lehem+1.967
RON+1.863
rans+1.827
rons+1.786
enance+1.781
Neg logit contributions
jriwal-1.397
kefeller-1.273
 impulse-1.209
 turmoil-1.135
 reaction-1.107
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
jriwal+0.534
kefeller+0.488
 impulse+0.476
 turmoil+0.449
 reaction+0.439
Neg logit contributions
lehem-0.614
RON-0.577
rans-0.564
rons-0.552
enance-0.547
Token no
Token ID645
Feature activation-2.05e+00

Pos logit contributions
lehem+0.342
RON+0.322
rans+0.316
rons+0.310
enance+0.309
Neg logit contributions
jriwal-0.252
kefeller-0.229
 impulse-0.219
 turmoil-0.205
 reaction-0.200
Token a
Token ID257
Feature activation+9.74e-01

Pos logit contributions
jriwal+0.729
kefeller+0.660
 impulse+0.647
 turmoil+0.608
 reaction+0.593
Neg logit contributions
lehem-1.002
RON-0.946
rans-0.924
rons-0.906
enance-0.901
Token sc
Token ID629
Feature activation+3.26e-01

Pos logit contributions
lehem+1.156
RON+1.103
rans+1.087
rons+1.064
enance+1.054
Neg logit contributions
jriwal-0.640
kefeller-0.568
 impulse-0.533
 turmoil-0.486
 reaction-0.469
Tokenuffle
Token ID18137
Feature activation+6.57e-01

Pos logit contributions
lehem+0.345
RON+0.326
rans+0.320
rons+0.313
enance+0.310
Neg logit contributions
jriwal-0.257
kefeller-0.233
 impulse-0.227
 turmoil-0.212
 reaction-0.207
Token,
Token ID11
Feature activation-2.97e-01

Pos logit contributions
lehem+0.675
RON+0.638
rans+0.625
rons+0.612
enance+0.606
Neg logit contributions
jriwal-0.538
kefeller-0.491
 impulse-0.471
 turmoil-0.441
 reaction-0.430
Token with
Token ID351
Feature activation+4.47e-01

Pos logit contributions
jriwal+0.236
kefeller+0.215
 impulse+0.208
 turmoil+0.195
 reaction+0.190
Neg logit contributions
lehem-0.311
RON-0.294
rans-0.288
rons-0.282
enance-0.279
Token Hew
Token ID30446
Feature activation-5.84e-01

Pos logit contributions
lehem+0.444
RON+0.418
rans+0.409
rons+0.401
enance+0.396
Neg logit contributions
jriwal-0.379
kefeller-0.347
 impulse-0.336
 turmoil-0.317
 reaction-0.310
Tokenett
Token ID3087
Feature activation+2.84e+00

Pos logit contributions
jriwal+0.409
kefeller+0.366
 impulse+0.355
 turmoil+0.329
 reaction+0.320
Neg logit contributions
lehem-0.669
RON-0.634
rans-0.622
rons-0.610
enance-0.606
Token getting
Token ID1972
Feature activation-2.00e-01

Pos logit contributions
lehem+3.093
RON+2.960
rans+2.908
rons+2.862
enance+2.811
Neg logit contributions
jriwal-2.123
kefeller-1.963
 impulse-1.791
 turmoil-1.665
senal-1.613
Token hit
Token ID2277
Feature activation+1.49e+00

Pos logit contributions
jriwal+0.148
kefeller+0.133
 impulse+0.128
 turmoil+0.120
 reaction+0.117
Neg logit contributions
lehem-0.221
RON-0.209
rans-0.205
rons-0.202
enance-0.200
Token in
Token ID287
Feature activation-3.88e+00

Pos logit contributions
lehem+1.546
RON+1.456
rans+1.431
rons+1.404
enance+1.387
Neg logit contributions
jriwal-1.203
kefeller-1.098
 impulse-1.058
 turmoil-0.993
 reaction-0.967
Token the
Token ID262
Feature activation-9.14e-02

