TOP ACTIVATIONS
MAX = 4.933

projectile flies further , she deals more stun on her attacks
many economic indicators that inter play to create a judgement on
planned to happen in two phases , according to project manager
Airbnb is disrupting hospitality . https :// www . bel fast
drug addict . The common denomin ator throughout these disparate roles
they can prepare for their client s upcoming trial
ve developed parad ig ms based on such limited
female comic book characters do indeed have staying power , then
y aku za group par aded as many as 100 gang
is impossible to dis amb ig uate any single measurement ,
s opportunity to decentral ize . Both
s a narrow , par och ial my country
as could be , and certainly will look great in a
the S , can now line up much tighter , across
said the decision gives his client a new avenue to apply
! Sign up for our Email News letters here . <|endoftext|>
in an eight - man front , but still overwhelmed at
D . S . ( 1984 ). P iers - Harris
free agent from Denver ,- certainly looks the part at 6
") $ i = 1 Try { for ($ i ;

MIN ACTIVATIONS
MIN = -5.151

day ( and eliminate sn acking ). The easiest and best
he offered a tweet of condol ence to those affected by
a giant lizard that sw am in shallow ocean waters .
time and attention to the bell es of the evening ,
CPUs and memory ( Intel VT - x , AMD -
disappointed but Canadians as a whole are , said
ings . This is a must visit temple for anyone interested
for CPUs and memory ( Intel VT - x , AMD
greenhouse gases such as nit rous ox ides . The new
alling together in a cr um pled mess of mutual uncertainty
two counts of violation of ignition inter lock driver 's license
s hands . The score is 44 for one .
re both pure goal score rs . If you want
finding the back of the net . In addition to the
ant ins , Survivor Heroes vs . Vill ains , Survivor
virus quickly , a doctor must send blood taken during the
Del Sur featuring Coach ( Surv iv or T oc ant
at the sm ok est ack , natural gas is a
stand - off and scr um - half respectively .
Remember , though , that thanks to Amazon s

INTERVAL 2.412 - 4.933
CONTAINS 0.275%

room , a pair of Silver Phant oms should acqu it
TW O WOM EN . It s
ap . parse _ args ()) # initialize a rectangular and
Appeal 's 3 - 0 ruling agreed with a federal judge
, or about three per cent of the 9 , 204

INTERVAL -0.109 - 2.412
CONTAINS 56.394%

Where 's the money ?" Haitian activists protesting the theft of
minutes for longest . This will be updated when I have
ursed for hand lot ion , a floor mat , $
obtained by multiplying the bottleneck bandwidth and round - trip propagation
profit margin on $ 700 million in revenue delivers operating profits

INTERVAL -2.630 - -0.109
CONTAINS 43.137%

to protect polling stations ahead of the ' b anned '
е е о� ь
_ 00 61 E , DP 02 _ 00 62 E
, a Facebook spokesman , said the company had tried outsourcing
I Na of umi -

INTERVAL -5.151 - -2.630
CONTAINS 0.193%

that may or may not agree with my own views .
finally , please have a look to the new . Released
today ! Che ers to our sponsors , like
And that 's the problem . Clinton and most
PHOTOS : Top Gr ads of YouTube U
Token projectile
Token ID26489
Feature activation+2.95e-01

Pos logit contributions
+1.037
joy+0.999
ˈ+0.997
 Twain+0.997
TPPStreamerBot+0.976
Neg logit contributions
alian-0.760
 rob-0.709
 harms-0.699
cade-0.696
pha-0.669
Token flies
Token ID17607
Feature activation+2.04e+00

Pos logit contributions
alian+0.169
 rob+0.158
 harms+0.157
cade+0.155
pha+0.148
Neg logit contributions
-0.241
joy-0.231
ˈ-0.230
 Twain-0.229
TPPStreamerBot-0.227
Token further
Token ID2252
Feature activation+5.65e-01

Pos logit contributions
alian+1.259
 harms+1.197
 rob+1.192
cade+1.160
ao+1.106
Neg logit contributions
-1.600
ˈ-1.513
 Twain-1.496
joy-1.496
TPPStreamerBot-1.491
Token,
Token ID11
Feature activation+8.10e-01

Pos logit contributions
alian+0.358
 rob+0.337
 harms+0.336
cade+0.333
pha+0.318
Neg logit contributions
-0.428
joy-0.408
ˈ-0.408
 Twain-0.405
TPPStreamerBot-0.402
Token she
Token ID673
Feature activation+7.76e-01

Pos logit contributions
alian+0.474
 rob+0.447
 harms+0.447
cade+0.438
kai+0.414
Neg logit contributions
-0.653
ˈ-0.622
joy-0.622
 Twain-0.617
TPPStreamerBot-0.615
Token deals
Token ID7529
Feature activation+4.93e+00

Pos logit contributions
alian+0.461
 rob+0.433
 harms+0.432
cade+0.426
pha+0.406
Neg logit contributions
-0.617
ˈ-0.590
joy-0.590
 Twain-0.586
TPPStreamerBot-0.583
Token more
Token ID517
Feature activation+1.48e+00

Pos logit contributions
alian+3.132
 harms+3.087
 rob+3.059
cade+2.944
kai+2.848
Neg logit contributions
-3.666
ˈ-3.395
TPPStreamerBot-3.389
 Twain-3.380
joy-3.379
Token stun
Token ID7991
Feature activation+2.40e+00

Pos logit contributions
alian+0.505
 rob+0.452
 harms+0.450
cade+0.438
pha+0.399
Neg logit contributions
-1.550
joy-1.497
ˈ-1.497
 Twain-1.490
TPPStreamerBot-1.483
Token on
Token ID319
Feature activation+3.97e-01

Pos logit contributions
alian+1.251
 rob+1.166
 harms+1.165
cade+1.143
pha+1.078
Neg logit contributions
-2.091
ˈ-2.004
joy-2.004
 Twain-1.994
TPPStreamerBot-1.982
Token her
Token ID607
Feature activation+5.33e-01

Pos logit contributions
alian+0.257
 rob+0.243
 harms+0.242
cade+0.239
pha+0.229
Neg logit contributions
-0.294
joy-0.281
ˈ-0.281
 Twain-0.279
TPPStreamerBot-0.277
Token attacks
Token ID3434
Feature activation+4.11e-01

Pos logit contributions
alian+0.287
 rob+0.268
 harms+0.267
cade+0.262
pha+0.248
Neg logit contributions
-0.455
ˈ-0.435
joy-0.435
 Twain-0.433
TPPStreamerBot-0.431
Token many
Token ID867
Feature activation-2.08e-01

Pos logit contributions
alian+0.047
 rob+0.044
 harms+0.044
cade+0.044
pha+0.042
Neg logit contributions
-0.054
joy-0.051
ˈ-0.051
 Twain-0.051
TPPStreamerBot-0.051
Token economic
Token ID3034
Feature activation+4.58e-01

Pos logit contributions
+0.148
ˈ+0.141
joy+0.141
 Twain+0.140
TPPStreamerBot+0.139
Neg logit contributions
alian-0.140
 rob-0.132
 harms-0.131
cade-0.131
pha-0.125
Token indicators
Token ID21337
Feature activation+6.57e-01

Pos logit contributions
alian+0.327
 rob+0.310
 harms+0.310
cade+0.306
pha+0.294
Neg logit contributions
-0.310
joy-0.294
ˈ-0.294
 Twain-0.292
TPPStreamerBot-0.290
Token that
Token ID326
Feature activation+4.40e-01

Pos logit contributions
alian+0.404
 rob+0.381
 harms+0.381
cade+0.374
pha+0.356
Neg logit contributions
-0.510
joy-0.487
ˈ-0.486
 Twain-0.483
TPPStreamerBot-0.481
Token inter
Token ID987
Feature activation+1.19e+00

Pos logit contributions
alian+0.267
 rob+0.252
 harms+0.251
cade+0.247
pha+0.236
Neg logit contributions
-0.344
joy-0.328
ˈ-0.328
 Twain-0.326
TPPStreamerBot-0.324
Tokenplay
Token ID1759
Feature activation+4.37e+00

Pos logit contributions
alian+0.763
 rob+0.722
 harms+0.721
cade+0.712
pha+0.678
Neg logit contributions
-0.886
ˈ-0.846
joy-0.846
 Twain-0.839
TPPStreamerBot-0.832
Token to
Token ID284
Feature activation+2.91e-01

Pos logit contributions
alian+2.549
 rob+2.421
 harms+2.419
cade+2.305
 localization+2.208
Neg logit contributions
-3.510
ˈ-3.342
joy-3.332
TPPStreamerBot-3.329
 Twain-3.304
Token create
Token ID2251
Feature activation+6.97e-01

Pos logit contributions
alian+0.174
 rob+0.163
 harms+0.163
cade+0.161
pha+0.153
Neg logit contributions
-0.230
joy-0.220
ˈ-0.220
 Twain-0.219
TPPStreamerBot-0.217
Token a
Token ID257
Feature activation-6.55e-01

Pos logit contributions
alian+0.457
 harms+0.441
 rob+0.440
cade+0.423
 localization+0.407
Neg logit contributions
-0.510
joy-0.484
ˈ-0.483
 Twain-0.478
TPPStreamerBot-0.477
Token judgement
Token ID23071
Feature activation+4.07e-01

Pos logit contributions
+0.460
ˈ+0.434
joy+0.433
 Twain+0.430
TPPStreamerBot+0.429
Neg logit contributions
alian-0.453
 rob-0.434
 harms-0.432
cade-0.425
pha-0.405
Token on
Token ID319
Feature activation-5.03e-01

Pos logit contributions
alian+0.250
 rob+0.235
 harms+0.234
cade+0.231
pha+0.220
Neg logit contributions
-0.316
joy-0.302
ˈ-0.302
 Twain-0.300
TPPStreamerBot-0.298
Token planned
Token ID6027
Feature activation+1.06e+00

Pos logit contributions
alian+0.205
 rob+0.193
 harms+0.193
cade+0.188
pha+0.179
Neg logit contributions
-0.291
joy-0.277
ˈ-0.277
 Twain-0.274
TPPStreamerBot-0.274
Token to
Token ID284
Feature activation+9.98e-01

Pos logit contributions
alian+0.644
 harms+0.605
 rob+0.605
cade+0.598
pha+0.569
Neg logit contributions
-0.826
ˈ-0.792
joy-0.790
 Twain-0.787
TPPStreamerBot-0.781
Token happen
Token ID1645
Feature activation+1.10e+00

Pos logit contributions
alian+0.671
 rob+0.638
 harms+0.635
cade+0.626
pha+0.599
Neg logit contributions
-0.718
joy-0.682
ˈ-0.681
 Twain-0.676
TPPStreamerBot-0.673
Token in
Token ID287
Feature activation+1.20e+00

Pos logit contributions
alian+0.662
 rob+0.623
 harms+0.621
cade+0.611
pha+0.582
Neg logit contributions
-0.877
joy-0.835
ˈ-0.834
 Twain-0.828
TPPStreamerBot-0.823
Token two
Token ID734
Feature activation+1.53e-01

Pos logit contributions
alian+0.739
 rob+0.702
 harms+0.699
cade+0.684
pha+0.654
Neg logit contributions
-0.931
joy-0.880
ˈ-0.877
TPPStreamerBot-0.869
 Twain-0.867
Token phases
Token ID21164
Feature activation+4.17e+00

Pos logit contributions
alian+0.064
 rob+0.059
 harms+0.058
cade+0.057
pha+0.053
Neg logit contributions
-0.149
ˈ-0.143
joy-0.143
 Twain-0.143
TPPStreamerBot-0.142
Token,
Token ID11
Feature activation+3.51e-01

Pos logit contributions
alian+2.178
 rob+2.067
 harms+2.035
cade+1.985
kai+1.871
Neg logit contributions
-3.645
joy-3.453
ˈ-3.445
 Twain-3.412
TPPStreamerBot-3.380
Token according
Token ID1864
Feature activation+1.00e+00

Pos logit contributions
alian+0.222
 rob+0.210
 harms+0.209
cade+0.206
pha+0.196
Neg logit contributions
-0.267
joy-0.254
ˈ-0.253
 Twain-0.251
TPPStreamerBot-0.250
Token to
Token ID284
Feature activation+9.09e-01

Pos logit contributions
alian+0.559
 rob+0.537
 harms+0.522
cade+0.515
ctl+0.493
Neg logit contributions
-0.859
ˈ-0.794
joy-0.792
 Twain-0.791
TPPStreamerBot-0.788
Token project
Token ID1628
Feature activation+6.24e-01

Pos logit contributions
alian+0.601
 rob+0.577
 harms+0.570
cade+0.561
pha+0.536
Neg logit contributions
-0.668
ˈ-0.629
joy-0.627
TPPStreamerBot-0.624
 Twain-0.620
Token manager
Token ID4706
Feature activation+9.63e-01

Pos logit contributions
alian+0.460
 rob+0.438
 harms+0.436
cade+0.431
ao+0.415
Neg logit contributions
-0.411
ˈ-0.387
joy-0.386
 Twain-0.385
TPPStreamerBot-0.383
Token Airbnb
Token ID35079
Feature activation+5.51e-01

Pos logit contributions
+0.292
joy+0.278
ˈ+0.278
 Twain+0.276
TPPStreamerBot+0.274
Neg logit contributions
alian-0.257
 rob-0.242
 harms-0.242
cade-0.239
pha-0.228
Token is
Token ID318
Feature activation-4.95e-01

Pos logit contributions
alian+0.247
 rob+0.228
 harms+0.227
cade+0.222
pha+0.208
Neg logit contributions
-0.518
joy-0.499
ˈ-0.499
 Twain-0.496
TPPStreamerBot-0.493
Token disrupting
Token ID37915
Feature activation+2.55e-01

Pos logit contributions
+0.376
joy+0.359
ˈ+0.359
 Twain+0.357
TPPStreamerBot+0.354
Neg logit contributions
alian-0.312
 rob-0.293
 harms-0.293
cade-0.289
pha-0.276
Token hospitality
Token ID33362
Feature activation-1.04e-01

Pos logit contributions
alian+0.166
 rob+0.158
 harms+0.157
cade+0.155
pha+0.148
Neg logit contributions
-0.188
ˈ-0.179
joy-0.179
 Twain-0.177
TPPStreamerBot-0.177
Token.
Token ID13
Feature activation+9.53e-02

Pos logit contributions
+0.087
ˈ+0.083
joy+0.083
 Twain+0.082
TPPStreamerBot+0.082
Neg logit contributions
alian-0.058
 rob-0.054
 harms-0.054
cade-0.053
pha-0.050
Token https
Token ID3740
Feature activation+4.14e+00

Pos logit contributions
alian+0.049
 rob+0.046
 harms+0.046
cade+0.045
pha+0.042
Neg logit contributions
-0.083
ˈ-0.080
joy-0.080
 Twain-0.079
TPPStreamerBot-0.079
Token://
Token ID1378
Feature activation+2.59e+00

Pos logit contributions
alian+3.052
 rob+2.995
cade+2.950
 harms+2.875
ao+2.849
Neg logit contributions
-2.784
 Twain-2.498
 wiser-2.388
�士-2.385
 unbeat-2.377
Tokenwww
Token ID2503
Feature activation-4.98e-01

Pos logit contributions
alian+1.933
 rob+1.864
cade+1.854
 harms+1.826
kai+1.761
Neg logit contributions
-1.728
 Twain-1.621
ˈ-1.558
TPPStreamerBot-1.542
joy-1.529
Token.
Token ID13
Feature activation-8.15e-01

Pos logit contributions
+0.428
joy+0.413
ˈ+0.413
 Twain+0.409
TPPStreamerBot+0.407
Neg logit contributions
alian-0.263
 harms-0.244
 rob-0.244
cade-0.239
pha-0.226
Tokenbel
Token ID6667
Feature activation+1.12e-01

Pos logit contributions
joy+0.563
+0.557
ˈ+0.547
TPPStreamerBot+0.539
 Twain+0.528
Neg logit contributions
alian-0.552
 rob-0.527
 harms-0.526
cade-0.501
 localization-0.497
Tokenfast
Token ID7217
Feature activation-1.62e-01

Pos logit contributions
alian+0.105
 rob+0.102
 harms+0.101
cade+0.101
pha+0.097
Neg logit contributions
-0.049
joy-0.046
ˈ-0.046
 Twain-0.044
TPPStreamerBot-0.044
Token drug
Token ID2563
Feature activation+9.81e-02

Pos logit contributions
+0.136
joy+0.129
ˈ+0.129
 Twain+0.128
TPPStreamerBot+0.127
Neg logit contributions
alian-0.136
 rob-0.129
 harms-0.128
cade-0.127
pha-0.122
Token addict
Token ID19678
Feature activation+4.11e-02

Pos logit contributions
alian+0.064
 rob+0.061
 harms+0.061
cade+0.060
pha+0.057
Neg logit contributions
-0.072
joy-0.069
ˈ-0.069
 Twain-0.068
TPPStreamerBot-0.068
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
alian+0.022
 rob+0.021
 harms+0.021
cade+0.020
pha+0.019
Neg logit contributions
-0.035
ˈ-0.033
joy-0.033
 Twain-0.033
TPPStreamerBot-0.033
Token The
Token ID383
Feature activation+3.03e-01

Pos logit contributions
alian+0.133
 rob+0.126
 harms+0.126
cade+0.124
pha+0.119
Neg logit contributions
-0.144
joy-0.137
ˈ-0.137
 Twain-0.135
TPPStreamerBot-0.135
Token common
Token ID2219
Feature activation+1.33e-01

Pos logit contributions
alian+0.191
 rob+0.181
 harms+0.181
cade+0.177
pha+0.169
Neg logit contributions
-0.230
ˈ-0.219
joy-0.219
 Twain-0.217
TPPStreamerBot-0.216
Token denomin
Token ID31457
Feature activation+4.13e+00

Pos logit contributions
alian+0.081
 rob+0.076
 harms+0.075
cade+0.074
pha+0.071
Neg logit contributions
-0.104
joy-0.100
ˈ-0.100
 Twain-0.100
TPPStreamerBot-0.098
Tokenator
Token ID1352
Feature activation+1.36e+00

Pos logit contributions
alian+2.312
cade+2.151
 harms+2.110
 rob+2.097
ao+2.051
Neg logit contributions
-3.498
ˈ-3.300
 Twain-3.262
TPPStreamerBot-3.249
 unbeat-3.229
Token throughout
Token ID3690
Feature activation+2.30e-01

Pos logit contributions
alian+0.753
 harms+0.707
 rob+0.705
cade+0.692
pha+0.655
Neg logit contributions
-1.140
ˈ-1.089
joy-1.087
 Twain-1.078
TPPStreamerBot-1.078
Token these
Token ID777
Feature activation-2.92e-02

Pos logit contributions
alian+0.145
 rob+0.136
 harms+0.135
cade+0.134
pha+0.128
Neg logit contributions
-0.176
ˈ-0.168
joy-0.168
 Twain-0.167
TPPStreamerBot-0.165
Token disparate
Token ID37433
Feature activation+1.07e+00

Pos logit contributions
+0.022
ˈ+0.021
joy+0.021
 Twain+0.021
TPPStreamerBot+0.021
Neg logit contributions
alian-0.018
 rob-0.017
 harms-0.017
cade-0.017
pha-0.016
Token roles
Token ID9176
Feature activation-6.10e-01

Pos logit contributions
alian+0.651
 rob+0.613
 harms+0.612
cade+0.603
pha+0.574
Neg logit contributions
-0.840
ˈ-0.802
joy-0.801
 Twain-0.796
TPPStreamerBot-0.792
Token they
Token ID484
Feature activation-1.95e-01

Pos logit contributions
alian+0.267
 rob+0.253
 harms+0.252
cade+0.249
pha+0.237
Neg logit contributions
-0.339
joy-0.324
ˈ-0.324
 Twain-0.321
TPPStreamerBot-0.320
Token can
Token ID460
Feature activation+2.04e-01

Pos logit contributions
+0.169
joy+0.162
ˈ+0.162
 Twain+0.161
TPPStreamerBot+0.160
Neg logit contributions
alian-0.102
 rob-0.095
 harms-0.095
cade-0.093
pha-0.088
Token prepare
Token ID8335
Feature activation-1.23e+00

Pos logit contributions
alian+0.136
 rob+0.129
 harms+0.129
cade+0.127
pha+0.121
Neg logit contributions
-0.148
joy-0.141
ˈ-0.141
 Twain-0.140
TPPStreamerBot-0.139
Token for
Token ID329
Feature activation-1.30e-01

Pos logit contributions
+0.905
ˈ+0.865
joy+0.864
 Twain+0.862
TPPStreamerBot+0.850
Neg logit contributions
alian-0.801
 rob-0.750
 harms-0.750
cade-0.747
pha-0.713
Token their
Token ID511
Feature activation-2.24e-01

Pos logit contributions
+0.102
ˈ+0.097
joy+0.097
 Twain+0.097
TPPStreamerBot+0.096
Neg logit contributions
alian-0.079
 rob-0.074
 harms-0.074
cade-0.073
pha-0.069
Token client
Token ID5456
Feature activation+4.10e+00

Pos logit contributions
+0.176
ˈ+0.168
joy+0.168
 Twain+0.167
TPPStreamerBot+0.166
Neg logit contributions
alian-0.136
 rob-0.127
 harms-0.126
cade-0.126
pha-0.120
Token
Token ID447
Feature activation+4.09e-01

Pos logit contributions
alian+2.151
 rob+2.004
 harms+1.997
cade+1.950
ao+1.843
Neg logit contributions
-3.541
joy-3.393
ˈ-3.393
 Twain-3.375
TPPStreamerBot-3.375
Token
Token ID247
Feature activation+3.32e-01

Pos logit contributions
alian+0.359
 rob+0.343
 harms+0.341
cade+0.339
pha+0.330
Neg logit contributions
-0.212
joy-0.195
ˈ-0.195
 Twain-0.194
TPPStreamerBot-0.191
Tokens
Token ID82
Feature activation+8.37e-01

Pos logit contributions
alian+0.210
 rob+0.197
 harms+0.197
cade+0.194
pha+0.186
Neg logit contributions
-0.250
ˈ-0.240
joy-0.240
 Twain-0.238
TPPStreamerBot-0.236
Token upcoming
Token ID7865
Feature activation-6.13e-02

Pos logit contributions
alian+0.494
 rob+0.462
 harms+0.461
cade+0.456
pha+0.434
Neg logit contributions
-0.669
ˈ-0.639
joy-0.639
 Twain-0.637
TPPStreamerBot-0.631
Token trial
Token ID4473
Feature activation-3.88e-01

Pos logit contributions
+0.049
ˈ+0.047
joy+0.047
 Twain+0.047
TPPStreamerBot+0.046
Neg logit contributions
alian-0.036
 rob-0.033
 harms-0.033
cade-0.033
pha-0.031
Token
Token ID447
Feature activation+5.10e-02

Pos logit contributions
alian+0.080
 rob+0.075
 harms+0.074
cade+0.074
ao+0.071
Neg logit contributions
-0.088
 Twain-0.084
joy-0.084
ˈ-0.083
TPPStreamerBot-0.082
Token
Token ID247
Feature activation+1.92e-01

Pos logit contributions
alian+0.044
 rob+0.042
 harms+0.042
cade+0.042
pha+0.040
Neg logit contributions
-0.028
 Twain-0.025
joy-0.025
ˈ-0.025
TPPStreamerBot-0.025
Tokenve
Token ID303
Feature activation-1.05e+00

Pos logit contributions
alian+0.136
cade+0.128
 rob+0.128
 harms+0.127
kai+0.122
Neg logit contributions
-0.133
 Twain-0.125
joy-0.124
ˈ-0.124
TPPStreamerBot-0.123
Token developed
Token ID4166
Feature activation-8.68e-01

Pos logit contributions
+0.698
joy+0.659
ˈ+0.657
 Twain+0.654
TPPStreamerBot+0.648
Neg logit contributions
alian-0.764
 rob-0.727
 harms-0.723
cade-0.715
ao-0.686
Token parad
Token ID11497
Feature activation+1.93e-01

Pos logit contributions
+0.626
ˈ+0.594
joy+0.592
 Twain+0.588
TPPStreamerBot+0.586
Neg logit contributions
alian-0.583
 rob-0.553
 harms-0.551
cade-0.544
ao-0.519
Tokenig
Token ID328
Feature activation+4.09e+00

Pos logit contributions
alian+0.120
 rob+0.113
 harms+0.113
cade+0.111
pha+0.106
Neg logit contributions
-0.149
joy-0.142
ˈ-0.142
 Twain-0.141
TPPStreamerBot-0.140
Tokenms
Token ID907
Feature activation-3.28e-01

Pos logit contributions
alian+2.254
 rob+2.118
 harms+2.116
cade+2.063
pha+2.009
Neg logit contributions
-3.430
 Twain-3.290
ˈ-3.271
joy-3.267
TPPStreamerBot-3.229
Token based
Token ID1912
Feature activation-2.86e-01

Pos logit contributions
+0.259
joy+0.247
ˈ+0.247
 Twain+0.245
TPPStreamerBot+0.244
Neg logit contributions
alian-0.197
 rob-0.185
 harms-0.185
cade-0.182
pha-0.173
Token on
Token ID319
Feature activation+4.24e-01

Pos logit contributions
+0.212
ˈ+0.202
joy+0.202
 Twain+0.200
TPPStreamerBot+0.199
Neg logit contributions
alian-0.186
 rob-0.176
 harms-0.175
cade-0.173
pha-0.165
Token such
Token ID884
Feature activation-2.44e-01

Pos logit contributions
alian+0.282
 rob+0.268
 harms+0.267
cade+0.263
ao+0.250
Neg logit contributions
-0.309
ˈ-0.293
joy-0.291
 Twain-0.290
TPPStreamerBot-0.289
Token limited
Token ID3614
Feature activation+2.38e-01

Pos logit contributions
+0.183
joy+0.176
ˈ+0.175
 Twain+0.175
TPPStreamerBot+0.173
Neg logit contributions
alian-0.154
 rob-0.145
 harms-0.145
cade-0.143
pha-0.137
Token female
Token ID4048
Feature activation+7.22e-01

Pos logit contributions
+0.003
ˈ+0.003
joy+0.003
 Twain+0.003
TPPStreamerBot+0.003
Neg logit contributions
alian-0.003
 rob-0.002
 harms-0.002
cade-0.002
pha-0.002
Token comic
Token ID9048
Feature activation-5.31e-01

Pos logit contributions
alian+0.478
 rob+0.451
 harms+0.450
cade+0.445
pha+0.426
Neg logit contributions
-0.525
joy-0.500
ˈ-0.500
 Twain-0.498
TPPStreamerBot-0.493
Token book
Token ID1492
Feature activation+1.13e+00

Pos logit contributions
+0.370
joy+0.352
ˈ+0.352
 Twain+0.349
TPPStreamerBot+0.346
Neg logit contributions
alian-0.368
 rob-0.348
 harms-0.347
cade-0.343
pha-0.329
Token characters
Token ID3435
Feature activation+1.56e-01

Pos logit contributions
alian+0.735
 rob+0.694
 harms+0.693
cade+0.683
pha+0.654
Neg logit contributions
-0.840
ˈ-0.799
joy-0.799
 Twain-0.794
TPPStreamerBot-0.789
Token do
Token ID466
Feature activation+1.04e+00

Pos logit contributions
alian+0.091
 rob+0.085
 harms+0.085
cade+0.084
pha+0.080
Neg logit contributions
-0.126
ˈ-0.120
joy-0.120
 Twain-0.120
TPPStreamerBot-0.119
Token indeed
Token ID5600
Feature activation+4.04e+00

Pos logit contributions
alian+0.662
 rob+0.625
 harms+0.623
cade+0.614
pha+0.586
Neg logit contributions
-0.782
joy-0.743
ˈ-0.743
 Twain-0.739
TPPStreamerBot-0.738
Token have
Token ID423
Feature activation+9.23e-01

Pos logit contributions
alian+2.561
 rob+2.475
 harms+2.418
cade+2.357
kai+2.268
Neg logit contributions
-3.079
TPPStreamerBot-2.903
joy-2.893
 Twain-2.867
ˈ-2.853
Token staying
Token ID10589
Feature activation-5.89e-01

Pos logit contributions
alian+0.624
 rob+0.597
 harms+0.596
cade+0.578
ao+0.559
Neg logit contributions
-0.663
ˈ-0.622
joy-0.620
TPPStreamerBot-0.620
 Twain-0.615
Token power
Token ID1176
Feature activation-3.35e-01

Pos logit contributions
+0.455
joy+0.436
ˈ+0.436
 Twain+0.434
TPPStreamerBot+0.428
Neg logit contributions
alian-0.362
 rob-0.340
 harms-0.338
cade-0.336
pha-0.318
Token,
Token ID11
Feature activation+1.71e-01

Pos logit contributions
+0.275
joy+0.263
ˈ+0.263
 Twain+0.262
TPPStreamerBot+0.259
Neg logit contributions
alian-0.191
 rob-0.178
 harms-0.178
cade-0.176
pha-0.167
Token then
Token ID788
Feature activation+7.74e-01

Pos logit contributions
alian+0.113
 rob+0.107
 harms+0.107
cade+0.105
ao+0.100
Neg logit contributions
-0.125
ˈ-0.119
joy-0.119
TPPStreamerBot-0.117
 Twain-0.117
Token y
Token ID331
Feature activation+1.05e-01

Pos logit contributions
alian+0.134
 rob+0.126
 harms+0.126
cade+0.124
pha+0.118
Neg logit contributions
-0.175
ˈ-0.167
joy-0.167
 Twain-0.166
TPPStreamerBot-0.165
Tokenaku
Token ID8719
Feature activation-5.72e-01

Pos logit contributions
alian+0.051
 rob+0.047
 harms+0.047
cade+0.046
pha+0.043
Neg logit contributions
-0.096
joy-0.092
ˈ-0.092
 Twain-0.092
TPPStreamerBot-0.091
Tokenza
Token ID4496
Feature activation-4.50e-01

Pos logit contributions
+0.560
ˈ+0.542
joy+0.542
 Twain+0.538
TPPStreamerBot+0.536
Neg logit contributions
alian-0.234
 rob-0.213
 harms-0.213
cade-0.208
pha-0.192
Token group
Token ID1448
Feature activation+5.09e-01

Pos logit contributions
+0.353
joy+0.338
ˈ+0.338
 Twain+0.336
TPPStreamerBot+0.334
Neg logit contributions
alian-0.271
 harms-0.254
 rob-0.253
cade-0.250
pha-0.239
Token par
Token ID1582
Feature activation+3.05e-01

Pos logit contributions
alian+0.306
 rob+0.289
 harms+0.287
cade+0.283
pha+0.269
Neg logit contributions
-0.403
joy-0.384
ˈ-0.384
 Twain-0.381
TPPStreamerBot-0.379
Tokenaded
Token ID5286
Feature activation+3.97e+00

Pos logit contributions
alian+0.138
 rob+0.127
 harms+0.126
cade+0.124
pha+0.116
Neg logit contributions
-0.286
ˈ-0.275
joy-0.275
 Twain-0.274
TPPStreamerBot-0.273
Token as
Token ID355
Feature activation+8.95e-01

Pos logit contributions
alian+2.333
 rob+2.281
 harms+2.217
cade+2.169
ao+2.048
Neg logit contributions
-3.244
ˈ-3.049
joy-3.013
TPPStreamerBot-3.010
 Twain-2.972
Token many
Token ID867
Feature activation-8.17e-01

Pos logit contributions
alian+0.624
 harms+0.591
 rob+0.590
cade+0.582
pha+0.559
Neg logit contributions
-0.619
joy-0.590
ˈ-0.589
 Twain-0.585
TPPStreamerBot-0.580
Token as
Token ID355
Feature activation+1.12e+00

Pos logit contributions
+0.715
joy+0.700
ˈ+0.697
 Twain+0.696
 scrambled+0.685
Neg logit contributions
alian-0.408
 harms-0.374
 rob-0.368
cade-0.365
pha-0.350
Token 100
Token ID1802
Feature activation+1.80e-01

Pos logit contributions
alian+0.811
 rob+0.780
 harms+0.773
cade+0.763
ao+0.729
Neg logit contributions
-0.769
ˈ-0.712
joy-0.707
TPPStreamerBot-0.707
 Twain-0.700
Token gang
Token ID7706
Feature activation+1.43e-02

Pos logit contributions
alian+0.106
 harms+0.099
 rob+0.099
cade+0.098
pha+0.093
Neg logit contributions
-0.144
joy-0.138
ˈ-0.138
 Twain-0.137
TPPStreamerBot-0.136
Token is
Token ID318
Feature activation+4.84e-01

Pos logit contributions
alian+0.243
 rob+0.227
 harms+0.227
cade+0.223
pha+0.212
Neg logit contributions
-0.363
ˈ-0.348
joy-0.348
 Twain-0.346
TPPStreamerBot-0.343
Token impossible
Token ID5340
Feature activation-1.23e+00

Pos logit contributions
alian+0.312
 rob+0.296
 harms+0.296
cade+0.290
pha+0.277
Neg logit contributions
-0.361
ˈ-0.343
joy-0.343
 Twain-0.340
TPPStreamerBot-0.338
Token to
Token ID284
Feature activation-9.63e-01

Pos logit contributions
+0.923
joy+0.888
ˈ+0.886
 Twain+0.884
TPPStreamerBot+0.874
Neg logit contributions
alian-0.774
 harms-0.728
 rob-0.727
cade-0.724
pha-0.694
Token dis
Token ID595
Feature activation+2.36e+00

Pos logit contributions
+0.709
ˈ+0.681
joy+0.679
 Twain+0.679
TPPStreamerBot+0.670
Neg logit contributions
alian-0.622
 harms-0.583
 rob-0.581
cade-0.578
pha-0.557
Tokenamb
Token ID4131
Feature activation-1.92e-01

Pos logit contributions
alian+1.844
 rob+1.753
 harms+1.750
cade+1.737
ao+1.673
Neg logit contributions
-1.448
ˈ-1.353
 Twain-1.346
joy-1.345
TPPStreamerBot-1.332
Tokenig
Token ID328
Feature activation+3.96e+00

Pos logit contributions
+0.151
ˈ+0.143
 Twain+0.142
joy+0.142
TPPStreamerBot+0.142
Neg logit contributions
alian-0.117
 rob-0.110
 harms-0.109
cade-0.109
pha-0.103
Tokenuate
Token ID4985
Feature activation+2.04e+00

Pos logit contributions
alian+2.375
 rob+2.237
 harms+2.220
cade+2.198
ao+2.112
Neg logit contributions
-3.157
ˈ-2.984
joy-2.967
TPPStreamerBot-2.960
 Twain-2.958
Token any
Token ID597
Feature activation+1.89e-01

Pos logit contributions
alian+1.262
 harms+1.207
 rob+1.207
cade+1.170
ao+1.120
Neg logit contributions
-1.576
ˈ-1.500
joy-1.494
TPPStreamerBot-1.475
 Twain-1.472
Token single
Token ID2060
Feature activation+2.34e-01

Pos logit contributions
alian+0.114
 rob+0.108
 harms+0.107
cade+0.106
pha+0.101
Neg logit contributions
-0.148
ˈ-0.141
joy-0.141
 Twain-0.140
TPPStreamerBot-0.139
Token measurement
Token ID15558
Feature activation-1.25e+00

Pos logit contributions
alian+0.155
 rob+0.147
 harms+0.147
cade+0.144
pha+0.138
Neg logit contributions
-0.171
ˈ-0.163
joy-0.163
 Twain-0.161
TPPStreamerBot-0.160
Token,
Token ID11
Feature activation-3.88e-01

Pos logit contributions
+0.929
joy+0.891
 Twain+0.890
ˈ+0.889
TPPStreamerBot+0.876
Neg logit contributions
alian-0.800
 rob-0.748
 harms-0.745
cade-0.742
pha-0.710
Token
Token ID447
Feature activation+6.40e-01

Pos logit contributions
alian+0.246
 rob+0.233
 harms+0.232
cade+0.228
pha+0.218
Neg logit contributions
-0.302
ˈ-0.288
joy-0.288
 Twain-0.285
TPPStreamerBot-0.284
Token
Token ID247
Feature activation+2.67e-01

Pos logit contributions
alian+0.570
 rob+0.544
 harms+0.542
cade+0.539
pha+0.525
Neg logit contributions
-0.320
joy-0.297
ˈ-0.296
 Twain-0.294
TPPStreamerBot-0.290
Tokens
Token ID82
Feature activation-7.37e-02

Pos logit contributions
alian+0.165
 rob+0.155
 harms+0.155
cade+0.152
pha+0.145
Neg logit contributions
-0.206
ˈ-0.197
joy-0.197
 Twain-0.196
TPPStreamerBot-0.194
Token opportunity
Token ID3663
Feature activation+5.14e-02

Pos logit contributions
+0.053
joy+0.051
ˈ+0.051
 Twain+0.051
TPPStreamerBot+0.050
Neg logit contributions
alian-0.049
 rob-0.046
 harms-0.046
cade-0.046
pha-0.044
Token to
Token ID284
Feature activation-1.45e-01

Pos logit contributions
alian+0.029
 rob+0.027
 harms+0.027
cade+0.027
pha+0.025
Neg logit contributions
-0.042
joy-0.041
ˈ-0.041
 Twain-0.040
TPPStreamerBot-0.040
Token decentral
Token ID20649
Feature activation+3.90e+00

Pos logit contributions
+0.111
ˈ+0.106
joy+0.106
 Twain+0.106
TPPStreamerBot+0.105
Neg logit contributions
alian-0.091
 rob-0.085
 harms-0.085
cade-0.084
pha-0.080
Tokenize
Token ID1096
Feature activation+8.63e-01

Pos logit contributions
alian+1.350
 rob+1.236
 harms+1.207
cade+1.199
ao+1.101
Neg logit contributions
-4.051
ˈ-3.926
 Twain-3.900
TPPStreamerBot-3.888
joy-3.887
Token.
Token ID13
Feature activation+3.86e-01

Pos logit contributions
alian+0.542
 rob+0.514
 harms+0.513
cade+0.503
pha+0.481
Neg logit contributions
-0.657
ˈ-0.626
joy-0.626
 Twain-0.621
TPPStreamerBot-0.619
Token
Token ID198
Feature activation+6.10e-01

Pos logit contributions
alian+0.249
 rob+0.237
 harms+0.236
cade+0.232
pha+0.223
Neg logit contributions
-0.288
joy-0.272
ˈ-0.272
TPPStreamerBot-0.270
 Twain-0.267
Token
Token ID198
Feature activation+3.19e-01

Pos logit contributions
alian+0.384
 rob+0.366
 harms+0.361
cade+0.360
kai+0.343
Neg logit contributions
-0.474
ˈ-0.439
 Twain-0.438
joy-0.437
TPPStreamerBot-0.436
TokenBoth
Token ID10265
Feature activation-1.54e-02

Pos logit contributions
alian+0.203
 rob+0.191
 harms+0.191
cade+0.190
ao+0.181
Neg logit contributions
-0.240
 Twain-0.227
joy-0.227
ˈ-0.227
TPPStreamerBot-0.224
Tokens
Token ID82
Feature activation+2.05e-01

Pos logit contributions
alian+0.390
 rob+0.368
 harms+0.366
cade+0.362
pha+0.345
Neg logit contributions
-0.485
ˈ-0.465
joy-0.464
 Twain-0.460
TPPStreamerBot-0.457
Token a
Token ID257
Feature activation+2.93e-01

Pos logit contributions
alian+0.135
 rob+0.127
 harms+0.127
cade+0.125
pha+0.120
Neg logit contributions
-0.151
joy-0.144
ˈ-0.144
 Twain-0.143
TPPStreamerBot-0.142
Token narrow
Token ID7135
Feature activation+7.20e-01

Pos logit contributions
alian+0.198
 rob+0.187
 harms+0.187
cade+0.184
pha+0.177
Neg logit contributions
-0.210
joy-0.200
ˈ-0.200
 Twain-0.198
TPPStreamerBot-0.197
Token,
Token ID11
Feature activation-2.89e-01

Pos logit contributions
alian+0.473
 rob+0.449
 harms+0.447
cade+0.441
pha+0.422
Neg logit contributions
-0.527
ˈ-0.501
joy-0.500
 Twain-0.498
TPPStreamerBot-0.496
Token par
Token ID1582
Feature activation-5.28e-01

Pos logit contributions
+0.212
joy+0.201
ˈ+0.201
 Twain+0.200
TPPStreamerBot+0.199
Neg logit contributions
alian-0.190
 rob-0.180
 harms-0.179
cade-0.177
pha-0.169
Tokenoch
Token ID5374
Feature activation+3.86e+00

Pos logit contributions
+0.359
ˈ+0.343
joy+0.343
 Twain+0.337
TPPStreamerBot+0.334
Neg logit contributions
alian-0.372
 harms-0.355
 rob-0.355
cade-0.349
pha-0.334
Tokenial
Token ID498
Feature activation+9.67e-01

Pos logit contributions
alian+1.964
 rob+1.802
 harms+1.784
cade+1.775
ao+1.682
Neg logit contributions
-3.453
ˈ-3.282
joy-3.277
 Twain-3.274
TPPStreamerBot-3.270
Token
Token ID564
Feature activation+3.05e-01

Pos logit contributions
alian+0.644
 rob+0.612
 harms+0.609
cade+0.601
pha+0.575
Neg logit contributions
-0.700
ˈ-0.665
joy-0.665
 Twain-0.661
TPPStreamerBot-0.658
Token
Token ID246
Feature activation-4.80e-01