Pos logit contributions
jriwal+2.907
kefeller+2.610
 impulse+2.563
 turmoil+2.395
 reaction+2.362
Neg logit contributions
lehem-4.240
RON-4.010
rans-3.914
rons-3.823
enance-3.823
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
jriwal+0.234
kefeller+0.215
 impulse+0.210
 turmoil+0.198
 reaction+0.194
Neg logit contributions
lehem-0.231
RON-0.217
rans-0.212
rons-0.207
enance-0.205
TokenThings
Token ID22248
Feature activation-2.57e-01

Pos logit contributions
jriwal+0.109
kefeller+0.101
 impulse+0.099
 turmoil+0.094
 reaction+0.093
Neg logit contributions
lehem-0.093
RON-0.086
rans-0.084
rons-0.082
enance-0.081
Token started
Token ID2067
Feature activation-8.87e-01

Pos logit contributions
jriwal+0.207
kefeller+0.188
 impulse+0.182
 turmoil+0.170
 reaction+0.165
Neg logit contributions
lehem-0.268
RON-0.253
rans-0.249
rons-0.243
enance-0.240
Token to
Token ID284
Feature activation+1.59e+00

Pos logit contributions
jriwal+0.597
kefeller+0.532
 impulse+0.510
 turmoil+0.471
 reaction+0.456
Neg logit contributions
lehem-1.040
RON-0.989
rans-0.973
rons-0.953
enance-0.946
Token become
Token ID1716
Feature activation+1.85e+00

Pos logit contributions
lehem+1.528
RON+1.434
rans+1.418
rons+1.378
enance+1.361
Neg logit contributions
jriwal-1.390
kefeller-1.279
 impulse-1.220
 turmoil-1.147
senal-1.124
Token confusing
Token ID15337
Feature activation-7.00e-01

Pos logit contributions
lehem+2.040
RON+1.933
rans+1.905
rons+1.863
enance+1.847
Neg logit contributions
jriwal-1.360
kefeller-1.231
 impulse-1.159
 turmoil-1.070
 reaction-1.043
Token here
Token ID994
Feature activation-4.36e-01

Pos logit contributions
jriwal+0.557
kefeller+0.506
 impulse+0.490
 turmoil+0.459
 reaction+0.448
Neg logit contributions
lehem-0.737
RON-0.695
rans-0.681
rons-0.667
enance-0.662
Token for
Token ID329
Feature activation-1.36e+00

Pos logit contributions
jriwal+0.357
kefeller+0.325
 impulse+0.316
 turmoil+0.297
 reaction+0.290
Neg logit contributions
lehem-0.448
RON-0.422
rans-0.412
rons-0.404
enance-0.401
Token two
Token ID734
Feature activation+6.20e-01

Pos logit contributions
jriwal+1.035
kefeller+0.935
 impulse+0.909
 turmoil+0.849
 reaction+0.829
Neg logit contributions
lehem-1.471
RON-1.390
rans-1.361
rons-1.335
enance-1.325
Token reasons
Token ID3840
Feature activation-3.68e-01

Pos logit contributions
lehem+0.702
RON+0.667
rans+0.656
rons+0.645
enance+0.638
Neg logit contributions
jriwal-0.442
kefeller-0.397
 impulse-0.378
 turmoil-0.353
 reaction-0.340
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
jriwal+0.317
kefeller+0.291
 impulse+0.282
 turmoil+0.266
 reaction+0.260
Neg logit contributions
lehem-0.362
RON-0.340
rans-0.332
rons-0.325
enance-0.322
Token exceptions
Token ID13269
Feature activation+4.07e+00

Pos logit contributions
lehem+3.503
RON+3.280
rans+3.219
rons+3.145
enance+3.116
Neg logit contributions
jriwal-3.623
kefeller-3.354
 impulse-3.142
senal-2.935
 turmoil-2.925
Token,
Token ID11
Feature activation+4.35e-02