Pos logit contributions
alian+0.309
 rob+0.298
 harms+0.298
cade+0.296
pha+0.288
Neg logit contributions
-0.115
joy-0.104
 Twain-0.104
ˈ-0.103
TPPStreamerBot-0.102
Tokenmy
Token ID1820
Feature activation+9.02e-02

Pos logit contributions
+0.353
joy+0.337
ˈ+0.337
 Twain+0.333
TPPStreamerBot+0.331
Neg logit contributions
alian-0.314
 rob-0.297
 harms-0.297
cade-0.292
pha-0.279
Token country
Token ID1499
Feature activation-5.71e-01

Pos logit contributions
alian+0.057
 rob+0.054
 harms+0.054
cade+0.053
pha+0.050
Neg logit contributions
-0.068
joy-0.065
ˈ-0.065
 Twain-0.065
TPPStreamerBot-0.064
Token as
Token ID355
Feature activation+6.44e-01

Pos logit contributions
+0.297
ˈ+0.288
joy+0.288
 Twain+0.285
TPPStreamerBot+0.283
Neg logit contributions
alian-0.171
 harms-0.159
 rob-0.158
cade-0.156
pha-0.148
Token could
Token ID714
Feature activation+3.14e-01

Pos logit contributions
alian+0.419
 rob+0.395
 harms+0.395
cade+0.389
pha+0.372
Neg logit contributions
-0.477
joy-0.454
ˈ-0.454
 Twain-0.451
TPPStreamerBot-0.447
Token be
Token ID307
Feature activation+5.70e-01

Pos logit contributions
alian+0.188
 harms+0.177
 rob+0.177
cade+0.174
pha+0.166
Neg logit contributions
-0.248
joy-0.237
ˈ-0.237
 Twain-0.236
TPPStreamerBot-0.234
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
alian+0.319
 rob+0.298
 harms+0.297
cade+0.293
pha+0.278
Neg logit contributions
-0.474
joy-0.454
ˈ-0.453
 Twain-0.451
TPPStreamerBot-0.448
Token and
Token ID290
Feature activation+9.67e-01

Pos logit contributions
alian+0.136
 rob+0.128
 harms+0.127
cade+0.125
pha+0.119
Neg logit contributions
-0.183
ˈ-0.175
joy-0.175
 Twain-0.174
TPPStreamerBot-0.173
Token certainly
Token ID3729
Feature activation+3.79e+00

Pos logit contributions
alian+0.621
 rob+0.587
 harms+0.585
cade+0.577
pha+0.550
Neg logit contributions
-0.725
ˈ-0.690
joy-0.688
 Twain-0.684
TPPStreamerBot-0.681
Token will
Token ID481
Feature activation+8.35e-01

Pos logit contributions
alian+2.357
 rob+2.270
 harms+2.245
cade+2.188
kai+2.077
Neg logit contributions
-2.940
ˈ-2.768
joy-2.734
TPPStreamerBot-2.731
 Twain-2.709
Token look
Token ID804
Feature activation-1.13e+00

Pos logit contributions
alian+0.540
 harms+0.508
 rob+0.505
cade+0.501
pha+0.483
Neg logit contributions
-0.616
joy-0.591
ˈ-0.591
 Twain-0.586
TPPStreamerBot-0.578
Token great
Token ID1049
Feature activation-7.97e-01

Pos logit contributions
+0.814
joy+0.781
ˈ+0.778
 Twain+0.775
TPPStreamerBot+0.766
Neg logit contributions
alian-0.748
 rob-0.701
 harms-0.701
cade-0.699
pha-0.672
Token in
Token ID287
Feature activation+1.83e-01

Pos logit contributions
+0.607
joy+0.588
ˈ+0.585
 Twain+0.581
TPPStreamerBot+0.575
Neg logit contributions
alian-0.490
 rob-0.459
 harms-0.458
cade-0.455
pha-0.437
Token a
Token ID257
Feature activation+2.83e-01

Pos logit contributions
alian+0.120
 rob+0.112
cade+0.112
 harms+0.112
pha+0.108
Neg logit contributions
-0.133
joy-0.129
ˈ-0.128
 Twain-0.128
TPPStreamerBot-0.126
Token the
Token ID262
Feature activation+5.14e-01

Pos logit contributions
alian+0.060
 rob+0.057
 harms+0.057
cade+0.056
pha+0.054
Neg logit contributions
-0.061
joy-0.058
ˈ-0.058
 Twain-0.057
TPPStreamerBot-0.057
Token S
Token ID311
Feature activation+1.41e+00

Pos logit contributions
alian+0.347
 rob+0.331
 harms+0.329
cade+0.324
pha+0.310
Neg logit contributions
-0.369
joy-0.349
ˈ-0.348
 Twain-0.345
TPPStreamerBot-0.345
Token,
Token ID11
Feature activation+6.00e-01

Pos logit contributions
alian+0.880
 rob+0.831
 harms+0.827
cade+0.817
pha+0.787
Neg logit contributions
-1.077
joy-1.024
ˈ-1.023
 Twain-1.019
TPPStreamerBot-1.014
Token can
Token ID460
Feature activation+9.86e-01

Pos logit contributions
alian+0.394
 rob+0.375
 harms+0.374
cade+0.367
pha+0.351
Neg logit contributions
-0.443
joy-0.420
ˈ-0.419
 Twain-0.414
TPPStreamerBot-0.414
Token now
Token ID783
Feature activation-5.70e-02

Pos logit contributions
alian+0.648
 rob+0.614
 harms+0.611
cade+0.603
pha+0.577
Neg logit contributions
-0.724
joy-0.688
ˈ-0.687
 Twain-0.683
TPPStreamerBot-0.679
Token line
Token ID1627
Feature activation+3.79e+00

Pos logit contributions
+0.041
ˈ+0.040
joy+0.039
 Twain+0.039
TPPStreamerBot+0.039
Neg logit contributions
alian-0.038
 harms-0.035
 rob-0.035
cade-0.035
pha-0.034
Token up
Token ID510
Feature activation+1.61e+00

Pos logit contributions
alian+1.822
 rob+1.729
 harms+1.691
cade+1.670
ao+1.594
Neg logit contributions
-3.437
ˈ-3.264
TPPStreamerBot-3.257
joy-3.244
 Twain-3.200
Token much
Token ID881
Feature activation+3.97e-01

Pos logit contributions
alian+0.954
 rob+0.907
 harms+0.900
cade+0.885
kai+0.838
Neg logit contributions
-1.289
ˈ-1.220
joy-1.219
TPPStreamerBot-1.208
 Twain-1.203
Token tighter
Token ID28619
Feature activation+5.31e-01

Pos logit contributions
alian+0.264
 rob+0.250
 harms+0.249
cade+0.246
pha+0.235
Neg logit contributions
-0.289
ˈ-0.274
joy-0.274
 Twain-0.272
TPPStreamerBot-0.271
Token,
Token ID11
Feature activation+4.42e-01

Pos logit contributions
alian+0.320
 rob+0.300
 harms+0.300
cade+0.296
pha+0.282
Neg logit contributions
-0.418
ˈ-0.399
joy-0.399
 Twain-0.397
TPPStreamerBot-0.394
Token across
Token ID1973
Feature activation+1.66e+00

Pos logit contributions
alian+0.264
 rob+0.251
 harms+0.250
cade+0.245
kai+0.233
Neg logit contributions
-0.353
joy-0.335
ˈ-0.334
TPPStreamerBot-0.331
 Twain-0.331
Token said
Token ID531
Feature activation-6.91e-01

Pos logit contributions
+0.336
ˈ+0.322
joy+0.321
 Twain+0.319
TPPStreamerBot+0.317
Neg logit contributions
alian-0.272
 rob-0.256
 harms-0.255
cade-0.252
pha-0.240
Token the
Token ID262
Feature activation-7.23e-01

Pos logit contributions
+0.484
joy+0.461
ˈ+0.460
 Twain+0.459
TPPStreamerBot+0.454
Neg logit contributions
alian-0.475
 rob-0.448
 harms-0.447
cade-0.443
pha-0.424
Token decision
Token ID2551
Feature activation+1.63e+00

Pos logit contributions
+0.505
joy+0.480
ˈ+0.480
 Twain+0.477
TPPStreamerBot+0.473
Neg logit contributions
alian-0.499
 rob-0.473
 harms-0.472
cade-0.466
pha-0.447
Token gives
Token ID3607
Feature activation-1.20e+00

Pos logit contributions
alian+0.948
 harms+0.892
 rob+0.892
cade+0.870
pha+0.827
Neg logit contributions
-1.325
joy-1.265
ˈ-1.263
 Twain-1.254
TPPStreamerBot-1.252
Token his
Token ID465
Feature activation-6.57e-01

Pos logit contributions
+0.816
joy+0.775
ˈ+0.775
 Twain+0.770
TPPStreamerBot+0.763
Neg logit contributions
alian-0.855
 rob-0.809
 harms-0.807
cade-0.800
pha-0.766
Token client
Token ID5456
Feature activation+3.78e+00

Pos logit contributions
+0.506
joy+0.485
ˈ+0.484
 Twain+0.482
TPPStreamerBot+0.476
Neg logit contributions
alian-0.404
 rob-0.378
 harms-0.378
cade-0.375
pha-0.359
Token a
Token ID257
Feature activation-2.37e-01

Pos logit contributions
alian+2.423
 harms+2.337
 rob+2.299
cade+2.246
pha+2.167
Neg logit contributions
-2.800
TPPStreamerBot-2.649
joy-2.643
ˈ-2.634
 Twain-2.628
Token new
Token ID649
Feature activation-6.53e-01

Pos logit contributions
+0.166
ˈ+0.156
TPPStreamerBot+0.155
joy+0.155
 Twain+0.154
Neg logit contributions
alian-0.164
 rob-0.159
 harms-0.158
cade-0.154
pha-0.149
Token avenue
Token ID36132
Feature activation+5.39e-01

Pos logit contributions
+0.467
ˈ+0.442
 Twain+0.437
TPPStreamerBot+0.436
joy+0.436
Neg logit contributions
alian-0.444
 rob-0.426
 harms-0.423
cade-0.414
pha-0.400
Token to
Token ID284
Feature activation+1.24e-01

Pos logit contributions
alian+0.317
 rob+0.297
 harms+0.297
cade+0.292
pha+0.278
Neg logit contributions
-0.433
ˈ-0.414
joy-0.414
 Twain-0.411
TPPStreamerBot-0.409
Token apply
Token ID4174
Feature activation+2.50e-01

Pos logit contributions
alian+0.089
 rob+0.085
 harms+0.085
cade+0.084
pha+0.080
Neg logit contributions
-0.083
joy-0.079
ˈ-0.079
 Twain-0.078
TPPStreamerBot-0.078
Token!
Token ID0
Feature activation-5.77e-01

Pos logit contributions
+0.543
joy+0.534
ˈ+0.520
 Twain+0.520
 scrambled+0.516
Neg logit contributions
alian-0.373
cade-0.342
 rob-0.339
 harms-0.334
pha-0.324
Token Sign
Token ID5865
Feature activation-1.80e-01

Pos logit contributions
+0.340
joy+0.317
ˈ+0.316
TPPStreamerBot+0.315
 Twain+0.314
Neg logit contributions
alian-0.464
 rob-0.443
 harms-0.441
cade-0.436
pha-0.422
Token up
Token ID510
Feature activation-5.97e-01

Pos logit contributions
+0.157
joy+0.150
ˈ+0.150
 Twain+0.149
TPPStreamerBot+0.149
Neg logit contributions
alian-0.094
 rob-0.088
 harms-0.087
cade-0.086
ao-0.081
Token for
Token ID329
Feature activation-1.04e-01

Pos logit contributions
+0.492
joy+0.470
ˈ+0.469
 Twain+0.467
TPPStreamerBot+0.464
Neg logit contributions
alian-0.339
 rob-0.318
 harms-0.317
cade-0.312
pha-0.296
Token our
Token ID674
Feature activation+6.47e-01

Pos logit contributions
+0.081
joy+0.078
ˈ+0.077
 Twain+0.077
TPPStreamerBot+0.077
Neg logit contributions
alian-0.064
 rob-0.060
 harms-0.059
cade-0.059
pha-0.057
Token Email
Token ID9570
Feature activation+3.77e+00

Pos logit contributions
alian+0.435
 rob+0.412
 harms+0.411
cade+0.404
pha+0.386
Neg logit contributions
-0.466
ˈ-0.443
joy-0.443
 Twain-0.440
TPPStreamerBot-0.439
Token News
Token ID3000
Feature activation+7.04e-01

Pos logit contributions
alian+2.531
 rob+2.437
 harms+2.432
cade+2.422
ctl+2.310
Neg logit contributions
-2.697
ˈ-2.541
TPPStreamerBot-2.531
joy-2.521
 Twain-2.507
Tokenletters
Token ID15653
Feature activation+3.01e+00

Pos logit contributions
alian+0.454
 rob+0.431
 harms+0.430
cade+0.423
ao+0.404
Neg logit contributions
-0.525
ˈ-0.501
joy-0.497
 Twain-0.496
TPPStreamerBot-0.493
Token here
Token ID994
Feature activation+1.44e+00

Pos logit contributions
alian+1.522
 harms+1.391
 rob+1.386
cade+1.371
pha+1.290
Neg logit contributions
-2.676
ˈ-2.573
joy-2.572
 Twain-2.566
TPPStreamerBot-2.535
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
alian+0.655
 rob+0.616
 harms+0.611
cade+0.580
ctl+0.571
Neg logit contributions
-1.364
ˈ-1.292
TPPStreamerBot-1.292
 Twain-1.277
joy-1.268
Token<|endoftext|>
Token ID50256
Feature activation-4.51e-01

Pos logit contributions
alian+0.178
 harms+0.170
 rob+0.170
cade+0.166
ctl+0.162
Neg logit contributions
-0.164
TPPStreamerBot-0.154
 Twain-0.154
ˈ-0.153
joy-0.153
Token in
Token ID287
Feature activation+4.70e-01

Pos logit contributions
alian+0.348
 rob+0.336
 harms+0.332
cade+0.325
kai+0.313
Neg logit contributions
-0.417
ˈ-0.392
joy-0.391
 Twain-0.389
TPPStreamerBot-0.386
Token an
Token ID281
Feature activation+3.28e-01

Pos logit contributions
alian+0.301
 harms+0.288
 rob+0.287
cade+0.282
pha+0.269
Neg logit contributions
-0.352
ˈ-0.335
joy-0.333
 Twain-0.331
TPPStreamerBot-0.330
Token eight
Token ID3624
Feature activation+1.25e+00

Pos logit contributions
alian+0.222
 rob+0.213
 harms+0.212
cade+0.207
ao+0.200
Neg logit contributions
-0.235
joy-0.222
ˈ-0.220
 Twain-0.218
TPPStreamerBot-0.217
Token-
Token ID12
Feature activation+9.11e-02

Pos logit contributions
alian+0.812
 rob+0.770
 harms+0.764
cade+0.755
ao+0.721
Neg logit contributions
-0.927
ˈ-0.881
joy-0.880
 Twain-0.873
TPPStreamerBot-0.869
Tokenman
Token ID805
Feature activation+2.19e-01

Pos logit contributions
alian+0.068
 rob+0.065
 harms+0.065
cade+0.064
pha+0.061
Neg logit contributions
-0.059
ˈ-0.055
joy-0.055
 Twain-0.055
TPPStreamerBot-0.055
Token front
Token ID2166
Feature activation+3.76e+00

Pos logit contributions
alian+0.144
 rob+0.138
 harms+0.137
cade+0.135
ao+0.129
Neg logit contributions
-0.161
joy-0.153
ˈ-0.152
 Twain-0.151
TPPStreamerBot-0.151
Token,
Token ID11
Feature activation+4.00e-01

Pos logit contributions
alian+2.135
 rob+2.006
cade+1.976
 harms+1.969
kai+1.872
Neg logit contributions
-3.122
ˈ-2.968
joy-2.945
TPPStreamerBot-2.943
 Twain-2.938
Token but
Token ID475
Feature activation+8.51e-01

Pos logit contributions
alian+0.240
 rob+0.227
 harms+0.226
cade+0.222
pha+0.211
Neg logit contributions
-0.317
ˈ-0.302
joy-0.302
 Twain-0.300
TPPStreamerBot-0.298
Token still
Token ID991
Feature activation+1.46e+00

Pos logit contributions
alian+0.543
 rob+0.516
 harms+0.514
cade+0.506
pha+0.483
Neg logit contributions
-0.642
ˈ-0.610
joy-0.608
 Twain-0.603
TPPStreamerBot-0.601
Token overwhelmed
Token ID20974
Feature activation-9.69e-01

Pos logit contributions
alian+0.866
 harms+0.826
 rob+0.824
cade+0.802
ao+0.764
Neg logit contributions
-1.162
ˈ-1.107
joy-1.102
 Twain-1.095
TPPStreamerBot-1.093
Token at
Token ID379
Feature activation-4.82e-01

Pos logit contributions
+0.710
joy+0.678
ˈ+0.677
 Twain+0.674
TPPStreamerBot+0.668
Neg logit contributions
alian-0.636
 rob-0.599
 harms-0.598
cade-0.591
pha-0.566
Token D
Token ID360
Feature activation+1.63e+00

Pos logit contributions
alian+1.348
 rob+1.311
 harms+1.291
cade+1.277
kai+1.228
Neg logit contributions
-1.406
TPPStreamerBot-1.283
ˈ-1.273
joy-1.258
 unbeat-1.226
Token.
Token ID13
Feature activation+2.58e+00

Pos logit contributions
alian+0.857
 rob+0.792
 harms+0.790
cade+0.776
pha+0.736
Neg logit contributions
-1.419
ˈ-1.358
joy-1.357
 Twain-1.353
TPPStreamerBot-1.350
Token S
Token ID311
Feature activation+1.57e+00

Pos logit contributions
alian+1.743
 rob+1.669
 harms+1.653
cade+1.633
ao+1.569
Neg logit contributions
-1.908
TPPStreamerBot-1.774
ˈ-1.748
joy-1.724
 unbeat-1.688
Token.
Token ID13
Feature activation+2.73e+00

Pos logit contributions
alian+0.850
 rob+0.788
 harms+0.787
cade+0.774
pha+0.736
Neg logit contributions
-1.332
ˈ-1.275
joy-1.272
 Twain-1.270
TPPStreamerBot-1.267
Token (
Token ID357
Feature activation+1.59e+00

Pos logit contributions
alian+1.635
 rob+1.534
 harms+1.526
cade+1.498
kai+1.443
Neg logit contributions
-2.177
TPPStreamerBot-2.076
ˈ-2.052
joy-2.044
 Twain-2.030
Token 1984
Token ID12844
Feature activation+3.75e+00

Pos logit contributions
alian+1.050
 rob+1.014
 harms+0.999
cade+0.990
kai+0.946
Neg logit contributions
-1.171
TPPStreamerBot-1.089
ˈ-1.087
joy-1.085
 Twain-1.064
Token ).
Token ID6739
Feature activation+3.04e+00

Pos logit contributions
alian+2.407
 rob+2.283
 harms+2.252
cade+2.247
ao+2.148
Neg logit contributions
-2.787
ˈ-2.656
joy-2.647
TPPStreamerBot-2.643
 Twain-2.638
Token P
Token ID350
Feature activation+1.48e+00

Pos logit contributions
alian+1.990
 harms+1.905
 rob+1.895
cade+1.859
pha+1.782
Neg logit contributions
-2.240
joy-2.097
TPPStreamerBot-2.095
ˈ-2.094
 Twain-2.049
Tokeniers
Token ID3183
Feature activation-1.51e+00

Pos logit contributions
alian+0.970
 rob+0.917
 harms+0.911
cade+0.893
ao+0.870
Neg logit contributions
-1.095
ˈ-1.033
TPPStreamerBot-1.033
 Twain-1.032
joy-1.028
Token-
Token ID12
Feature activation+2.12e-01

Pos logit contributions
+1.160
joy+1.126
 Twain+1.121
ˈ+1.113
TPPStreamerBot+1.093
Neg logit contributions
alian-0.930
 harms-0.867
 rob-0.866
cade-0.858
pha-0.818
TokenHarris
Token ID41589
Feature activation-1.32e+00

Pos logit contributions
alian+0.146
 rob+0.138
 harms+0.138
cade+0.136
pha+0.131
Neg logit contributions
-0.149
ˈ-0.141
joy-0.141
 Twain-0.140
TPPStreamerBot-0.139
Token free
Token ID1479
Feature activation-5.14e-01

Pos logit contributions
+0.601
ˈ+0.578
joy+0.577
 Twain+0.575
TPPStreamerBot+0.569
Neg logit contributions
alian-0.446
 harms-0.417
 rob-0.415
cade-0.410
pha-0.390
Token agent
Token ID5797
Feature activation-2.95e-01