Pos logit contributions
lehem+3.893
RON+3.634
rans+3.568
enance+3.474
rons+3.456
Neg logit contributions
jriwal-3.607
kefeller-3.347
 impulse-3.209
 turmoil-2.998
 reaction-2.921
Token public
Token ID1171
Feature activation-9.23e-01

Pos logit contributions
lehem+0.044
RON+0.041
rans+0.040
rons+0.039
enance+0.039
Neg logit contributions
jriwal-0.037
kefeller-0.034
 impulse-0.032
 turmoil-0.030
 reaction-0.030
Token reaction
Token ID6317
Feature activation-4.31e+00

Pos logit contributions
jriwal+0.630
kefeller+0.562
 impulse+0.542
 turmoil+0.501
 reaction+0.487
Neg logit contributions
lehem-1.075
RON-1.020
rans-1.001
rons-0.982
enance-0.976
Token was
Token ID373
Feature activation-8.71e-01

Pos logit contributions
jriwal+2.971
kefeller+2.626
 impulse+2.580
 turmoil+2.416
 reaction+2.374
Neg logit contributions
lehem-4.958
RON-4.678
rans-4.574
rons-4.480
enance-4.465
Token swift
Token ID14622
Feature activation-2.58e+00

Pos logit contributions
jriwal+0.667
kefeller+0.604
 impulse+0.576
 turmoil+0.537
 reaction+0.521
Neg logit contributions
lehem-0.944
RON-0.892
rans-0.877
rons-0.859
enance-0.854
Token and
Token ID290
Feature activation-2.96e+00

Pos logit contributions
jriwal+2.088
kefeller+1.897
 impulse+1.853
 turmoil+1.741
 reaction+1.711
Neg logit contributions
lehem-2.663
RON-2.508
rans-2.449
rons-2.401
enance-2.379
Token harsh
Token ID11859
Feature activation-5.23e+00

Pos logit contributions
jriwal+2.000
kefeller+1.785
 impulse+1.747
 turmoil+1.620
 reaction+1.584
Neg logit contributions
lehem-3.451
RON-3.274
rans-3.206
rons-3.150
enance-3.128
Token.
Token ID13
Feature activation+4.98e-01

Pos logit contributions
jriwal+4.121
kefeller+3.702
 impulse+3.693
 turmoil+3.468
 reaction+3.465
Neg logit contributions
lehem-5.441
RON-5.119
rans-4.961
rons-4.884
enance-4.809
Token The
Token ID383
Feature activation+1.63e-01

Pos logit contributions
lehem+0.452
RON+0.423
rans+0.412
rons+0.402
enance+0.399
Neg logit contributions
jriwal-0.469
kefeller-0.432
 impulse-0.420
 turmoil-0.398
 reaction-0.389
Token D
Token ID360
Feature activation+3.54e+00

Pos logit contributions
lehem+0.176
RON+0.167
rans+0.164
rons+0.160
enance+0.159
Neg logit contributions
jriwal-0.124
kefeller-0.113
 impulse-0.107
 turmoil-0.100
 reaction-0.097
Token
Token ID198
Feature activation+4.20e-03

Pos logit contributions
lehem+2.526
RON+2.372
rans+2.313
enance+2.263
rons+2.261
Neg logit contributions
jriwal-2.247
kefeller-2.055
 impulse-1.995
 turmoil-1.881
 reaction-1.837
Token
Token ID198
Feature activation+1.61e-01

Pos logit contributions
lehem+0.004
RON+0.004
rans+0.003
rons+0.003
enance+0.003
Neg logit contributions
jriwal-0.004
kefeller-0.004
 impulse-0.004
 turmoil-0.003
 reaction-0.003
TokenM
Token ID44
Feature activation+9.92e-01

Pos logit contributions
lehem+0.135
RON+0.125
rans+0.122
rons+0.119
enance+0.118
Neg logit contributions
jriwal-0.162
kefeller-0.150
 impulse-0.147
 turmoil-0.140
 reaction-0.138
Tokenasure
Token ID5015
Feature activation+2.98e+00