Pos logit contributions
+0.313
ˈ+0.295
joy+0.295
 Twain+0.293
TPPStreamerBot+0.289
Neg logit contributions
alian-0.401
 harms-0.381
 rob-0.381
cade-0.377
pha-0.364
Token from
Token ID422
Feature activation+4.78e-01

Pos logit contributions
+0.232
joy+0.220
ˈ+0.220
 Twain+0.217
TPPStreamerBot+0.217
Neg logit contributions
alian-0.181
 rob-0.171
 harms-0.170
cade-0.168
pha-0.159
Token Denver
Token ID10656
Feature activation+1.29e+00

Pos logit contributions
alian+0.326
 rob+0.313
 harms+0.311
cade+0.306
ao+0.293
Neg logit contributions
-0.339
ˈ-0.321
joy-0.320
TPPStreamerBot-0.317
 Twain-0.316
Token,-
Token ID12095
Feature activation-1.29e+00

Pos logit contributions
alian+0.763
 rob+0.717
 harms+0.709
cade+0.708
ao+0.668
Neg logit contributions
-1.034
joy-0.978
ˈ-0.973
TPPStreamerBot-0.970
 Twain-0.968
Token certainly
Token ID3729
Feature activation+3.74e+00

Pos logit contributions
+0.990
ˈ+0.947
joy+0.947
 Twain+0.940
TPPStreamerBot+0.935
Neg logit contributions
alian-0.798
 rob-0.752
 harms-0.751
cade-0.737
pha-0.704
Token looks
Token ID3073
Feature activation-8.53e-01

Pos logit contributions
alian+2.189
 harms+2.082
 rob+2.069
cade+2.008
ao+1.905
Neg logit contributions
-3.048
TPPStreamerBot-2.859
joy-2.855
ˈ-2.848
 Twain-2.842
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
+0.649
ˈ+0.618
joy+0.617
 Twain+0.614
TPPStreamerBot+0.610
Neg logit contributions
alian-0.538
 rob-0.509
 harms-0.507
cade-0.500
pha-0.477
Token part
Token ID636
Feature activation-6.10e-01

Pos logit contributions
+0.089
ˈ+0.085
joy+0.085
 Twain+0.084
TPPStreamerBot+0.084
Neg logit contributions
alian-0.080
 rob-0.076
 harms-0.076
cade-0.075
pha-0.071
Token at
Token ID379
Feature activation-1.22e-01

Pos logit contributions
+0.499
ˈ+0.482
joy+0.482
 Twain+0.479
TPPStreamerBot+0.475
Neg logit contributions
alian-0.343
 harms-0.323
 rob-0.322
cade-0.317
pha-0.302
Token 6
Token ID718
Feature activation+4.24e-01

Pos logit contributions
+0.090
ˈ+0.086
joy+0.086
 Twain+0.085
TPPStreamerBot+0.085
Neg logit contributions
alian-0.079
 rob-0.075
 harms-0.075
cade-0.073
pha-0.070
Token")
Token ID4943
Feature activation-2.57e-01

Pos logit contributions
+0.317
ˈ+0.301
joy+0.301
 Twain+0.300
TPPStreamerBot+0.297
Neg logit contributions
alian-0.297
 rob-0.280
 harms-0.280
cade-0.277
pha-0.265
Token $
Token ID720
Feature activation+9.74e-01

Pos logit contributions
+0.191
joy+0.182
ˈ+0.182
 Twain+0.181
TPPStreamerBot+0.179
Neg logit contributions
alian-0.166
 harms-0.157
 rob-0.156
cade-0.155
pha-0.147
Tokeni
Token ID72
Feature activation+7.42e-01

Pos logit contributions
alian+0.624
 rob+0.589
 harms+0.587
cade+0.580
pha+0.555
Neg logit contributions
-0.731
ˈ-0.696
joy-0.695
 Twain-0.692
TPPStreamerBot-0.686
Token =
Token ID796
Feature activation-1.62e-01

Pos logit contributions
alian+0.361
 harms+0.335
 rob+0.334
cade+0.327
pha+0.307
Neg logit contributions
-0.669
joy-0.646
ˈ-0.644
 Twain-0.641
TPPStreamerBot-0.638
Token 1
Token ID352
Feature activation+4.67e-01

Pos logit contributions
+0.113
joy+0.107
ˈ+0.107
 Twain+0.106
TPPStreamerBot+0.106
Neg logit contributions
alian-0.112
 rob-0.107
 harms-0.106
cade-0.105
pha-0.101
Token Try
Token ID9993
Feature activation+3.72e+00

Pos logit contributions
alian+0.288
 rob+0.271
 harms+0.270
cade+0.267
pha+0.254
Neg logit contributions
-0.361
joy-0.345
ˈ-0.345
 Twain-0.343
TPPStreamerBot-0.340
Token {
Token ID1391
Feature activation+1.88e+00

Pos logit contributions
alian+2.833
 rob+2.737
 harms+2.686
cade+2.663
pha+2.580
Neg logit contributions
-2.333
ˈ-2.197
joy-2.185
 Twain-2.164
TPPStreamerBot-2.153
Token for
Token ID329
Feature activation+1.78e+00

Pos logit contributions
alian+1.275
 rob+1.221
 harms+1.203
cade+1.189
pha+1.142
Neg logit contributions
-1.341
joy-1.273
ˈ-1.273
TPPStreamerBot-1.263
 Twain-1.258
Token ($
Token ID7198
Feature activation+1.57e+00

Pos logit contributions
alian+1.086
 rob+1.023
 harms+1.019
cade+1.005
pha+0.958
Neg logit contributions
-1.387
joy-1.322
ˈ-1.322
 Twain-1.313
TPPStreamerBot-1.306
Tokeni
Token ID72
Feature activation+1.08e+00

Pos logit contributions
alian+0.833
 rob+0.776
 harms+0.774
cade+0.761
pha+0.719
Neg logit contributions
-1.355
joy-1.300
ˈ-1.300
 Twain-1.292
TPPStreamerBot-1.285
Token ;
Token ID2162
Feature activation+6.75e-01

Pos logit contributions
alian+0.326
 harms+0.288
 rob+0.287
cade+0.279
pha+0.249
Neg logit contributions
-1.173
joy-1.142
ˈ-1.139
 Twain-1.138
TPPStreamerBot-1.132
Token day
Token ID1110
Feature activation-1.61e-01

Pos logit contributions
alian+0.461
 rob+0.434
 harms+0.432
cade+0.426
pha+0.406
Neg logit contributions
-0.606
ˈ-0.578
joy-0.578
 Twain-0.575
TPPStreamerBot-0.571
Token (
Token ID357
Feature activation-5.64e-01

Pos logit contributions
+0.130
joy+0.125
ˈ+0.125
 Twain+0.124
TPPStreamerBot+0.123
Neg logit contributions
alian-0.093
 harms-0.087
 rob-0.087
cade-0.086
pha-0.082
Tokenand
Token ID392
Feature activation+6.93e-01

Pos logit contributions
+0.386
joy+0.368
ˈ+0.368
 Twain+0.364
TPPStreamerBot+0.362
Neg logit contributions
alian-0.397
 rob-0.377
 harms-0.377
cade-0.372
pha-0.357
Token eliminate
Token ID11005
Feature activation-3.41e-01

Pos logit contributions
alian+0.453
 rob+0.433
 harms+0.429
cade+0.419
ao+0.403
Neg logit contributions
-0.516
joy-0.486
ˈ-0.485
 Twain-0.481
TPPStreamerBot-0.480
Token sn
Token ID3013
Feature activation-1.59e+00

Pos logit contributions
+0.254
ˈ+0.242
joy+0.242
 Twain+0.240
TPPStreamerBot+0.239
Neg logit contributions
alian-0.220
 rob-0.208
 harms-0.208
cade-0.205
pha-0.196
Tokenacking
Token ID5430
Feature activation-5.15e+00

Pos logit contributions
+1.238
ˈ+1.218
joy+1.215
 Twain+1.200
 scrambled+1.186
Neg logit contributions
alian-0.919
 harms-0.872
 rob-0.867
cade-0.848
pha-0.810
Token).
Token ID737
Feature activation-3.87e-01

Pos logit contributions
+3.623
joy+3.527
ˈ+3.520
 Twain+3.505
 scrambled+3.485
Neg logit contributions
alian-3.320
cade-3.162
 rob-3.111
 harms-3.063
pha-2.983
Token The
Token ID383
Feature activation-1.98e-01

Pos logit contributions
+0.279
joy+0.264
ˈ+0.264
 Twain+0.262
TPPStreamerBot+0.261
Neg logit contributions
alian-0.260
 rob-0.246
 harms-0.245
cade-0.242
pha-0.232
Token easiest
Token ID16638
Feature activation+3.07e-02

Pos logit contributions
+0.141
ˈ+0.134
joy+0.134
 Twain+0.133
TPPStreamerBot+0.132
Neg logit contributions
alian-0.134
 rob-0.127
 harms-0.126
cade-0.125
pha-0.120
Token and
Token ID290
Feature activation-2.81e-01

Pos logit contributions
alian+0.025
 rob+0.024
 harms+0.024
cade+0.024
pha+0.023
Neg logit contributions
-0.017
joy-0.016
ˈ-0.016
 Twain-0.016
TPPStreamerBot-0.016
Token best
Token ID1266
Feature activation-1.89e-02

Pos logit contributions
+0.212
ˈ+0.202
joy+0.202
 Twain+0.200
TPPStreamerBot+0.199
Neg logit contributions
alian-0.179
 rob-0.169
 harms-0.169
cade-0.166
pha-0.159
Token he
Token ID339
Feature activation+1.70e-01

Pos logit contributions
alian+0.180
 rob+0.171
 harms+0.170
cade+0.168
ao+0.160
Neg logit contributions
-0.190
ˈ-0.180
joy-0.179
 Twain-0.178
TPPStreamerBot-0.177
Token offered
Token ID4438
Feature activation+3.78e-01

Pos logit contributions
alian+0.116
 rob+0.110
 harms+0.109
cade+0.108
kai+0.103
Neg logit contributions
-0.121
joy-0.114
ˈ-0.114
 Twain-0.114
TPPStreamerBot-0.113
Token a
Token ID257
Feature activation+6.35e-02

Pos logit contributions
alian+0.247
 rob+0.234
 harms+0.233
cade+0.229
pha+0.219
Neg logit contributions
-0.281
ˈ-0.266
joy-0.266
 Twain-0.264
TPPStreamerBot-0.263
Token tweet
Token ID6126
Feature activation+6.99e-01

Pos logit contributions
alian+0.043
 rob+0.041
 harms+0.041
cade+0.040
pha+0.039
Neg logit contributions
-0.045
joy-0.043
ˈ-0.043
 Twain-0.043
TPPStreamerBot-0.042
Token of
Token ID286
Feature activation+2.64e-01

Pos logit contributions
alian+0.380
 harms+0.356
 rob+0.355
cade+0.349
pha+0.332
Neg logit contributions
-0.588
joy-0.567
ˈ-0.565
 Twain-0.563
TPPStreamerBot-0.559
Token condol
Token ID35059
Feature activation-4.66e+00

Pos logit contributions
alian+0.182
 rob+0.174
 harms+0.173
cade+0.170
pha+0.163
Neg logit contributions
-0.186
ˈ-0.175
joy-0.174
 Twain-0.173
TPPStreamerBot-0.173
Tokenence
Token ID594
Feature activation-1.23e+00

Pos logit contributions
+2.809
joy+2.795
ˈ+2.728
 Twain+2.681
TPPStreamerBot+2.670
Neg logit contributions
alian-3.546
 harms-3.410
 rob-3.390
cade-3.320
pha-3.179
Token to
Token ID284
Feature activation+2.19e-01

Pos logit contributions
+0.966
joy+0.933
 Twain+0.926
ˈ+0.926
TPPStreamerBot+0.915
Neg logit contributions
alian-0.734
 harms-0.686
 rob-0.684
cade-0.677
pha-0.645
Token those
Token ID883
Feature activation-7.96e-01

Pos logit contributions
alian+0.144
 rob+0.136
 harms+0.136
cade+0.134
pha+0.129
Neg logit contributions
-0.159
joy-0.152
ˈ-0.152
 Twain-0.151
TPPStreamerBot-0.150
Token affected
Token ID5676
Feature activation-6.13e-01

Pos logit contributions
+0.644
joy+0.619
ˈ+0.617
 Twain+0.616
TPPStreamerBot+0.610
Neg logit contributions
alian-0.460
 rob-0.430
 harms-0.428
cade-0.423
pha-0.405
Token by
Token ID416
Feature activation+1.18e+00

Pos logit contributions
+0.443
joy+0.427
ˈ+0.426
 Twain+0.422
TPPStreamerBot+0.417
Neg logit contributions
alian-0.403
 rob-0.379
 harms-0.376
cade-0.373
pha-0.361
Token a
Token ID257
Feature activation-2.79e-01

Pos logit contributions
+0.287
joy+0.273
ˈ+0.273
 Twain+0.271
TPPStreamerBot+0.269
Neg logit contributions
alian-0.251
 rob-0.238
 harms-0.237
cade-0.233
pha-0.223
Token giant
Token ID6175
Feature activation-9.24e-01

Pos logit contributions
+0.207
ˈ+0.199
joy+0.198
 Twain+0.197
TPPStreamerBot+0.196
Neg logit contributions
alian-0.179
 harms-0.168
 rob-0.168
cade-0.167
pha-0.158
Token lizard
Token ID42406
Feature activation+1.32e-01

Pos logit contributions
+0.743
joy+0.717
ˈ+0.715
 Twain+0.712
TPPStreamerBot+0.705
Neg logit contributions
alian-0.532
 harms-0.498
cade-0.496
 rob-0.492
pha-0.465
Token that
Token ID326
Feature activation+3.72e-02

Pos logit contributions
alian+0.077
 rob+0.073
 harms+0.072
cade+0.071
pha+0.068
Neg logit contributions
-0.107
ˈ-0.102
joy-0.102
 Twain-0.101
TPPStreamerBot-0.101
Token sw
Token ID1509
Feature activation-2.41e-01

Pos logit contributions
alian+0.023
 rob+0.022
 harms+0.022
cade+0.021
pha+0.020
Neg logit contributions
-0.029
joy-0.028
ˈ-0.027
 Twain-0.027
TPPStreamerBot-0.027
Tokenam
Token ID321
Feature activation-4.36e+00

Pos logit contributions
+0.203
ˈ+0.197
joy+0.197
 Twain+0.194
TPPStreamerBot+0.193
Neg logit contributions
alian-0.128
 rob-0.121
 harms-0.121
cade-0.118
pha-0.112
Token in
Token ID287
Feature activation-1.25e-01

Pos logit contributions
+3.198
ˈ+3.127
joy+3.118
 Twain+3.093
 scrambled+3.059
Neg logit contributions
alian-2.725
cade-2.549
 rob-2.526
 harms-2.509
ctl-2.412
Token shallow
Token ID19337
Feature activation+2.28e-01

Pos logit contributions
+0.093
joy+0.088
ˈ+0.088
 Twain+0.088
TPPStreamerBot+0.087
Neg logit contributions
alian-0.080
 rob-0.076
 harms-0.076
cade-0.075
pha-0.072
Token ocean
Token ID9151
Feature activation-2.25e+00

Pos logit contributions
alian+0.138
 rob+0.128
 harms+0.128
cade+0.128
pha+0.121
Neg logit contributions
-0.179
ˈ-0.171
joy-0.171
 Twain-0.171
TPPStreamerBot-0.169
Token waters
Token ID10150
Feature activation-9.83e-01

Pos logit contributions
+1.795
ˈ+1.724
joy+1.722
 Twain+1.712
TPPStreamerBot+1.686
Neg logit contributions
alian-1.304
cade-1.222
 rob-1.212
 harms-1.201
ctl-1.153
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
+0.794
joy+0.764
ˈ+0.763
 Twain+0.759
TPPStreamerBot+0.752
Neg logit contributions
alian-0.567
 rob-0.530
 harms-0.529
cade-0.524
pha-0.498
Token time
Token ID640
Feature activation+1.67e+00

Pos logit contributions
alian+0.760
 rob+0.732
 harms+0.731
cade+0.713
ao+0.688
Neg logit contributions
-0.738
ˈ-0.694
joy-0.687
TPPStreamerBot-0.685
 Twain-0.680
Token and
Token ID290
Feature activation+1.08e-01

Pos logit contributions
alian+0.993
 rob+0.938
 harms+0.933
cade+0.915
pha+0.873
Neg logit contributions
-1.336
ˈ-1.272
joy-1.268
 Twain-1.265
TPPStreamerBot-1.259
Token attention
Token ID3241
Feature activation+1.40e-01

Pos logit contributions
alian+0.078
 rob+0.074
 harms+0.074
cade+0.073
pha+0.070
Neg logit contributions
-0.073
ˈ-0.069
joy-0.068
TPPStreamerBot-0.068
 Twain-0.068
Token to
Token ID284
Feature activation-6.77e-01

Pos logit contributions
alian+0.087
 harms+0.082
 rob+0.082
cade+0.081
pha+0.077
Neg logit contributions
-0.108
joy-0.103
ˈ-0.103
 Twain-0.103
TPPStreamerBot-0.102
Token the
Token ID262
Feature activation-3.21e-01

Pos logit contributions
+0.488
joy+0.467
ˈ+0.464
 Twain+0.464
TPPStreamerBot+0.457
Neg logit contributions
alian-0.453
 rob-0.424
 harms-0.424
cade-0.421
pha-0.403
Token bell
Token ID8966
Feature activation-4.33e+00

Pos logit contributions
+0.235
joy+0.225
ˈ+0.224
 Twain+0.223
TPPStreamerBot+0.221
Neg logit contributions
alian-0.211
 rob-0.198
 harms-0.198
cade-0.196
pha-0.188
Tokenes
Token ID274
Feature activation-7.27e-01

Pos logit contributions
joy+3.554
+3.540
ˈ+3.456
 Twain+3.455
 scrambled+3.395
Neg logit contributions
alian-2.270
 harms-2.120
 rob-2.069
cade-2.031
kai-1.973
Token of
Token ID286
Feature activation-5.11e-01

Pos logit contributions
+0.556
joy+0.530
ˈ+0.530
 Twain+0.527
TPPStreamerBot+0.522
Neg logit contributions
alian-0.455
 rob-0.428
 harms-0.428
cade-0.421
pha-0.402
Token the
Token ID262
Feature activation-6.53e-01

Pos logit contributions
+0.369
joy+0.353
ˈ+0.352
 Twain+0.350
TPPStreamerBot+0.346
Neg logit contributions
alian-0.341
 rob-0.321
 harms-0.321
cade-0.317
pha-0.304
Token evening
Token ID6180
Feature activation-1.10e+00

Pos logit contributions
+0.468
joy+0.445
ˈ+0.445
 Twain+0.443
TPPStreamerBot+0.439
Neg logit contributions
alian-0.440
 rob-0.415
 harms-0.415
cade-0.410
pha-0.393
Token,
Token ID11
Feature activation-9.55e-01

Pos logit contributions
+0.852
joy+0.823
ˈ+0.817
 Twain+0.815
TPPStreamerBot+0.808
Neg logit contributions
alian-0.666
 harms-0.625
 rob-0.621
cade-0.614
pha-0.593
Token CPUs
Token ID32340
Feature activation-8.53e-01

Pos logit contributions
alian+0.168
 rob+0.160
 harms+0.159
cade+0.157
pha+0.150
Neg logit contributions
-0.188
ˈ-0.179
joy-0.179
 Twain-0.178
TPPStreamerBot-0.177
Token and
Token ID290
Feature activation-2.73e-01

Pos logit contributions
+0.670
joy+0.644
ˈ+0.642
 Twain+0.639
TPPStreamerBot+0.633
Neg logit contributions
alian-0.511
 rob-0.479
 harms-0.477
cade-0.473
pha-0.451
Token memory
Token ID4088
Feature activation-9.19e-01

Pos logit contributions
+0.214
joy+0.204
ˈ+0.204
 Twain+0.203
TPPStreamerBot+0.201
Neg logit contributions
alian-0.166
 rob-0.156
 harms-0.156
cade-0.154
pha-0.146
Token (
Token ID357
Feature activation-1.09e+00

Pos logit contributions
+0.745
joy+0.718
ˈ+0.713
 Twain+0.711
TPPStreamerBot+0.706
Neg logit contributions
alian-0.529
 rob-0.493
 harms-0.491
cade-0.486
pha-0.462
TokenIntel
Token ID24123
Feature activation-4.15e+00

Pos logit contributions
+0.844
joy+0.811
ˈ+0.808
 Twain+0.801
TPPStreamerBot+0.797
Neg logit contributions
alian-0.669
 harms-0.630
 rob-0.630
cade-0.618
pha-0.590
Token VT
Token ID32751
Feature activation-4.32e+00

Pos logit contributions
+3.002
joy+2.927
ˈ+2.907
 Twain+2.871
 scrambled+2.827
Neg logit contributions
alian-2.699
 harms-2.539
 rob-2.512
cade-2.484
pha-2.383
Token-
Token ID12
Feature activation-3.00e-01