Pos logit contributions
lehem+0.922
RON+0.862
rans+0.847
rons+0.830
enance+0.817
Neg logit contributions
jriwal-0.907
kefeller-0.831
 impulse-0.817
 turmoil-0.774
 reaction-0.756
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
lehem+2.811
RON+2.645
rans+2.607
rons+2.538
enance+2.506
Neg logit contributions
jriwal-2.678
kefeller-2.468
 impulse-2.385
 turmoil-2.248
 reaction-2.173
Token R
Token ID371
Feature activation-7.94e+00

Pos logit contributions
jriwal+0.147
kefeller+0.136
 impulse+0.133
 turmoil+0.126
 reaction+0.124
Neg logit contributions
lehem-0.147
RON-0.137
rans-0.134
rons-0.131
enance-0.130
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
jriwal+5.738
kefeller+5.261
 impulse+5.234
 turmoil+4.887
 reaction+4.823
Neg logit contributions
lehem-8.381
RON-7.810
rans-7.637
enance-7.460
rons-7.412
Token H
Token ID367
Feature activation-3.16e+00

Pos logit contributions
lehem+1.278
RON+1.197
rans+1.160
rons+1.132
enance+1.122
Neg logit contributions
jriwal-1.444
kefeller-1.329
 impulse-1.294
 turmoil-1.230
 reaction-1.204
Token.,
Token ID1539
Feature activation+6.06e-01

Pos logit contributions
jriwal+2.664
kefeller+2.450
 impulse+2.390
 turmoil+2.240
 reaction+2.215
Neg logit contributions
lehem-3.105
RON-2.923
rans-2.840
enance-2.768
rons-2.767
Token Al
Token ID978
Feature activation-1.17e+00

Pos logit contributions
lehem+0.571
RON+0.534
rans+0.521
rons+0.510
enance+0.506
Neg logit contributions
jriwal-0.551
kefeller-0.504
 impulse-0.492
 turmoil-0.465
 reaction-0.454
Tokenlee
Token ID7197
Feature activation-1.07e+00

Pos logit contributions
jriwal+1.071
kefeller+0.986
 impulse+0.962
 turmoil+0.910
 reaction+0.893
Neg logit contributions
lehem-1.091
RON-1.022
rans-0.996
rons-0.973
enance-0.965
Token rest
Token ID1334
Feature activation+1.14e+00

Pos logit contributions
lehem+4.643
RON+4.396
rons+4.300
rans+4.291
enance+4.168
Neg logit contributions
jriwal-3.844
kefeller-3.548
 impulse-3.284
 turmoil-3.087
 reaction-2.993
Tokenants
Token ID1187
Feature activation+4.29e+00

Pos logit contributions
lehem+0.832
RON+0.765
rans+0.743
rons+0.721
enance+0.712
Neg logit contributions
jriwal-1.276
kefeller-1.194
 impulse-1.169
 turmoil-1.120
 reaction-1.101
Token.
Token ID13
Feature activation+5.10e-01

Pos logit contributions
lehem+4.207
RON+3.988
rans+3.896
rons+3.874
enance+3.804
Neg logit contributions
jriwal-3.630
kefeller-3.357
 impulse-3.131
 turmoil-2.941
senal-2.857
TokenPar
Token ID10044
Feature activation+3.30e+00

Pos logit contributions
lehem+0.468
RON+0.439
rans+0.427
rons+0.418
enance+0.414
Neg logit contributions
jriwal-0.474
kefeller-0.436
 impulse-0.425
 turmoil-0.403
 reaction-0.395
Token le
Token ID443
Feature activation-2.13e+00

Pos logit contributions
lehem+3.283
RON+3.107
rans+3.030
rons+2.990
enance+2.945
Neg logit contributions
jriwal-2.780
kefeller-2.566
 impulse-2.446
 turmoil-2.304
 reaction-2.232
Token pr
Token ID778
Feature activation-6.51e+00