Pos logit contributions
+3.034
joy+2.907
 Twain+2.865
ˈ+2.859
TPPStreamerBot+2.838
Neg logit contributions
alian-2.959
 rob-2.811
 harms-2.785
cade-2.729
pha-2.650
Tokenx
Token ID87
Feature activation+1.18e-01

Pos logit contributions
+0.289
joy+0.279
ˈ+0.277
TPPStreamerBot+0.276
 Twain+0.276
Neg logit contributions
alian-0.128
 rob-0.119
 harms-0.118
cade-0.113
pha-0.107
Token,
Token ID11
Feature activation-4.88e-01

Pos logit contributions
alian+0.070
 rob+0.066
 harms+0.065
cade+0.064
pha+0.061
Neg logit contributions
-0.095
ˈ-0.091
joy-0.090
 Twain-0.090
TPPStreamerBot-0.090
Token AMD
Token ID10324
Feature activation-2.36e+00

Pos logit contributions
+0.365
joy+0.349
ˈ+0.348
 Twain+0.346
TPPStreamerBot+0.343
Neg logit contributions
alian-0.313
 rob-0.294
 harms-0.294
cade-0.290
pha-0.278
Token-
Token ID12
Feature activation-5.93e-01

Pos logit contributions
+1.785
joy+1.734
ˈ+1.712
 Twain+1.710
TPPStreamerBot+1.680
Neg logit contributions
alian-1.460
 harms-1.376
 rob-1.360
cade-1.346
pha-1.294
Token disappointed
Token ID11679
Feature activation-8.76e-01

Pos logit contributions
+0.174
ˈ+0.165
joy+0.165
 Twain+0.164
TPPStreamerBot+0.163
Neg logit contributions
alian-0.147
 rob-0.139
 harms-0.138
cade-0.136
pha-0.130
Token but
Token ID475
Feature activation+1.70e-01

Pos logit contributions
+0.714
joy+0.685
ˈ+0.683
 Twain+0.679
TPPStreamerBot+0.676
Neg logit contributions
alian-0.502
 rob-0.470
 harms-0.469
cade-0.462
pha-0.440
Token Canadians
Token ID14008
Feature activation+1.34e+00

Pos logit contributions
alian+0.107
 rob+0.102
 harms+0.101
cade+0.100
pha+0.095
Neg logit contributions
-0.129
ˈ-0.123
joy-0.123
 Twain-0.122
TPPStreamerBot-0.121
Token as
Token ID355
Feature activation-1.31e-01

Pos logit contributions
alian+0.885
 rob+0.837
 harms+0.834
cade+0.824
pha+0.784
Neg logit contributions
-0.986
ˈ-0.937
joy-0.934
 Twain-0.930
TPPStreamerBot-0.924
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
+0.099
ˈ+0.094
joy+0.094
 Twain+0.094
TPPStreamerBot+0.093
Neg logit contributions
alian-0.083
 rob-0.078
 harms-0.078
cade-0.077
pha-0.073
Token whole
Token ID2187
Feature activation-4.15e+00

Pos logit contributions
+0.637
ˈ+0.596
joy+0.595
 Twain+0.589
TPPStreamerBot+0.582
Neg logit contributions
alian-1.065
 rob-1.020
 harms-1.019
cade-1.009
pha-0.976
Token are
Token ID389
Feature activation-1.29e-01

Pos logit contributions
+3.328
joy+3.212
ˈ+3.198
 Twain+3.158
TPPStreamerBot+3.141
Neg logit contributions
alian-2.363
 rob-2.215
 harms-2.210
cade-2.185
pha-2.092
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
+0.096
ˈ+0.092
joy+0.092
 Twain+0.091
TPPStreamerBot+0.090
Neg logit contributions
alian-0.083
 rob-0.079
 harms-0.079
cade-0.078
pha-0.074
Token
Token ID447
Feature activation-2.39e-01

Pos logit contributions
alian+0.076
 rob+0.072
 harms+0.072
cade+0.071
pha+0.068
Neg logit contributions
-0.077
ˈ-0.072
joy-0.072
 Twain-0.072
TPPStreamerBot-0.071
Token
Token ID251
Feature activation-3.12e-01

Pos logit contributions
+0.117
joy+0.108
ˈ+0.108
 Twain+0.107
TPPStreamerBot+0.106
Neg logit contributions
alian-0.215
 rob-0.207
 harms-0.206
cade-0.204
pha-0.198
Token said
Token ID531
Feature activation-2.74e-01

Pos logit contributions
+0.233
joy+0.222
ˈ+0.222
 Twain+0.221
TPPStreamerBot+0.219
Neg logit contributions
alian-0.201
 rob-0.189
 harms-0.189
cade-0.186
pha-0.179
Tokenings
Token ID654
Feature activation+2.19e-01

Pos logit contributions
alian+0.520
 rob+0.475
 harms+0.474
cade+0.463
pha+0.430
Neg logit contributions
-1.198
joy-1.156
ˈ-1.155
 Twain-1.149
TPPStreamerBot-1.142
Token.
Token ID13
Feature activation-6.99e-01

Pos logit contributions
alian+0.123
 rob+0.115
 harms+0.114
cade+0.113
pha+0.107
Neg logit contributions
-0.182
ˈ-0.174
joy-0.174
 Twain-0.173
TPPStreamerBot-0.172
TokenThis
Token ID1212
Feature activation-4.02e-01

Pos logit contributions
+0.525
joy+0.500
ˈ+0.500
 Twain+0.497
TPPStreamerBot+0.493
Neg logit contributions
alian-0.447
 rob-0.421
 harms-0.421
cade-0.415
pha-0.396
Token is
Token ID318
Feature activation-5.93e-01

Pos logit contributions
+0.308
ˈ+0.294
joy+0.293
 Twain+0.292
TPPStreamerBot+0.290
Neg logit contributions
alian-0.252
 rob-0.237
 harms-0.236
cade-0.233
pha-0.222
Token a
Token ID257
Feature activation-8.58e-01

Pos logit contributions
+0.440
ˈ+0.418
joy+0.418
 Twain+0.415
TPPStreamerBot+0.412
Neg logit contributions
alian-0.386
 rob-0.365
 harms-0.364
cade-0.359
pha-0.343
Token must
Token ID1276
Feature activation-4.15e+00

Pos logit contributions
+0.604
ˈ+0.574
joy+0.574
 Twain+0.570
TPPStreamerBot+0.566
Neg logit contributions
alian-0.589
 rob-0.558
 harms-0.557
cade-0.550
pha-0.527
Token visit
Token ID3187
Feature activation+2.11e-01

Pos logit contributions
+3.146
joy+3.050
ˈ+3.021
 Twain+2.996
 scrambled+2.974
Neg logit contributions
alian-2.487
 harms-2.403
cade-2.365
 rob-2.354
ctl-2.265
Token temple
Token ID12505
Feature activation+1.31e-01

Pos logit contributions
alian+0.125
 rob+0.117
 harms+0.117
cade+0.115
pha+0.110
Neg logit contributions
-0.169
ˈ-0.161
joy-0.160
 Twain-0.160
TPPStreamerBot-0.159
Token for
Token ID329
Feature activation-6.55e-01

Pos logit contributions
alian+0.075
 rob+0.070
 harms+0.070
cade+0.068
pha+0.065
Neg logit contributions
-0.108
ˈ-0.103
joy-0.103
 Twain-0.102
TPPStreamerBot-0.102
Token anyone
Token ID2687
Feature activation+3.00e-01

Pos logit contributions
+0.484
ˈ+0.459
joy+0.459
 Twain+0.456
TPPStreamerBot+0.453
Neg logit contributions
alian-0.428
 rob-0.405
 harms-0.404
cade-0.398
pha-0.381
Token interested
Token ID4609
Feature activation+1.33e+00

Pos logit contributions
alian+0.188
 rob+0.176
 harms+0.176
cade+0.173
pha+0.165
Neg logit contributions
-0.230
ˈ-0.219
joy-0.219
 Twain-0.218
TPPStreamerBot-0.217
Token for
Token ID329
Feature activation+2.56e-01

Pos logit contributions
+1.686
joy+1.638
 Twain+1.633
ˈ+1.628
 scrambled+1.609
Neg logit contributions
alian-1.320
 rob-1.222
cade-1.216
 harms-1.211
pha-1.166
Token CPUs
Token ID32340
Feature activation-8.53e-01

Pos logit contributions
alian+0.168
 rob+0.160
 harms+0.159
cade+0.157
pha+0.150
Neg logit contributions
-0.188
ˈ-0.179
joy-0.179
 Twain-0.178
TPPStreamerBot-0.177
Token and
Token ID290
Feature activation-2.73e-01

Pos logit contributions
+0.670
joy+0.644
ˈ+0.642
 Twain+0.639
TPPStreamerBot+0.633
Neg logit contributions
alian-0.511
 rob-0.479
 harms-0.477
cade-0.473
pha-0.451
Token memory
Token ID4088
Feature activation-9.19e-01

Pos logit contributions
+0.214
joy+0.204
ˈ+0.204
 Twain+0.203
TPPStreamerBot+0.201
Neg logit contributions
alian-0.166
 rob-0.156
 harms-0.156
cade-0.154
pha-0.146
Token (
Token ID357
Feature activation-1.09e+00

Pos logit contributions
+0.745
joy+0.718
ˈ+0.713
 Twain+0.711
TPPStreamerBot+0.706
Neg logit contributions
alian-0.529
 rob-0.493
 harms-0.491
cade-0.486
pha-0.462
TokenIntel
Token ID24123
Feature activation-4.15e+00

Pos logit contributions
+0.844
joy+0.811
ˈ+0.808
 Twain+0.801
TPPStreamerBot+0.797
Neg logit contributions
alian-0.669
 harms-0.630
 rob-0.630
cade-0.618
pha-0.590
Token VT
Token ID32751
Feature activation-4.32e+00

Pos logit contributions
+3.002
joy+2.927
ˈ+2.907
 Twain+2.871
 scrambled+2.827
Neg logit contributions
alian-2.699
 harms-2.539
 rob-2.512
cade-2.484
pha-2.383
Token-
Token ID12
Feature activation-3.00e-01

Pos logit contributions
+3.034
joy+2.907
 Twain+2.865
ˈ+2.859
TPPStreamerBot+2.838
Neg logit contributions
alian-2.959
 rob-2.811
 harms-2.785
cade-2.729
pha-2.650
Tokenx
Token ID87
Feature activation+1.18e-01

Pos logit contributions
+0.289
joy+0.279
ˈ+0.277
TPPStreamerBot+0.276
 Twain+0.276
Neg logit contributions
alian-0.128
 rob-0.119
 harms-0.118
cade-0.113
pha-0.107
Token,
Token ID11
Feature activation-4.88e-01

Pos logit contributions
alian+0.070
 rob+0.066
 harms+0.065
cade+0.064
pha+0.061
Neg logit contributions
-0.095
ˈ-0.091
joy-0.090
 Twain-0.090
TPPStreamerBot-0.090
Token AMD
Token ID10324
Feature activation-2.36e+00

Pos logit contributions
+0.365
joy+0.349
ˈ+0.348
 Twain+0.346
TPPStreamerBot+0.343
Neg logit contributions
alian-0.313
 rob-0.294
 harms-0.294
cade-0.290
pha-0.278
Token greenhouse
Token ID16325
Feature activation-1.13e+00

Pos logit contributions
+0.831
joy+0.800
ˈ+0.800
 Twain+0.797
TPPStreamerBot+0.787
Neg logit contributions
alian-0.653
cade-0.604
 rob-0.602
 harms-0.594
pha-0.575
Token gases
Token ID21678
Feature activation-1.63e+00

Pos logit contributions
+0.741
joy+0.709
ˈ+0.706
 Twain+0.698
TPPStreamerBot+0.689
Neg logit contributions
alian-0.819
cade-0.773
 rob-0.769
 harms-0.768
pha-0.737
Token such
Token ID884
Feature activation-8.56e-01

Pos logit contributions
+1.101
ˈ+1.062
joy+1.057
 Twain+1.056
 scrambled+1.039
Neg logit contributions
alian-1.135
cade-1.068
 rob-1.061
 harms-1.051
pha-1.024
Token as
Token ID355
Feature activation+4.29e-02

Pos logit contributions
+0.783
ˈ+0.757
joy+0.756
 Twain+0.754
TPPStreamerBot+0.748
Neg logit contributions
alian-0.403
 rob-0.368
 harms-0.368
cade-0.364
pha-0.341
Token nit
Token ID13759
Feature activation+2.90e-01

Pos logit contributions
alian+0.029
 rob+0.027
 harms+0.027
cade+0.027
pha+0.026
Neg logit contributions
-0.031
joy-0.029
ˈ-0.029
 Twain-0.029
TPPStreamerBot-0.029
Tokenrous
Token ID7596
Feature activation-4.11e+00

Pos logit contributions
alian+0.172
 rob+0.162
 harms+0.161
cade+0.159
pha+0.153
Neg logit contributions
-0.233
ˈ-0.221
 Twain-0.221
joy-0.220
TPPStreamerBot-0.220
Token ox
Token ID12018
Feature activation-7.34e-01

Pos logit contributions
+2.630
ˈ+2.571
joy+2.528
 Twain+2.497
 scrambled+2.496
Neg logit contributions
alian-3.027
cade-2.797
 rob-2.727
 harms-2.713
ctl-2.659
Tokenides
Token ID1460
Feature activation-2.42e+00

Pos logit contributions
+0.589
joy+0.574
ˈ+0.571
 Twain+0.564
TPPStreamerBot+0.554
Neg logit contributions
alian-0.419
 rob-0.398
 harms-0.395
cade-0.391
pha-0.367
Token.
Token ID13
Feature activation+1.17e-02

Pos logit contributions
+1.828
joy+1.772
ˈ+1.770
 Twain+1.758
 scrambled+1.734
Neg logit contributions
alian-1.507
cade-1.398
 rob-1.396
 harms-1.388
pha-1.326
Token The
Token ID383
Feature activation-3.19e-01

Pos logit contributions
alian+0.008
 rob+0.007
 harms+0.007
cade+0.007
pha+0.007
Neg logit contributions
-0.008
joy-0.008
ˈ-0.008
 Twain-0.008
TPPStreamerBot-0.008
Token new
Token ID649
Feature activation-6.10e-01

Pos logit contributions
+0.251
ˈ+0.239
joy+0.239
 Twain+0.237
TPPStreamerBot+0.236
Neg logit contributions
alian-0.193
 harms-0.183
 rob-0.183
cade-0.179
pha-0.170
Tokenalling
Token ID9221
Feature activation-1.25e+00

Pos logit contributions
+0.003
joy+0.003
ˈ+0.003
 Twain+0.003
TPPStreamerBot+0.002
Neg logit contributions
alian-0.003
 rob-0.002
 harms-0.002
cade-0.002
pha-0.002
Token together
Token ID1978
Feature activation-4.44e-01

Pos logit contributions
+0.972
joy+0.940
 Twain+0.932
ˈ+0.930
TPPStreamerBot+0.926
Neg logit contributions
alian-0.760
 rob-0.711
cade-0.707
 harms-0.704
pha-0.669
Token in
Token ID287
Feature activation+1.40e-01

Pos logit contributions
+0.357
joy+0.343
ˈ+0.343
 Twain+0.341
TPPStreamerBot+0.338
Neg logit contributions
alian-0.258
 rob-0.241
 harms-0.240
cade-0.238
pha-0.227
Token a
Token ID257
Feature activation+5.78e-02

Pos logit contributions
alian+0.090
 rob+0.085
 harms+0.085
cade+0.084
pha+0.080
Neg logit contributions
-0.104
ˈ-0.099
joy-0.099
 Twain-0.098
TPPStreamerBot-0.098
Token cr
Token ID1067
Feature activation+6.80e-01

Pos logit contributions
alian+0.039
 rob+0.037
 harms+0.037
cade+0.036
pha+0.035
Neg logit contributions
-0.042
joy-0.040
ˈ-0.040
 Twain-0.039
TPPStreamerBot-0.039
Tokenum
Token ID388
Feature activation-4.05e+00

Pos logit contributions
alian+0.401
 rob+0.377
 harms+0.376
cade+0.370
pha+0.353
Neg logit contributions
-0.543
joy-0.520
ˈ-0.520
 Twain-0.516
TPPStreamerBot-0.514
Tokenpled
Token ID10137
Feature activation-8.10e-01

Pos logit contributions
+2.226
ˈ+2.177
joy+2.166
 Twain+2.062
TPPStreamerBot+2.061
Neg logit contributions
alian-3.272
 harms-3.144
 rob-3.104
cade-3.094
ao-2.989
Token mess
Token ID2085
Feature activation-3.61e-01

Pos logit contributions
+0.579
joy+0.554
ˈ+0.553
 Twain+0.550
TPPStreamerBot+0.545
Neg logit contributions
alian-0.545
 harms-0.512
 rob-0.512
cade-0.507
pha-0.487
Token of
Token ID286
Feature activation+2.43e-01

Pos logit contributions
+0.294
joy+0.283
ˈ+0.282
 Twain+0.281
TPPStreamerBot+0.278
Neg logit contributions
alian-0.206
 rob-0.193
 harms-0.192
cade-0.190
pha-0.181
Token mutual
Token ID13584
Feature activation-1.16e+00

Pos logit contributions
alian+0.157
 rob+0.148
 harms+0.148
cade+0.146
pha+0.139
Neg logit contributions
-0.181
joy-0.173
ˈ-0.172
 Twain-0.171
TPPStreamerBot-0.170
Token uncertainty
Token ID13479
Feature activation-2.32e-01

Pos logit contributions
+0.814
joy+0.786
 Twain+0.780
ˈ+0.773
 scrambled+0.766
Neg logit contributions
alian-0.787
cade-0.742
 rob-0.733
 harms-0.724
pha-0.702
Token two
Token ID734
Feature activation-4.45e-01

Pos logit contributions
+0.285
joy+0.270
ˈ+0.270
 Twain+0.268
TPPStreamerBot+0.267
Neg logit contributions
alian-0.258
 rob-0.246
 harms-0.245
cade-0.241
pha-0.230
Token counts
Token ID9853
Feature activation+9.62e-01

Pos logit contributions
+0.337
ˈ+0.320
joy+0.320
 Twain+0.318
TPPStreamerBot+0.317
Neg logit contributions
alian-0.282
 rob-0.268
 harms-0.267
cade-0.263
pha-0.251
Token of
Token ID286
Feature activation+1.05e-01

Pos logit contributions
alian+0.525
 harms+0.488
 rob+0.487
cade+0.481
pha+0.454
Neg logit contributions
-0.812
joy-0.778
ˈ-0.778
 Twain-0.775
TPPStreamerBot-0.769
Token violation
Token ID8747
Feature activation-2.96e-01

Pos logit contributions
alian+0.065
 rob+0.062
 harms+0.062
cade+0.060
pha+0.057
Neg logit contributions
-0.081
joy-0.077
ˈ-0.077
 Twain-0.076
TPPStreamerBot-0.076
Token of
Token ID286
Feature activation+8.00e-03

Pos logit contributions
+0.249
ˈ+0.239
joy+0.239
 Twain+0.238
TPPStreamerBot+0.236
Neg logit contributions
alian-0.162
 harms-0.150
 rob-0.150
cade-0.148
pha-0.141
Token ignition
Token ID37594
Feature activation-4.04e+00

Pos logit contributions
alian+0.005
 rob+0.005
 harms+0.005
cade+0.005
ctl+0.005
Neg logit contributions
-0.006
ˈ-0.005
joy-0.005
TPPStreamerBot-0.005
 Twain-0.005
Token inter
Token ID987
Feature activation-2.02e-01

Pos logit contributions
+3.329
joy+3.195
ˈ+3.191
 Twain+3.175
 scrambled+3.131
Neg logit contributions
alian-2.269
 harms-2.066
 rob-2.065
cade-2.052
pha-1.979
Tokenlock
Token ID5354
Feature activation-1.94e+00

Pos logit contributions
+0.194
ˈ+0.186
 Twain+0.186
joy+0.186
TPPStreamerBot+0.185
Neg logit contributions
alian-0.087
 rob-0.080
 harms-0.080
cade-0.078
pha-0.073
Token driver
Token ID4639
Feature activation-2.45e+00

Pos logit contributions
+1.541
joy+1.477
ˈ+1.475
 Twain+1.469
TPPStreamerBot+1.454
Neg logit contributions
alian-1.151
 rob-1.075
 harms-1.073
cade-1.063
pha-1.012
Token's
Token ID338
Feature activation-9.10e-01

Pos logit contributions
+2.180
joy+2.103
ˈ+2.093
 Twain+2.091
TPPStreamerBot+2.069
Neg logit contributions
alian-1.207
 rob-1.112
 harms-1.106
cade-1.097
pha-1.039
Token license
Token ID5964
Feature activation-8.71e-01

Pos logit contributions
+0.668
ˈ+0.636
joy+0.635
 Twain+0.631
TPPStreamerBot+0.630
Neg logit contributions
alian-0.598
 harms-0.576
 rob-0.575
cade-0.559
ao-0.537
Token
Token ID247
Feature activation-4.16e-01

Pos logit contributions
+0.228
joy+0.209
ˈ+0.208
 Twain+0.207
TPPStreamerBot+0.205
Neg logit contributions
alian-0.378
 rob-0.361
 harms-0.359
cade-0.357
pha-0.347
Tokens
Token ID82
Feature activation-4.27e-02

Pos logit contributions
+0.324
ˈ+0.312
joy+0.312
 Twain+0.309
TPPStreamerBot+0.306
Neg logit contributions
alian-0.252
 rob-0.237
 harms-0.237
cade-0.233
pha-0.223
Token hands
Token ID2832
Feature activation+4.49e-01

Pos logit contributions
+0.033
joy+0.032
ˈ+0.032
 Twain+0.031
TPPStreamerBot+0.031
Neg logit contributions
alian-0.026
 rob-0.025
 harms-0.025
cade-0.024
pha-0.023
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
alian+0.240
 rob+0.223
 harms+0.223
cade+0.219
pha+0.207
Neg logit contributions
-0.386
ˈ-0.369
joy-0.368
 Twain-0.367
TPPStreamerBot-0.365
Token The
Token ID383
Feature activation-1.81e-01

Pos logit contributions
+0.076
ˈ+0.073
joy+0.072
 Twain+0.072
TPPStreamerBot+0.072
Neg logit contributions
alian-0.069
 rob-0.066
 harms-0.065
cade-0.065
pha-0.062
Token score
Token ID4776
Feature activation-4.03e+00

Pos logit contributions
+0.124
ˈ+0.117
joy+0.117
 Twain+0.116
TPPStreamerBot+0.116
Neg logit contributions
alian-0.128
 rob-0.123
 harms-0.122
cade-0.120
pha-0.115
Token is
Token ID318
Feature activation-2.87e-02

Pos logit contributions
+3.080
joy+3.024
 Twain+2.973
ˈ+2.972
 scrambled+2.911
Neg logit contributions
alian-2.407
 rob-2.279
 harms-2.258
cade-2.230
pha-2.151
Token 44
Token ID5846
Feature activation-3.13e-01

Pos logit contributions
+0.019
ˈ+0.018
joy+0.018
TPPStreamerBot+0.018
 Twain+0.018
Neg logit contributions
alian-0.021
 rob-0.020
 harms-0.020
cade-0.020
ao-0.019
Token for
Token ID329
Feature activation+1.00e-02

Pos logit contributions
+0.250
ˈ+0.238
joy+0.238
 Twain+0.237
TPPStreamerBot+0.236
Neg logit contributions
alian-0.185
 rob-0.175
 harms-0.174
cade-0.171
pha-0.163
Token one
Token ID530
Feature activation+4.42e-01

Pos logit contributions
alian+0.007
 rob+0.007
 harms+0.007
cade+0.007
pha+0.006
Neg logit contributions
-0.007
ˈ-0.006
joy-0.006
 Twain-0.006
TPPStreamerBot-0.006
Token.
Token ID13
Feature activation+3.60e-01

Pos logit contributions
alian+0.251
 rob+0.237
 harms+0.236
cade+0.230
pha+0.219
Neg logit contributions
-0.364
ˈ-0.348
joy-0.347
 Twain-0.345
TPPStreamerBot-0.345
Token
Token ID247
Feature activation+1.89e-01

Pos logit contributions
alian+0.015
 rob+0.014
 harms+0.014
cade+0.014
pha+0.013
Neg logit contributions
-0.009
joy-0.008
 Twain-0.008
ˈ-0.008
TPPStreamerBot-0.008
Tokenre
Token ID260
Feature activation+2.73e-01

Pos logit contributions
alian+0.134
 rob+0.127
 harms+0.127
cade+0.126
pha+0.121
Neg logit contributions
-0.129
joy-0.121
ˈ-0.121
 Twain-0.121
TPPStreamerBot-0.120
Token both
Token ID1111
Feature activation+7.98e-01

Pos logit contributions
alian+0.177
 rob+0.168
 harms+0.167
cade+0.165
pha+0.157
Neg logit contributions
-0.203
ˈ-0.193
joy-0.193
 Twain-0.192
TPPStreamerBot-0.190
Token pure
Token ID5899
Feature activation-4.88e-01

Pos logit contributions
alian+0.531
 rob+0.508
 harms+0.506
cade+0.494
ao+0.473
Neg logit contributions
-0.580
joy-0.548
ˈ-0.547
 Twain-0.543
TPPStreamerBot-0.541
Token goal
Token ID3061
Feature activation-3.54e-01

Pos logit contributions
+0.346
joy+0.331
ˈ+0.330
 Twain+0.328
TPPStreamerBot+0.325
Neg logit contributions
alian-0.333
 rob-0.312
 harms-0.312
cade-0.311
pha-0.296
Token score
Token ID4776
Feature activation-4.01e+00

Pos logit contributions
+0.301
joy+0.291
ˈ+0.290
 Twain+0.288
TPPStreamerBot+0.286
Neg logit contributions
alian-0.191
 rob-0.177
 harms-0.176
cade-0.175
pha-0.165
Tokenrs
Token ID3808
Feature activation-1.43e+00

Pos logit contributions
+2.358
joy+2.268
ˈ+2.222
 Twain+2.208
TPPStreamerBot+2.168
Neg logit contributions
alian-3.129
 rob-3.003
cade-2.991
 harms-2.985
pha-2.884
Token.
Token ID13
Feature activation-6.16e-02

Pos logit contributions
+1.191
joy+1.142
ˈ+1.142
 Twain+1.133
TPPStreamerBot+1.127
Neg logit contributions
alian-0.797
 rob-0.744
 harms-0.743
cade-0.734
pha-0.697
Token If
Token ID1002
Feature activation-7.48e-02

Pos logit contributions
+0.045
ˈ+0.043
joy+0.043
 Twain+0.042
TPPStreamerBot+0.042
Neg logit contributions
alian-0.041
 rob-0.039
 harms-0.038
cade-0.038
pha-0.036
Token you
Token ID345
Feature activation+6.76e-01

Pos logit contributions
+0.049
joy+0.047
ˈ+0.047
 Twain+0.046
TPPStreamerBot+0.046
Neg logit contributions
alian-0.055
 rob-0.052
 harms-0.052
cade-0.051
pha-0.049
Token want
Token ID765
Feature activation+2.51e+00

Pos logit contributions
alian+0.457
 rob+0.433
 harms+0.432
cade+0.426
pha+0.408
Neg logit contributions
-0.483
joy-0.459
ˈ-0.459
 Twain-0.456
TPPStreamerBot-0.453
Token finding
Token ID4917
Feature activation-1.66e-01

Pos logit contributions
+0.705
joy+0.674
ˈ+0.673
 Twain+0.670
TPPStreamerBot+0.665
Neg logit contributions
alian-0.538
 rob-0.505
 harms-0.505
cade-0.497
pha-0.474
Token the
Token ID262
Feature activation-4.70e-01

Pos logit contributions
+0.121
ˈ+0.115
joy+0.115
 Twain+0.114
TPPStreamerBot+0.114
Neg logit contributions
alian-0.109
 rob-0.104
 harms-0.103
cade-0.101
pha-0.097
Token back
Token ID736
Feature activation-1.02e+00

Pos logit contributions
+0.349
joy+0.329
ˈ+0.329
 Twain+0.327
TPPStreamerBot+0.327
Neg logit contributions
alian-0.306
 rob-0.292
 harms-0.291
cade-0.284
pha-0.272
Token of
Token ID286
Feature activation-8.73e-01

Pos logit contributions
+0.842
joy+0.816
ˈ+0.812
 Twain+0.803
TPPStreamerBot+0.796
Neg logit contributions
alian-0.564
 rob-0.525
 harms-0.525
cade-0.517
pha-0.496
Token the
Token ID262
Feature activation-9.08e-01

Pos logit contributions
+0.639
joy+0.609
ˈ+0.608
 Twain+0.605
TPPStreamerBot+0.599
Neg logit contributions
alian-0.575
 rob-0.541
 harms-0.540
cade-0.535
pha-0.512
Token net
Token ID2010
Feature activation-4.01e+00

Pos logit contributions
+0.752
joy+0.719
ˈ+0.719
 Twain+0.715
TPPStreamerBot+0.711
Neg logit contributions
alian-0.512
 rob-0.480
 harms-0.479
cade-0.470
pha-0.445
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
+3.089
joy+3.033
 Twain+2.996
ˈ+2.992
 scrambled+2.976
Neg logit contributions
alian-2.362
 harms-2.199
 rob-2.185
cade-2.185
pha-2.121
Token In
Token ID554
Feature activation+1.56e-01

Pos logit contributions
alian+0.082
 harms+0.077
 rob+0.077
cade+0.076
pha+0.073
Neg logit contributions
-0.095
joy-0.091
ˈ-0.091
 Twain-0.091
TPPStreamerBot-0.090
Token addition
Token ID3090
Feature activation-1.30e+00

Pos logit contributions
alian+0.101
 rob+0.095
 harms+0.095
cade+0.094
pha+0.089
Neg logit contributions
-0.117
ˈ-0.111
joy-0.111
 Twain-0.111
TPPStreamerBot-0.110
Token to
Token ID284
Feature activation+6.39e-01

Pos logit contributions
+1.004
joy+0.973
 Twain+0.959
ˈ+0.953
TPPStreamerBot+0.941
Neg logit contributions
alian-0.794
 harms-0.744
cade-0.736
 rob-0.732
pha-0.699
Token the
Token ID262
Feature activation+8.71e-02

Pos logit contributions
alian+0.408
 rob+0.388
 harms+0.385
cade+0.379
ao+0.362
Neg logit contributions
-0.481
ˈ-0.458
joy-0.456
 Twain-0.453
TPPStreamerBot-0.452
Tokenant
Token ID415
Feature activation-1.10e+00

Pos logit contributions
alian+0.273
 rob+0.253
 harms+0.252
cade+0.250
ao+0.238
Neg logit contributions
-0.432
ˈ-0.412
joy-0.410
 Twain-0.409
TPPStreamerBot-0.408
Tokenins
Token ID1040
Feature activation-1.92e-01

Pos logit contributions
+0.804
joy+0.778
ˈ+0.772
 Twain+0.771
TPPStreamerBot+0.755
Neg logit contributions
alian-0.705
 harms-0.675
 rob-0.673
cade-0.663
ctl-0.634
Token,
Token ID11
Feature activation-1.78e-01

Pos logit contributions
+0.146
ˈ+0.140
joy+0.139
 Twain+0.139
TPPStreamerBot+0.138
Neg logit contributions
alian-0.121
 rob-0.114
 harms-0.113
cade-0.112
pha-0.107
Token Survivor
Token ID23740
Feature activation-2.16e+00

Pos logit contributions
+0.126
joy+0.119
ˈ+0.119
 Twain+0.119
TPPStreamerBot+0.118
Neg logit contributions
alian-0.122
 rob-0.116
 harms-0.115
cade-0.114
pha-0.109
Token Heroes
Token ID9896
Feature activation-1.24e+00

Pos logit contributions
+1.556
joy+1.499
ˈ+1.492
 Twain+1.488
TPPStreamerBot+1.466
Neg logit contributions
alian-1.427
 harms-1.344
 rob-1.336
cade-1.319
pha-1.266
Token vs
Token ID3691
Feature activation-4.01e+00

Pos logit contributions
+1.014
ˈ+0.970
joy+0.968
 Twain+0.963
TPPStreamerBot+0.958
Neg logit contributions
alian-0.706
 rob-0.663
 harms-0.661
cade-0.651
pha-0.618
Token.
Token ID13
Feature activation-5.50e-01

Pos logit contributions
+2.918
joy+2.835
 Twain+2.806
ˈ+2.775
 unbeat+2.722
Neg logit contributions
alian-2.642
 harms-2.438
cade-2.417
 rob-2.401
ao-2.288
Token Vill
Token ID9757
Feature activation-1.40e+00

Pos logit contributions
+0.365
ˈ+0.344
joy+0.344
TPPStreamerBot+0.343
 Twain+0.341
Neg logit contributions
alian-0.397
 rob-0.382
 harms-0.380
cade-0.375
kai-0.361
Tokenains
Token ID1299
Feature activation-8.12e-01

Pos logit contributions
+0.878
joy+0.832
ˈ+0.829
 Twain+0.823
TPPStreamerBot+0.814
Neg logit contributions
alian-1.071
 rob-1.023
 harms-1.020
cade-1.009
pha-0.970
Token,
Token ID11
Feature activation-5.27e-01

Pos logit contributions
+0.657
joy+0.629
ˈ+0.628
 Twain+0.625
TPPStreamerBot+0.620
Neg logit contributions
alian-0.472
 harms-0.441
 rob-0.441
cade-0.434
pha-0.413
Token Survivor
Token ID23740
Feature activation-2.29e+00

Pos logit contributions
+0.398
ˈ+0.379
joy+0.379
 Twain+0.376
TPPStreamerBot+0.374
Neg logit contributions
alian-0.335
 rob-0.316
 harms-0.316
cade-0.311
pha-0.297
Token virus
Token ID9471
Feature activation-1.34e+00

Pos logit contributions
+0.202
joy+0.191
ˈ+0.191
 Twain+0.190
TPPStreamerBot+0.188
Neg logit contributions
alian-0.217
 rob-0.206
 harms-0.206
cade-0.204
pha-0.196
Token quickly
Token ID2952
Feature activation-1.30e+00

Pos logit contributions
+1.084
ˈ+1.044
 Twain+1.039
joy+1.038
TPPStreamerBot+1.030
Neg logit contributions
alian-0.778
 rob-0.728
 harms-0.725
cade-0.715
pha-0.680
Token,
Token ID11
Feature activation-4.78e-01

Pos logit contributions
+1.031
ˈ+0.990
joy+0.986
 Twain+0.985
TPPStreamerBot+0.975
Neg logit contributions
alian-0.766
 rob-0.716
 harms-0.710
cade-0.707
pha-0.673
Token a
Token ID257
Feature activation+3.93e-01

Pos logit contributions
+0.350
joy+0.333
ˈ+0.332
 Twain+0.330
TPPStreamerBot+0.328
Neg logit contributions
alian-0.315
 rob-0.298
 harms-0.298
cade-0.293
pha-0.281
Token doctor
Token ID6253
Feature activation-4.82e-01

Pos logit contributions
alian+0.262
 rob+0.248
 harms+0.247
cade+0.244
pha+0.234
Neg logit contributions
-0.286
joy-0.271
ˈ-0.271
 Twain-0.269
TPPStreamerBot-0.268
Token must
Token ID1276
Feature activation-4.01e+00

Pos logit contributions
+0.408
ˈ+0.391
joy+0.391
 Twain+0.389
TPPStreamerBot+0.386
Neg logit contributions
alian-0.262
 rob-0.244
 harms-0.243
cade-0.240
pha-0.227
Token send
Token ID3758
Feature activation-2.49e-01

Pos logit contributions
+2.660
ˈ+2.612
 Twain+2.585
 scrambled+2.585
joy+2.584
Neg logit contributions
alian-2.736
 harms-2.584
cade-2.557
 rob-2.532
pha-2.471
Token blood
Token ID2910
Feature activation-2.44e-01

Pos logit contributions
+0.185
ˈ+0.175
joy+0.175
 Twain+0.174
TPPStreamerBot+0.173
Neg logit contributions
alian-0.162
 rob-0.154
 harms-0.153
cade-0.151
pha-0.144
Token taken
Token ID2077
Feature activation-1.11e+00

Pos logit contributions
+0.196
joy+0.188
ˈ+0.187
 Twain+0.187
TPPStreamerBot+0.185
Neg logit contributions
alian-0.142
 harms-0.133
 rob-0.133
cade-0.131
pha-0.125
Token during
Token ID1141
Feature activation-1.87e+00

Pos logit contributions
+0.808
joy+0.775
ˈ+0.774
 Twain+0.771
TPPStreamerBot+0.763
Neg logit contributions
alian-0.729
 rob-0.689
 harms-0.687
cade-0.680
pha-0.651
Token the
Token ID262
Feature activation+3.54e-01

Pos logit contributions
+1.331
ˈ+1.274
 Twain+1.271
joy+1.268
TPPStreamerBot+1.257
Neg logit contributions
alian-1.254
 rob-1.176
 harms-1.171
cade-1.164
pha-1.121
Token Del
Token ID4216
Feature activation+4.50e-01

Pos logit contributions
+0.866
joy+0.838
 Twain+0.827
ˈ+0.826
TPPStreamerBot+0.817
Neg logit contributions
alian-0.761
 harms-0.712
 rob-0.706
cade-0.699
kai-0.669
Token Sur
Token ID4198
Feature activation-2.19e-01

Pos logit contributions
alian+0.388
 rob+0.372
 harms+0.372
cade+0.369
ao+0.361
Neg logit contributions
-0.241
ˈ-0.221
TPPStreamerBot-0.221
joy-0.219
 Twain-0.218
Token featuring
Token ID9593
Feature activation+6.70e-01

Pos logit contributions
+0.182
joy+0.174
ˈ+0.174
 Twain+0.173
TPPStreamerBot+0.172
Neg logit contributions
alian-0.123
 harms-0.115
 rob-0.114
cade-0.113
pha-0.107
Token Coach
Token ID16393
Feature activation+3.28e-01

Pos logit contributions
alian+0.442
 rob+0.421
 harms+0.417
cade+0.411
pha+0.393
Neg logit contributions
-0.491
ˈ-0.467
joy-0.464
 Twain-0.462
TPPStreamerBot-0.462
Token (
Token ID357
Feature activation-5.90e-01

Pos logit contributions
alian+0.231
 rob+0.219
 harms+0.218
cade+0.216
pha+0.207
Neg logit contributions
-0.226
ˈ-0.214
joy-0.214
 Twain-0.212
TPPStreamerBot-0.211
TokenSurv
Token ID34652
Feature activation-3.99e+00

Pos logit contributions
+0.437
joy+0.418
ˈ+0.417
 Twain+0.414
TPPStreamerBot+0.411
Neg logit contributions
alian-0.382
 harms-0.361
 rob-0.361
cade-0.355
pha-0.340
Tokeniv
Token ID452
Feature activation-6.75e-01

Pos logit contributions
+1.808
joy+1.744
ˈ+1.712
 Twain+1.656
TPPStreamerBot+1.638
Neg logit contributions
alian-3.694
 harms-3.558
 rob-3.532
cade-3.475
ctl-3.384
Tokenor
Token ID273
Feature activation+4.58e-01

Pos logit contributions
+0.412
ˈ+0.387
joy+0.386
 Twain+0.386
TPPStreamerBot+0.383
Neg logit contributions
alian-0.528
 rob-0.502
 harms-0.500
cade-0.498
ao-0.481
Token T
Token ID309
Feature activation-8.31e-02

Pos logit contributions
alian+0.300
 rob+0.284
 harms+0.283
cade+0.279
pha+0.267
Neg logit contributions
-0.337
joy-0.320
ˈ-0.320
 Twain-0.318
TPPStreamerBot-0.316
Tokenoc
Token ID420
Feature activation+5.03e-01

Pos logit contributions
+0.061
joy+0.058
ˈ+0.058
 Twain+0.058
TPPStreamerBot+0.058
Neg logit contributions
alian-0.054
 rob-0.051
 harms-0.051
cade-0.050
pha-0.048
Tokenant
Token ID415
Feature activation-1.10e+00

Pos logit contributions
alian+0.273
 rob+0.253
 harms+0.252
cade+0.250
ao+0.238
Neg logit contributions
-0.432
ˈ-0.412
joy-0.410
 Twain-0.409
TPPStreamerBot-0.408
Token at
Token ID379
Feature activation+1.50e-01

Pos logit contributions
+0.038
joy+0.036
ˈ+0.036
 Twain+0.036
TPPStreamerBot+0.035
Neg logit contributions
alian-0.031
 rob-0.029
 harms-0.029
cade-0.029
pha-0.028
Token the
Token ID262
Feature activation+2.63e-01

Pos logit contributions
alian+0.100
 rob+0.094
 harms+0.094
cade+0.093
pha+0.089
Neg logit contributions
-0.109
ˈ-0.104
joy-0.104
 Twain-0.104
TPPStreamerBot-0.103
Token sm
Token ID895
Feature activation-6.61e-01

Pos logit contributions
alian+0.152
 rob+0.142
 harms+0.141
cade+0.140
pha+0.133
Neg logit contributions
-0.214
ˈ-0.205
joy-0.205
 Twain-0.204
TPPStreamerBot-0.202
Tokenok
Token ID482
Feature activation+4.42e-01