Pos logit contributions
jriwal+1.719
kefeller+1.557
 impulse+1.527
 turmoil+1.437
 reaction+1.409
Neg logit contributions
lehem-2.201
RON-2.068
rans-2.024
rons-1.978
enance-1.971
Tokenés
Token ID20954
Feature activation-3.34e-01

Pos logit contributions
jriwal+5.613
kefeller+5.066
 impulse+5.011
 turmoil+4.714
 reaction+4.640
Neg logit contributions
lehem-6.182
RON-5.799
rans-5.584
rons-5.412
enance-5.345
Tokenent
Token ID298
Feature activation+6.29e+00

Pos logit contributions
jriwal+0.353
kefeller+0.329
 impulse+0.322
 turmoil+0.308
 reaction+0.303
Neg logit contributions
lehem-0.263
RON-0.243
rans-0.237
rons-0.231
enance-0.229
Token act
Token ID719
Feature activation+3.77e+00

Pos logit contributions
lehem+5.982
RON+5.725
rans+5.627
rons+5.573
enance+5.513
Neg logit contributions
jriwal-5.395
kefeller-5.047
 impulse-4.642
 turmoil-4.416
senal-4.274
Tokene
Token ID68
Feature activation-1.01e+00

Pos logit contributions
lehem+3.633
RON+3.435
rans+3.381
rons+3.325
enance+3.310
Neg logit contributions
jriwal-3.289
kefeller-3.032
 impulse-2.890
 turmoil-2.735
 reaction-2.657
Token,
Token ID11
Feature activation+6.33e-02

Pos logit contributions
jriwal+0.845
kefeller+0.770
 impulse+0.751
 turmoil+0.707
 reaction+0.692
Neg logit contributions
lehem-1.023
RON-0.962
rans-0.941
rons-0.921
enance-0.913
Token city
Token ID1748
Feature activation+2.04e+00

Pos logit contributions
jriwal+0.934
kefeller+0.847
 impulse+0.811
 turmoil+0.757
 reaction+0.738
Neg logit contributions
lehem-1.338
RON-1.269
rans-1.242
rons-1.216
enance-1.208
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
lehem+2.027
RON+1.924
rans+1.891
rons+1.849
enance+1.821
Neg logit contributions
jriwal-1.708
kefeller-1.569
 impulse-1.495
 turmoil-1.401
 reaction-1.369
Token This
Token ID770
Feature activation-3.20e+00

Pos logit contributions
jriwal+1.083
kefeller+0.999
 impulse+0.984
 turmoil+0.935
 reaction+0.921
Neg logit contributions
lehem-1.036
RON-0.963
rans-0.940
rons-0.918
enance-0.911
Token series
Token ID2168
Feature activation+1.96e-01

Pos logit contributions
jriwal+2.370
kefeller+2.129
 impulse+2.091
 turmoil+1.947
 reaction+1.905
Neg logit contributions
lehem-3.526
RON-3.326
rans-3.261
rons-3.195
enance-3.175
Token of
Token ID286
Feature activation+5.48e-01

Pos logit contributions
lehem+0.195
RON+0.184
rans+0.180
rons+0.176
enance+0.175
Neg logit contributions
jriwal-0.167
kefeller-0.153
 impulse-0.148
 turmoil-0.139
 reaction-0.136
Token blog
Token ID4130
Feature activation-6.56e+00

Pos logit contributions
lehem+0.612
RON+0.582
rans+0.571
rons+0.562
enance+0.554
Neg logit contributions
jriwal-0.396
kefeller-0.359
 impulse-0.338
 turmoil-0.316
 reaction-0.305
Token posts
Token ID6851
Feature activation-3.23e+00

Pos logit contributions
jriwal+4.687
 impulse+4.133
kefeller+4.133
 reaction+3.858
 turmoil+3.848
Neg logit contributions
lehem-7.222
RON-6.773
rans-6.584
enance-6.543
rons-6.400
Token is
Token ID318
Feature activation-3.87e+00

Pos logit contributions
jriwal+2.741
kefeller+2.498
 impulse+2.459
 turmoil+2.318
 reaction+2.278
Neg logit contributions
lehem-3.211
RON-3.017
rans-2.939
rons-2.872
enance-2.857
Token an
Token ID281
Feature activation-1.17e+00

Pos logit contributions
jriwal+2.904
kefeller+2.606
 impulse+2.567
 turmoil+2.391
 reaction+2.348
Neg logit contributions
lehem-4.230
RON-3.991
rans-3.899
rons-3.827
enance-3.798
Token introduction
Token ID9793
Feature activation-5.61e-01

Pos logit contributions
jriwal+0.628
kefeller+0.554
 impulse+0.497
 turmoil+0.463
 reaction+0.430
Neg logit contributions
lehem-1.525
RON-1.469
rans-1.447
rons-1.427
enance-1.412
Token to
Token ID284
Feature activation+3.92e-01

Pos logit contributions
jriwal+0.368
kefeller+0.329
 impulse+0.314
 turmoil+0.290
 reaction+0.279
Neg logit contributions
lehem-0.666
RON-0.634
rans-0.622
rons-0.612
enance-0.607
Tokenort
Token ID419
Feature activation+4.41e+00

Pos logit contributions
lehem+0.093
RON+0.087
rans+0.084
rons+0.082
enance+0.081
Neg logit contributions
jriwal-0.105
kefeller-0.097
 impulse-0.095
 turmoil-0.090
 reaction-0.089
Tokenic
Token ID291
Feature activation-2.25e+00

Pos logit contributions
lehem+3.295
RON+3.052
rans+3.050
rons+2.919
enance+2.901
Neg logit contributions
jriwal-4.778
kefeller-4.382
 impulse-4.322
 turmoil-4.156
 reaction-4.028
Tokenotrop
Token ID34248
Feature activation+8.77e-01

Pos logit contributions
jriwal+2.110
kefeller+1.962
 impulse+1.914
 turmoil+1.811
 reaction+1.783
Neg logit contributions
lehem-2.028
RON-1.887
rans-1.829
enance-1.793
rons-1.784
Tokenin
Token ID259
Feature activation-5.73e+00

Pos logit contributions
lehem+0.667
RON+0.615
rans+0.598
rons+0.581
enance+0.574
Neg logit contributions
jriwal-0.951
kefeller-0.887
 impulse-0.868
 turmoil-0.831
 reaction-0.816
Token-
Token ID12
Feature activation+4.49e+00

Pos logit contributions
jriwal+4.463
 impulse+4.069
kefeller+4.041
 reaction+3.814
 turmoil+3.806
Neg logit contributions
lehem-5.978
RON-5.530
rans-5.403
enance-5.360
rons-5.325
Tokenre
Token ID260
Feature activation-8.56e+00

Pos logit contributions
lehem+2.633
RON+2.436
rans+2.380
rons+2.229
enance+2.122
Neg logit contributions
jriwal-5.601
kefeller-5.271
 impulse-5.095
 turmoil-4.939
 reaction-4.827
Tokenleasing
Token ID48764
Feature activation-6.73e-02

Pos logit contributions
jriwal+6.418
 impulse+5.916
kefeller+5.682
 turmoil+5.393
 reaction+5.310
Neg logit contributions
lehem-8.920
RON-8.481
rans-8.116
rons-8.048
enance-8.042
Token factor
Token ID5766
Feature activation-5.99e-01

Pos logit contributions
jriwal+0.042
kefeller+0.037
 impulse+0.036
 turmoil+0.033
 reaction+0.032
Neg logit contributions
lehem-0.082
RON-0.078
rans-0.077
rons-0.076
enance-0.075
Token (
Token ID357
Feature activation+3.51e-01

Pos logit contributions
jriwal+0.521
kefeller+0.477
 impulse+0.463
 turmoil+0.438
 reaction+0.428
Neg logit contributions
lehem-0.585
RON-0.550
rans-0.538
rons-0.526
enance-0.520
TokenCR
Token ID9419
Feature activation-8.68e+00