Pos logit contributions
+0.484
joy+0.467
ˈ+0.465
 Twain+0.460
TPPStreamerBot+0.456
Neg logit contributions
alian-0.428
 rob-0.407
 harms-0.405
cade-0.398
ctl-0.381
Tokenest
Token ID395
Feature activation+7.08e-01

Pos logit contributions
alian+0.168
 rob+0.151
 harms+0.151
cade+0.147
pha+0.135
Neg logit contributions
-0.448
ˈ-0.433
joy-0.431
 Twain-0.430
TPPStreamerBot-0.428
Tokenack
Token ID441
Feature activation-3.99e+00

Pos logit contributions
alian+0.417
 harms+0.390
 rob+0.390
cade+0.383
pha+0.366
Neg logit contributions
-0.573
ˈ-0.544
joy-0.543
 Twain-0.541
TPPStreamerBot-0.540
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
+2.846
joy+2.772
 Twain+2.767
ˈ+2.723
TPPStreamerBot+2.686
Neg logit contributions
alian-2.611
cade-2.412
 rob-2.410
 harms-2.379
pha-2.315
Token natural
Token ID3288
Feature activation+4.56e-01

Pos logit contributions
+0.129
joy+0.122
ˈ+0.122
 Twain+0.122
TPPStreamerBot+0.121
Neg logit contributions
alian-0.115
 rob-0.109
 harms-0.109
cade-0.107
pha-0.103
Token gas
Token ID3623
Feature activation+5.95e-01

Pos logit contributions
alian+0.283
 rob+0.266
 harms+0.265
cade+0.262
pha+0.250
Neg logit contributions
-0.351
joy-0.335
ˈ-0.335
 Twain-0.333
TPPStreamerBot-0.331
Token is
Token ID318
Feature activation-3.71e-01

Pos logit contributions
alian+0.340
 rob+0.318
 harms+0.316
cade+0.313
pha+0.297
Neg logit contributions
-0.486
ˈ-0.466
joy-0.466
 Twain-0.463
TPPStreamerBot-0.460
Token a
Token ID257
Feature activation-4.35e-01

Pos logit contributions
+0.273
ˈ+0.261
joy+0.261
 Twain+0.259
TPPStreamerBot+0.257
Neg logit contributions
alian-0.243
 rob-0.228
 harms-0.228
cade-0.226
pha-0.216
Token stand
Token ID1302
Feature activation+3.14e-01

Pos logit contributions
alian+0.159
 rob+0.151
 harms+0.151
cade+0.149
pha+0.143
Neg logit contributions
-0.163
ˈ-0.155
joy-0.155
 Twain-0.154
TPPStreamerBot-0.153
Token-
Token ID12
Feature activation-2.67e-01

Pos logit contributions
alian+0.206
 rob+0.196
 harms+0.195
cade+0.192
pha+0.184
Neg logit contributions
-0.231
ˈ-0.220
joy-0.218
 Twain-0.218
TPPStreamerBot-0.218
Tokenoff
Token ID2364
Feature activation-4.19e-01

Pos logit contributions
+0.205
joy+0.199
ˈ+0.198
 Twain+0.195
TPPStreamerBot+0.195
Neg logit contributions
alian-0.165
 rob-0.155
 harms-0.154
cade-0.151
pha-0.144
Token and
Token ID290
Feature activation+1.79e-01

Pos logit contributions
+0.324
joy+0.310
ˈ+0.309
 Twain+0.307
TPPStreamerBot+0.305
Neg logit contributions
alian-0.259
 rob-0.243
 harms-0.243
cade-0.239
pha-0.228
Token scr
Token ID6040
Feature activation-1.33e+00

Pos logit contributions
alian+0.118
 rob+0.111
 harms+0.111
cade+0.110
pha+0.105
Neg logit contributions
-0.131
ˈ-0.125
joy-0.124
 Twain-0.124
TPPStreamerBot-0.123
Tokenum
Token ID388
Feature activation-3.99e+00

Pos logit contributions
+0.914
joy+0.879
ˈ+0.874
 Twain+0.866
TPPStreamerBot+0.860
Neg logit contributions
alian-0.930
 rob-0.883
 harms-0.881
cade-0.865
pha-0.833
Token-
Token ID12
Feature activation-2.53e-01

Pos logit contributions
+2.639
joy+2.532
ˈ+2.507
 Twain+2.486
 scrambled+2.459
Neg logit contributions
alian-2.858
cade-2.669
 harms-2.660
 rob-2.660
pha-2.542
Tokenhalf
Token ID13959
Feature activation-1.86e+00

Pos logit contributions
+0.129
 Twain+0.117
ˈ+0.117
TPPStreamerBot+0.116
joy+0.116
Neg logit contributions
alian-0.225
 rob-0.218
 harms-0.217
cade-0.214
ao-0.209
Token respectively
Token ID8148
Feature activation+2.40e-01

Pos logit contributions
+1.373
joy+1.335
 Twain+1.317
ˈ+1.313
TPPStreamerBot+1.304
Neg logit contributions
alian-1.196
 harms-1.116
cade-1.111
 rob-1.110
pha-1.054
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
alian+0.128
 rob+0.118
 harms+0.118
cade+0.117
pha+0.110
Neg logit contributions
-0.205
joy-0.197
ˈ-0.197
 Twain-0.196
TPPStreamerBot-0.195
Token
Token ID198
Feature activation+8.15e-02

Pos logit contributions
+0.077
joy+0.074
ˈ+0.074
 Twain+0.073
TPPStreamerBot+0.072
Neg logit contributions
alian-0.075
 harms-0.071
 rob-0.071
cade-0.070
pha-0.067
TokenRemember
Token ID16676
Feature activation-5.06e-01

Pos logit contributions
+0.000
 Twain+0.000
ˈ+0.000
joy+0.000
TPPStreamerBot+0.000
Neg logit contributions
alian-0.000
 rob-0.000
 harms-0.000
cade-0.000
kai-0.000
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
+0.402
joy+0.385
ˈ+0.384
 Twain+0.384
TPPStreamerBot+0.380
Neg logit contributions
alian-0.301
 harms-0.281
 rob-0.281
cade-0.279
pha-0.264
Token though
Token ID996
Feature activation-3.60e-01

Pos logit contributions
+0.784
joy+0.748
ˈ+0.748
 Twain+0.746
TPPStreamerBot+0.738
Neg logit contributions
alian-0.651
 rob-0.610
 harms-0.610
cade-0.604
pha-0.576
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
+0.300
joy+0.287
ˈ+0.287
 Twain+0.286
TPPStreamerBot+0.283
Neg logit contributions
alian-0.201
 rob-0.187
 harms-0.187
cade-0.184
pha-0.175
Token that
Token ID326
Feature activation-4.07e-01

Pos logit contributions
alian+0.205
 rob+0.194
 harms+0.194
cade+0.190
pha+0.182
Neg logit contributions
-0.244
joy-0.232
ˈ-0.232
 Twain-0.229
TPPStreamerBot-0.229
Token thanks
Token ID5176
Feature activation-3.99e+00

Pos logit contributions
+0.295
joy+0.280
ˈ+0.280
 Twain+0.278
TPPStreamerBot+0.276
Neg logit contributions
alian-0.272
 rob-0.257
 harms-0.256
cade-0.253
pha-0.242
Token to
Token ID284
Feature activation-2.17e-01

Pos logit contributions
+2.879
joy+2.745
ˈ+2.732
 Twain+2.705
TPPStreamerBot+2.657
Neg logit contributions
alian-2.583
 harms-2.455
 rob-2.421
cade-2.409
ctl-2.306
Token Amazon
Token ID6186
Feature activation+3.16e-01

Pos logit contributions
+0.155
joy+0.148
ˈ+0.148
 Twain+0.147
TPPStreamerBot+0.146
Neg logit contributions
alian-0.146
 rob-0.138
 harms-0.138
cade-0.136
pha-0.130
Token
Token ID447
Feature activation+3.79e-01

Pos logit contributions
alian+0.175
 rob+0.163
 harms+0.163
cade+0.160
pha+0.152
Neg logit contributions
-0.265
ˈ-0.254
joy-0.254
 Twain-0.252
TPPStreamerBot-0.251
Token
Token ID247
Feature activation+3.52e-01

Pos logit contributions
alian+0.331
 rob+0.315
 harms+0.314
cade+0.312
pha+0.303
Neg logit contributions
-0.199
joy-0.184
 Twain-0.182
ˈ-0.182
TPPStreamerBot-0.179
Tokens
Token ID82
Feature activation-3.03e-01

Pos logit contributions
alian+0.218
 rob+0.205
 harms+0.204
cade+0.202
pha+0.192
Neg logit contributions
-0.271
joy-0.260
ˈ-0.259
 Twain-0.257
TPPStreamerBot-0.256
Token room
Token ID2119
Feature activation+1.56e+00

Pos logit contributions
alian+0.085
 rob+0.081
 harms+0.081
cade+0.080
pha+0.077
Neg logit contributions
-0.076
ˈ-0.071
joy-0.071
 Twain-0.071
TPPStreamerBot-0.070
Token,
Token ID11
Feature activation-3.77e-01

Pos logit contributions
alian+0.928
 rob+0.875
 harms+0.871
cade+0.858
pha+0.812
Neg logit contributions
-1.248
ˈ-1.193
joy-1.189
 Twain-1.183
TPPStreamerBot-1.177
Token a
Token ID257
Feature activation+6.17e-01

Pos logit contributions
+0.277
joy+0.264
ˈ+0.264
 Twain+0.262
TPPStreamerBot+0.260
Neg logit contributions
alian-0.247
 rob-0.233
 harms-0.233
cade-0.230
pha-0.220
Token pair
Token ID5166
Feature activation-1.27e+00

Pos logit contributions
alian+0.433
 rob+0.411
 harms+0.410
cade+0.405
pha+0.389
Neg logit contributions
-0.425
ˈ-0.403
joy-0.402
 Twain-0.400
TPPStreamerBot-0.397
Token of
Token ID286
Feature activation+7.99e-01

Pos logit contributions
+1.043
joy+1.005
ˈ+1.001
 Twain+1.000
TPPStreamerBot+0.986
Neg logit contributions
alian-0.706
 rob-0.658
 harms-0.656
cade-0.647
pha-0.623
Token Silver
Token ID7698
Feature activation+2.49e+00

Pos logit contributions
alian+0.536
 rob+0.508
 harms+0.506
cade+0.499
pha+0.478
Neg logit contributions
-0.577
ˈ-0.547
joy-0.547
 Twain-0.543
TPPStreamerBot-0.540
Token Phant
Token ID38699
Feature activation+5.87e-01

Pos logit contributions
alian+1.299
 rob+1.216
 harms+1.215
cade+1.189
pha+1.128
Neg logit contributions
-2.162
ˈ-2.070
joy-2.061
 Twain-2.054
TPPStreamerBot-2.046
Tokenoms
Token ID3150
Feature activation-1.23e+00

Pos logit contributions
alian+0.350
 rob+0.328
 harms+0.328
cade+0.323
pha+0.308
Neg logit contributions
-0.468
ˈ-0.446
joy-0.445
 Twain-0.443
TPPStreamerBot-0.440
Token should
Token ID815
Feature activation-8.80e-01

Pos logit contributions
+0.972
joy+0.933
ˈ+0.933
 Twain+0.929
TPPStreamerBot+0.918
Neg logit contributions
alian-0.726
 rob-0.676
 harms-0.673
cade-0.670
pha-0.642
Token acqu
Token ID4078
Feature activation+8.00e-01

Pos logit contributions
+0.627
ˈ+0.603
joy+0.602
 Twain+0.596
TPPStreamerBot+0.587
Neg logit contributions
alian-0.588
 harms-0.556
 rob-0.549
cade-0.546
pha-0.529
Tokenit
Token ID270
Feature activation+7.31e-01

Pos logit contributions
alian+0.520
 rob+0.487
 harms+0.485
cade+0.483
ao+0.464
Neg logit contributions
-0.607
 Twain-0.569
ˈ-0.565
joy-0.563
TPPStreamerBot-0.561
Token
Token ID564
Feature activation+7.26e-01

Pos logit contributions
alian+0.193
 rob+0.183
 harms+0.182
cade+0.180
pha+0.172
Neg logit contributions
-0.225
ˈ-0.214
joy-0.214
 Twain-0.212
TPPStreamerBot-0.212
Token
Token ID250
Feature activation-1.91e-01

Pos logit contributions
alian+0.663
 rob+0.637
 harms+0.636
cade+0.629
pha+0.612
Neg logit contributions
-0.345
joy-0.319
ˈ-0.319
 Twain-0.316
TPPStreamerBot-0.313
TokenTW
Token ID34551
Feature activation-1.31e-01

Pos logit contributions
+0.141
ˈ+0.134
joy+0.133
 Twain+0.133
TPPStreamerBot+0.132
Neg logit contributions
alian-0.125
 rob-0.118
 harms-0.117
cade-0.116
pha-0.111
TokenO
Token ID46
Feature activation-1.22e+00

Pos logit contributions
+0.097
joy+0.092
ˈ+0.092
 Twain+0.092
TPPStreamerBot+0.091
Neg logit contributions
alian-0.085
 rob-0.080
 harms-0.080
cade-0.079
pha-0.075
Token WOM
Token ID45386
Feature activation+5.98e-01

Pos logit contributions
+0.934
joy+0.901
ˈ+0.897
 Twain+0.890
TPPStreamerBot+0.879
Neg logit contributions
alian-0.755
 harms-0.706
 rob-0.704
cade-0.697
pha-0.665
TokenEN
Token ID1677
Feature activation+2.63e+00

Pos logit contributions
alian+0.468
 rob+0.447
 harms+0.446
cade+0.441
pha+0.425
Neg logit contributions
-0.363
joy-0.342
ˈ-0.342
 Twain-0.339
TPPStreamerBot-0.336
Token.
Token ID13
Feature activation+6.44e-01

Pos logit contributions
alian+1.544
 rob+1.467
 harms+1.451
cade+1.420
kai+1.355
Neg logit contributions
-2.115
joy-2.008
ˈ-2.005
 Twain-2.001
TPPStreamerBot-1.995
Token It
Token ID632
Feature activation+7.81e-01

Pos logit contributions
alian+0.423
 rob+0.401
 harms+0.398
cade+0.394
pha+0.377
Neg logit contributions
-0.472
ˈ-0.449
joy-0.448
 Twain-0.444
TPPStreamerBot-0.443
Token
Token ID447
Feature activation+3.39e-01

Pos logit contributions
alian+0.442
 rob+0.412
 harms+0.412
cade+0.405
pha+0.385
Neg logit contributions
-0.645
joy-0.617
ˈ-0.617
 Twain-0.614
TPPStreamerBot-0.610
Token
Token ID247
Feature activation+5.00e-01

Pos logit contributions
alian+0.300
 rob+0.286
 harms+0.285
cade+0.282
ao+0.274
Neg logit contributions
-0.174
joy-0.160
ˈ-0.160
 Twain-0.159
TPPStreamerBot-0.157
Tokens
Token ID82
Feature activation+4.72e-01

Pos logit contributions
alian+0.308
 rob+0.290
 harms+0.289
cade+0.285
pha+0.272
Neg logit contributions
-0.387
joy-0.370
ˈ-0.370
 Twain-0.367
TPPStreamerBot-0.365
Tokenap
Token ID499
Feature activation+7.68e-01

Pos logit contributions
alian+0.974
 rob+0.899
cade+0.897
 harms+0.882
ao+0.853
Neg logit contributions
-1.779
 Twain-1.693
ˈ-1.663
joy-1.660
TPPStreamerBot-1.651
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
alian+0.394
 rob+0.367
 harms+0.365
cade+0.360
pha+0.339
Neg logit contributions
-0.677
ˈ-0.646
joy-0.646
 Twain-0.644
TPPStreamerBot-0.640
Tokenparse
Token ID29572
Feature activation+1.31e+00

Pos logit contributions
alian+0.971
 rob+0.916
cade+0.909
 harms+0.907
pha+0.876
Neg logit contributions
-1.052
 Twain-0.982
joy-0.973
ˈ-0.973
TPPStreamerBot-0.960
Token_
Token ID62
Feature activation+1.26e+00

Pos logit contributions
alian+0.670
 rob+0.625
 harms+0.615
cade+0.613
ctl+0.580
Neg logit contributions
-1.159
 Twain-1.098
joy-1.095
ˈ-1.094
TPPStreamerBot-1.085
Tokenargs
Token ID22046
Feature activation+1.13e+00

Pos logit contributions
alian+0.591
 harms+0.543
cade+0.541
 rob+0.541
ctl+0.511
Neg logit contributions
-1.184
 Twain-1.131
ˈ-1.116
joy-1.115
TPPStreamerBot-1.105
Token())
Token ID28955
Feature activation+2.83e+00

Pos logit contributions
alian+0.616
 rob+0.571
cade+0.565
 harms+0.563
ctl+0.540
Neg logit contributions
-0.971
 Twain-0.920
ˈ-0.919
joy-0.919
TPPStreamerBot-0.904
Token #
Token ID1303
Feature activation+8.40e-01

Pos logit contributions
alian+1.374
 rob+1.273
 harms+1.268
cade+1.244
pha+1.170
Neg logit contributions
-2.567
ˈ-2.466
joy-2.466
 Twain-2.453
TPPStreamerBot-2.440
Token initialize
Token ID41216
Feature activation+1.90e+00

Pos logit contributions
alian+0.705
 harms+0.674
 rob+0.673
cade+0.668
pha+0.645
Neg logit contributions
-0.461
ˈ-0.432
joy-0.431
 Twain-0.429
TPPStreamerBot-0.423
Token a
Token ID257
Feature activation+1.09e+00

Pos logit contributions
alian+1.201
 rob+1.146
 harms+1.128
cade+1.111
ao+1.069
Neg logit contributions
-1.471
joy-1.368
ˈ-1.365
 Twain-1.358
TPPStreamerBot-1.355
Token rectangular
Token ID36954
Feature activation+6.88e-01

Pos logit contributions
alian+0.677
 rob+0.652
 harms+0.638
cade+0.629
kai+0.600
Neg logit contributions
-0.845
 Twain-0.797
joy-0.796
ˈ-0.793
TPPStreamerBot-0.782
Token and
Token ID290
Feature activation+3.60e-01

Pos logit contributions
alian+0.387
 rob+0.370
 harms+0.363
cade+0.353
ctl+0.338
Neg logit contributions
-0.582
 Twain-0.545
ˈ-0.544
joy-0.543
TPPStreamerBot-0.539
Token Appeal
Token ID31876
Feature activation-2.73e-01

Pos logit contributions
alian+0.131
 rob+0.125
 harms+0.125
cade+0.124
ao+0.119
Neg logit contributions
-0.113
ˈ-0.104
joy-0.104
TPPStreamerBot-0.103
 Twain-0.102
Token's
Token ID338
Feature activation-5.17e-01

Pos logit contributions
+0.206
joy+0.197
ˈ+0.197
 Twain+0.195
TPPStreamerBot+0.194
Neg logit contributions
alian-0.173
 rob-0.163
 harms-0.162
cade-0.160
pha-0.153
Token 3
Token ID513
Feature activation+9.98e-01

Pos logit contributions
+0.349
joy+0.331
ˈ+0.331
 Twain+0.329
TPPStreamerBot+0.326
Neg logit contributions
alian-0.369
 rob-0.350
 harms-0.350
cade-0.346
pha-0.332
Token-
Token ID12
Feature activation+4.04e-01

Pos logit contributions
alian+0.669
 rob+0.633
 harms+0.632
cade+0.624
pha+0.597
Neg logit contributions
-0.718
joy-0.683
ˈ-0.683
 Twain-0.678
TPPStreamerBot-0.674
Token0
Token ID15
Feature activation+9.36e-01

Pos logit contributions
alian+0.293
 rob+0.279
 harms+0.278
cade+0.275
pha+0.264
Neg logit contributions
-0.268
joy-0.254
ˈ-0.254
 Twain-0.252
TPPStreamerBot-0.250
Token ruling
Token ID6922
Feature activation+2.56e+00

Pos logit contributions
alian+0.665
 rob+0.635
 harms+0.633
cade+0.623
pha+0.598
Neg logit contributions
-0.637
joy-0.602
ˈ-0.602
 Twain-0.596
TPPStreamerBot-0.595
Token agreed
Token ID4987
Feature activation-1.51e+00

Pos logit contributions
alian+1.536
 harms+1.462
 rob+1.451
cade+1.410
pha+1.342
Neg logit contributions
-2.046
joy-1.938
ˈ-1.936
TPPStreamerBot-1.925
 Twain-1.914
Token with
Token ID351
Feature activation+6.82e-03

Pos logit contributions
+1.086
 Twain+1.048
joy+1.048
ˈ+1.039
TPPStreamerBot+1.025
Neg logit contributions
alian-0.998
 harms-0.935
 rob-0.934
cade-0.932
pha-0.889
Token a
Token ID257
Feature activation+5.21e-01