Pos logit contributions
lehem+0.333
RON+0.310
rans+0.303
rons+0.297
enance+0.295
Neg logit contributions
jriwal-0.316
kefeller-0.290
 impulse-0.283
 turmoil-0.268
 reaction-0.263
TokenF
Token ID37
Feature activation-2.23e+00

Pos logit contributions
jriwal+7.244
kefeller+6.831
 impulse+6.807
 reaction+6.395
 turmoil+6.326
Neg logit contributions
lehem-8.410
RON-7.532
rons-7.300
rans-7.232
enance-7.130
Token I
Token ID314
Feature activation+2.10e+00

Pos logit contributions
lehem+1.300
RON+1.234
rans+1.207
rons+1.188
enance+1.175
Neg logit contributions
jriwal-1.068
kefeller-0.980
 impulse-0.921
 turmoil-0.872
 reaction-0.844
Token refer
Token ID3522
Feature activation-3.45e-02

Pos logit contributions
lehem+2.286
RON+2.176
rans+2.148
rons+2.108
enance+2.091
Neg logit contributions
jriwal-1.565
kefeller-1.420
 impulse-1.328
 turmoil-1.251
 reaction-1.212
Token to
Token ID284
Feature activation+1.69e+00

Pos logit contributions
jriwal+0.023
kefeller+0.020
 impulse+0.019
 turmoil+0.018
 reaction+0.017
Neg logit contributions
lehem-0.041
RON-0.039
rans-0.038
rons-0.038
enance-0.038
Token
Token ID564
Feature activation+4.23e+00

Pos logit contributions
lehem+1.825
RON+1.733
rans+1.700
rons+1.671
enance+1.667
Neg logit contributions
jriwal-1.288
kefeller-1.168
 impulse-1.101
 turmoil-1.036
 reaction-0.998
Token
Token ID250
Feature activation+1.56e+00

Pos logit contributions
lehem+2.272
RON+2.098
rans+2.022
enance+1.925
rons+1.885
Neg logit contributions
jriwal-5.480
kefeller-5.203
 impulse-5.007
 turmoil-4.827
 reaction-4.768
TokenR
Token ID49
Feature activation-8.70e+00

Pos logit contributions
lehem+1.316
RON+1.230
rans+1.197
rons+1.162
enance+1.151
Neg logit contributions
jriwal-1.559
kefeller-1.449
 impulse-1.413
 turmoil-1.344
 reaction-1.317
Tokenalph
Token ID17307
Feature activation+3.28e+00

Pos logit contributions
jriwal+8.073
kefeller+7.487
 impulse+7.353
 reaction+6.976
 turmoil+6.953
Neg logit contributions
lehem-7.462
RON-6.944
rans-6.689
rons-6.470
enance-6.332
Token
Token ID447
Feature activation-2.13e+00

Pos logit contributions
lehem+2.926
RON+2.733
rans+2.660
enance+2.607
rons+2.597
Neg logit contributions
jriwal-3.129
kefeller-2.840
 impulse-2.772
 turmoil-2.620
 reaction-2.546
Token
Token ID251
Feature activation+4.10e+00

Pos logit contributions
jriwal+2.252
kefeller+2.092
 impulse+2.057
 turmoil+1.969
 reaction+1.935
Neg logit contributions
lehem-1.675
RON-1.545
rans-1.500
rons-1.463
enance-1.439
Token,
Token ID11
Feature activation-3.50e-01

Pos logit contributions
lehem+4.033
RON+3.817
rans+3.734
rons+3.685
enance+3.655
Neg logit contributions
jriwal-3.469
kefeller-3.173
 impulse-3.026
 turmoil-2.840
 reaction-2.753
Token the
Token ID262
Feature activation-8.46e-02

Pos logit contributions
jriwal+0.289
kefeller+0.264
 impulse+0.255
 turmoil+0.240
 reaction+0.234
Neg logit contributions
lehem-0.357
RON-0.336
rans-0.329
rons-0.322
enance-0.320