Pos logit contributions
alian+0.005
 rob+0.004
 harms+0.004
cade+0.004
pha+0.004
Neg logit contributions
-0.005
ˈ-0.005
joy-0.005
 Twain-0.005
TPPStreamerBot-0.005
Token federal
Token ID2717
Feature activation+3.69e-01

Pos logit contributions
alian+0.357
 rob+0.340
 harms+0.339
cade+0.334
pha+0.319
Neg logit contributions
-0.370
joy-0.350
ˈ-0.350
 Twain-0.346
TPPStreamerBot-0.345
Token judge
Token ID5052
Feature activation+1.70e+00

Pos logit contributions
alian+0.249
 rob+0.236
 harms+0.236
cade+0.232
pha+0.222
Neg logit contributions
-0.265
joy-0.251
ˈ-0.251
 Twain-0.249
TPPStreamerBot-0.248
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
alian+0.847
 rob+0.802
 harms+0.796
cade+0.777
pha+0.740
Neg logit contributions
-1.213
ˈ-1.160
joy-1.160
 Twain-1.152
TPPStreamerBot-1.147
Token or
Token ID393
Feature activation+3.79e-01

Pos logit contributions
+0.144
joy+0.137
ˈ+0.137
 Twain+0.136
TPPStreamerBot+0.135
Neg logit contributions
alian-0.129
 rob-0.122
 harms-0.121
cade-0.119
pha-0.114
Token about
Token ID546
Feature activation-1.84e-01

Pos logit contributions
alian+0.259
 rob+0.246
 harms+0.245
cade+0.241
pha+0.232
Neg logit contributions
-0.269
joy-0.255
ˈ-0.254
 Twain-0.253
TPPStreamerBot-0.251
Token three
Token ID1115
Feature activation+1.44e-01

Pos logit contributions
+0.119
joy+0.112
ˈ+0.112
 Twain+0.111
TPPStreamerBot+0.110
Neg logit contributions
alian-0.137
 rob-0.131
 harms-0.130
cade-0.129
pha-0.124
Token per
Token ID583
Feature activation-4.70e-01

Pos logit contributions
alian+0.084
 rob+0.078
 harms+0.078
cade+0.077
pha+0.073
Neg logit contributions
-0.117
ˈ-0.112
joy-0.112
 Twain-0.111
TPPStreamerBot-0.111
Token cent
Token ID1247
Feature activation+2.46e+00

Pos logit contributions
+0.418
ˈ+0.401
joy+0.401
 Twain+0.399
TPPStreamerBot+0.397
Neg logit contributions
alian-0.236
 rob-0.219
 harms-0.218
cade-0.214
pha-0.202
Token of
Token ID286
Feature activation-5.17e-01

Pos logit contributions
alian+1.308
 rob+1.220
 harms+1.214
cade+1.194
pha+1.131
Neg logit contributions
-2.110
ˈ-2.022
joy-2.021
 Twain-2.011
TPPStreamerBot-1.998
Token the
Token ID262
Feature activation-4.88e-01

Pos logit contributions
+0.388
ˈ+0.371
joy+0.370
 Twain+0.368
TPPStreamerBot+0.365
Neg logit contributions
alian-0.331
 rob-0.310
 harms-0.310
cade-0.307
pha-0.293
Token 9
Token ID860
Feature activation+4.77e-01

Pos logit contributions
+0.366
joy+0.348
ˈ+0.347
 Twain+0.345
TPPStreamerBot+0.343
Neg logit contributions
alian-0.314
 rob-0.297
 harms-0.296
cade-0.291
pha-0.278
Token,
Token ID11
Feature activation-1.26e-01

Pos logit contributions
alian+0.314
 rob+0.298
 harms+0.297
cade+0.292
pha+0.279
Neg logit contributions
-0.350
joy-0.333
ˈ-0.333
 Twain-0.331
TPPStreamerBot-0.329
Token204
Token ID18638
Feature activation+2.84e-01

Pos logit contributions
+0.080
joy+0.076
ˈ+0.076
 Twain+0.075
TPPStreamerBot+0.075
Neg logit contributions
alian-0.095
 rob-0.090
 harms-0.090
cade-0.089
pha-0.086
TokenWhere
Token ID8496
Feature activation-6.36e-01

Pos logit contributions
alian+0.800
 rob+0.762
 harms+0.756
cade+0.752
pha+0.715
Neg logit contributions
-0.875
ˈ-0.826
 Twain-0.825
joy-0.824
TPPStreamerBot-0.817
Token's
Token ID338
Feature activation-6.58e-01

Pos logit contributions
+0.484
joy+0.469
 Twain+0.465
ˈ+0.465
TPPStreamerBot+0.459
Neg logit contributions
alian-0.393
 rob-0.367
 harms-0.366
cade-0.364
pha-0.351
Token the
Token ID262
Feature activation-1.54e-01

Pos logit contributions
+0.469
joy+0.448
ˈ+0.446
 Twain+0.445
TPPStreamerBot+0.440
Neg logit contributions
alian-0.446
 harms-0.420
 rob-0.420
cade-0.415
pha-0.399
Token money
Token ID1637
Feature activation+1.93e+00

Pos logit contributions
+0.116
joy+0.111
ˈ+0.111
 Twain+0.110
TPPStreamerBot+0.109
Neg logit contributions
alian-0.098
 rob-0.092
 harms-0.092
cade-0.091
pha-0.087
Token?"
Token ID1701
Feature activation+3.83e-01

Pos logit contributions
alian+1.123
 rob+1.056
 harms+1.049
cade+1.032
pha+0.980
Neg logit contributions
-1.572
ˈ-1.499
joy-1.496
 Twain-1.486
TPPStreamerBot-1.479
Token Haitian
Token ID48723
Feature activation+7.14e-01

Pos logit contributions
alian+0.252
 rob+0.239
 harms+0.238
cade+0.235
pha+0.224
Neg logit contributions
-0.282
ˈ-0.268
joy-0.267
 Twain-0.265
TPPStreamerBot-0.264
Token activists
Token ID7941
Feature activation+1.13e+00

Pos logit contributions
alian+0.467
 rob+0.442
 harms+0.440
cade+0.435
pha+0.414
Neg logit contributions
-0.527
ˈ-0.501
joy-0.499
 Twain-0.497
TPPStreamerBot-0.496
Token protesting
Token ID23655
Feature activation+1.04e+00

Pos logit contributions
alian+0.657
 rob+0.620
 harms+0.614
cade+0.604
kai+0.572
Neg logit contributions
-0.918
ˈ-0.872
joy-0.868
 Twain-0.864
TPPStreamerBot-0.863
Token the
Token ID262
Feature activation+6.18e-01

Pos logit contributions
alian+0.627
 rob+0.595
 harms+0.593
cade+0.584
ao+0.551
Neg logit contributions
-0.815
ˈ-0.775
joy-0.774
 Twain-0.769
TPPStreamerBot-0.768
Token theft
Token ID12402
Feature activation+1.59e-01

Pos logit contributions
alian+0.391
 rob+0.371
 harms+0.369
cade+0.363
pha+0.345
Neg logit contributions
-0.470
joy-0.447
ˈ-0.447
 Twain-0.443
TPPStreamerBot-0.442
Token of
Token ID286
Feature activation-1.40e-01

Pos logit contributions
alian+0.088
 harms+0.081
 rob+0.081
cade+0.080
pha+0.076
Neg logit contributions
-0.133
joy-0.129
ˈ-0.128
 Twain-0.128
TPPStreamerBot-0.126
Token minutes
Token ID2431
Feature activation-1.59e+00

Pos logit contributions
+0.406
joy+0.387
ˈ+0.386
 Twain+0.383
TPPStreamerBot+0.380
Neg logit contributions
alian-0.411
 rob-0.389
 harms-0.388
cade-0.384
pha-0.368
Token for
Token ID329
Feature activation-4.55e-01

Pos logit contributions
+1.259
joy+1.216
ˈ+1.211
 Twain+1.210
TPPStreamerBot+1.199
Neg logit contributions
alian-0.934
 harms-0.872
 rob-0.872
cade-0.866
pha-0.825
Token longest
Token ID14069
Feature activation-4.53e-01

Pos logit contributions
+0.306
ˈ+0.288
joy+0.288
 Twain+0.284
TPPStreamerBot+0.284
Neg logit contributions
alian-0.329
 rob-0.314
 harms-0.314
cade-0.308
pha-0.296
Token.
Token ID13
Feature activation-4.61e-01

Pos logit contributions
+0.367
joy+0.352
ˈ+0.351
 Twain+0.351
TPPStreamerBot+0.348
Neg logit contributions
alian-0.262
 rob-0.245
 harms-0.244
cade-0.241
pha-0.230
Token This
Token ID770
Feature activation+1.42e-01

Pos logit contributions
+0.321
joy+0.305
ˈ+0.305
 Twain+0.303
TPPStreamerBot+0.300
Neg logit contributions
alian-0.321
 rob-0.304
 harms-0.303
cade-0.299
pha-0.287
Token will
Token ID481
Feature activation+1.51e-01

Pos logit contributions
alian+0.083
 rob+0.078
 harms+0.078
cade+0.076
pha+0.073
Neg logit contributions
-0.114
ˈ-0.109
joy-0.109
 Twain-0.108
TPPStreamerBot-0.108
Token be
Token ID307
Feature activation-8.13e-01

Pos logit contributions
alian+0.099
 harms+0.094
 rob+0.093
cade+0.093
pha+0.089
Neg logit contributions
-0.109
ˈ-0.105
joy-0.105
 Twain-0.104
TPPStreamerBot-0.103
Token updated
Token ID6153
Feature activation+4.49e-02

Pos logit contributions
+0.576
ˈ+0.548
joy+0.548
 Twain+0.545
TPPStreamerBot+0.540
Neg logit contributions
alian-0.554
 rob-0.524
 harms-0.523
cade-0.516
pha-0.495
Token when
Token ID618
Feature activation-2.04e-01

Pos logit contributions
alian+0.026
 harms+0.025
 rob+0.025
cade+0.024
pha+0.023
Neg logit contributions
-0.036
ˈ-0.034
joy-0.034
 Twain-0.034
TPPStreamerBot-0.034
Token I
Token ID314
Feature activation+9.04e-02

Pos logit contributions
+0.137
joy+0.130
ˈ+0.130
 Twain+0.130
TPPStreamerBot+0.128
Neg logit contributions
alian-0.146
 harms-0.138
 rob-0.138
cade-0.137
pha-0.132
Token have
Token ID423
Feature activation+2.06e-01

Pos logit contributions
alian+0.060
 rob+0.057
 harms+0.056
cade+0.056
pha+0.053
Neg logit contributions
-0.066
joy-0.063
ˈ-0.063
 Twain-0.062
TPPStreamerBot-0.062
Tokenursed
Token ID17539
Feature activation-1.35e+00

Pos logit contributions
+0.941
ˈ+0.895
joy+0.894
 Twain+0.890
TPPStreamerBot+0.883
Neg logit contributions
alian-0.806
 rob-0.761
 harms-0.759
cade-0.749
pha-0.715
Token for
Token ID329
Feature activation-1.27e+00

Pos logit contributions
+0.978
ˈ+0.937
joy+0.934
 Twain+0.931
TPPStreamerBot+0.923
Neg logit contributions
alian-0.899
 harms-0.843
 rob-0.842
cade-0.836
pha-0.801
Token hand
Token ID1021
Feature activation+7.82e-01

Pos logit contributions
+0.932
ˈ+0.891
joy+0.890
 Twain+0.886
TPPStreamerBot+0.877
Neg logit contributions
alian-0.834
 rob-0.783
 harms-0.782
cade-0.774
pha-0.742
Token lot
Token ID1256
Feature activation+8.24e-01

Pos logit contributions
alian+0.486
 rob+0.457
 harms+0.456
cade+0.449
pha+0.430
Neg logit contributions
-0.602
joy-0.575
ˈ-0.574
 Twain-0.571
TPPStreamerBot-0.567
Tokenion
Token ID295
Feature activation+2.98e-01

Pos logit contributions
alian+0.529
 rob+0.502
 harms+0.499
cade+0.492
ao+0.469
Neg logit contributions
-0.620
ˈ-0.590
joy-0.586
TPPStreamerBot-0.583
 Twain-0.583
Token,
Token ID11
Feature activation+7.00e-01

Pos logit contributions
alian+0.176
 rob+0.166
 harms+0.166
cade+0.163
pha+0.154
Neg logit contributions
-0.240
ˈ-0.229
joy-0.228
 Twain-0.226
TPPStreamerBot-0.226
Token a
Token ID257
Feature activation+8.46e-01

Pos logit contributions
alian+0.450
 rob+0.432
 harms+0.428
cade+0.419
kai+0.400
Neg logit contributions
-0.527
joy-0.498
ˈ-0.497
TPPStreamerBot-0.490
 Twain-0.489
Token floor
Token ID4314
Feature activation+3.17e-01

Pos logit contributions
alian+0.549
 rob+0.527
 harms+0.525
cade+0.514
pha+0.492
Neg logit contributions
-0.630
joy-0.595
ˈ-0.594
 Twain-0.588
TPPStreamerBot-0.587
Token mat
Token ID2603
Feature activation-1.32e+00

Pos logit contributions
alian+0.199
 rob+0.187
 harms+0.187
cade+0.184
pha+0.176
Neg logit contributions
-0.242
ˈ-0.231
joy-0.230
 Twain-0.229
TPPStreamerBot-0.228
Token,
Token ID11
Feature activation+8.21e-01

Pos logit contributions
+1.039
joy+0.998
ˈ+0.996
 Twain+0.995
TPPStreamerBot+0.983
Neg logit contributions
alian-0.785
 harms-0.737
 rob-0.735
cade-0.724
pha-0.694
Token $
Token ID720
Feature activation-4.20e-01

Pos logit contributions
alian+0.523
 rob+0.501
 harms+0.497
cade+0.487
pha+0.464
Neg logit contributions
-0.623
joy-0.587
ˈ-0.586
TPPStreamerBot-0.582
 Twain-0.579
Token obtained
Token ID6492
Feature activation-5.17e-01

Pos logit contributions
alian+0.349
 rob+0.331
 harms+0.330
cade+0.326
pha+0.311
Neg logit contributions
-0.387
ˈ-0.367
joy-0.367
 Twain-0.365
TPPStreamerBot-0.362
Token by
Token ID416
Feature activation-4.20e-01

Pos logit contributions
+0.364
ˈ+0.350
joy+0.349
 Twain+0.346
TPPStreamerBot+0.344
Neg logit contributions
alian-0.350
 rob-0.332
 harms-0.331
cade-0.327
pha-0.314
Token multiplying
Token ID48816
Feature activation-9.24e-01

Pos logit contributions
+0.292
joy+0.278
ˈ+0.278
 Twain+0.276
TPPStreamerBot+0.274
Neg logit contributions
alian-0.291
 rob-0.276
 harms-0.276
cade-0.272
pha-0.261
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
+0.669
ˈ+0.641
joy+0.638
 Twain+0.637
TPPStreamerBot+0.628
Neg logit contributions
alian-0.612
 harms-0.575
 rob-0.573
cade-0.569
pha-0.549
Token bottleneck
Token ID49936
Feature activation+7.11e-01

Pos logit contributions
alian+0.078
 rob+0.074
 harms+0.073
cade+0.073
pha+0.069
Neg logit contributions
-0.087
ˈ-0.083
joy-0.083
 Twain-0.082
TPPStreamerBot-0.082
Token bandwidth
Token ID19484
Feature activation-9.63e-02

Pos logit contributions
alian+0.465
 rob+0.439
 harms+0.439
cade+0.433
pha+0.414
Neg logit contributions
-0.523
ˈ-0.498
joy-0.498
 Twain-0.494
TPPStreamerBot-0.491
Token and
Token ID290
Feature activation-9.06e-02

Pos logit contributions
+0.068
joy+0.065
ˈ+0.065
 Twain+0.065
TPPStreamerBot+0.064
Neg logit contributions
alian-0.065
 rob-0.062
 harms-0.061
cade-0.061
pha-0.059
Token round
Token ID2835
Feature activation+1.59e+00

Pos logit contributions
+0.065
joy+0.062
ˈ+0.062
 Twain+0.062
TPPStreamerBot+0.061
Neg logit contributions
alian-0.061
 rob-0.057
 harms-0.057
cade-0.057
pha-0.054
Token-
Token ID12
Feature activation-1.04e+00

Pos logit contributions
alian+1.019
 rob+0.983
 harms+0.966
cade+0.951
ctl+0.914
Neg logit contributions
-1.203
joy-1.133
ˈ-1.131
 Twain-1.127
TPPStreamerBot-1.121
Tokentrip
Token ID39813
Feature activation-1.49e+00

Pos logit contributions
+0.757
joy+0.725
ˈ+0.724
 Twain+0.718
TPPStreamerBot+0.714
Neg logit contributions
alian-0.684
 harms-0.645
 rob-0.645
cade-0.635
pha-0.608
Token propagation
Token ID43594
Feature activation-2.07e-01

Pos logit contributions
+1.275
joy+1.230
 Twain+1.227
ˈ+1.227
TPPStreamerBot+1.216
Neg logit contributions
alian-0.784
 rob-0.716
 harms-0.713
cade-0.710
kai-0.674
Token profit
Token ID7630
Feature activation+8.42e-01

Pos logit contributions
alian+1.104
 rob+1.052
 harms+1.042
cade+1.020
ao+0.974
Neg logit contributions
-1.414
ˈ-1.335
joy-1.332
TPPStreamerBot-1.324
 Twain-1.321
Token margin
Token ID10330
Feature activation+1.33e+00

Pos logit contributions
alian+0.545
 rob+0.515
 harms+0.514
cade+0.505
pha+0.482
Neg logit contributions
-0.627
ˈ-0.597
joy-0.595
 Twain-0.592
TPPStreamerBot-0.589
Token on
Token ID319
Feature activation-7.59e-01

Pos logit contributions
alian+0.744
 harms+0.698
 rob+0.698
cade+0.681
pha+0.642
Neg logit contributions
-1.119
ˈ-1.067
joy-1.066
 Twain-1.057
TPPStreamerBot-1.057
Token $
Token ID720
Feature activation-4.69e-01

Pos logit contributions
+0.557
joy+0.529
ˈ+0.529
 Twain+0.525
TPPStreamerBot+0.522
Neg logit contributions
alian-0.499
 rob-0.472
 harms-0.471
cade-0.464
pha-0.444
Token700
Token ID9879
Feature activation-1.19e+00

Pos logit contributions
+0.317
joy+0.301
ˈ+0.301
 Twain+0.298
TPPStreamerBot+0.296
Neg logit contributions
alian-0.335
 rob-0.318
 harms-0.318
cade-0.313
pha-0.301
Token million
Token ID1510
Feature activation-9.01e-03

Pos logit contributions
+0.776
joy+0.735
ˈ+0.733
 Twain+0.727
TPPStreamerBot+0.719
Neg logit contributions
alian-0.875
 harms-0.827
 rob-0.826
cade-0.821
pha-0.791
Token in
Token ID287
Feature activation+3.76e-01

Pos logit contributions
+0.007
joy+0.007
 Twain+0.007
ˈ+0.007
TPPStreamerBot+0.007
Neg logit contributions
alian-0.005
 rob-0.005
 harms-0.005
cade-0.005
pha-0.005
Token revenue
Token ID6426
Feature activation+8.56e-01

Pos logit contributions
alian+0.237
 rob+0.224
 harms+0.223
cade+0.219
pha+0.209
Neg logit contributions
-0.287
joy-0.272
ˈ-0.272
 Twain-0.270
TPPStreamerBot-0.269
Token delivers
Token ID16316
Feature activation+9.41e-01

Pos logit contributions
alian+0.486
 rob+0.454
 harms+0.453
cade+0.447
pha+0.425
Neg logit contributions
-0.704
joy-0.674
ˈ-0.674
 Twain-0.670
TPPStreamerBot-0.666
Token operating
Token ID5361
Feature activation-1.25e+00

Pos logit contributions
alian+0.608
 rob+0.587
 harms+0.583
cade+0.570
ao+0.545
Neg logit contributions
-0.703
ˈ-0.661
joy-0.658
TPPStreamerBot-0.652
 Twain-0.650
Token profits
Token ID10177
Feature activation+1.55e-02

Pos logit contributions
+0.905
joy+0.864
ˈ+0.863
 Twain+0.860
TPPStreamerBot+0.855
Neg logit contributions
alian-0.826
 harms-0.768
cade-0.767
 rob-0.766
pha-0.735
Token to
Token ID284
Feature activation+5.11e-01

Pos logit contributions
alian+0.544
 rob+0.512
 harms+0.509
cade+0.503
pha+0.477
Neg logit contributions
-0.721
ˈ-0.687
joy-0.686
 Twain-0.683
TPPStreamerBot-0.678
Token protect
Token ID1805
Feature activation-4.70e-01

Pos logit contributions
alian+0.317
 rob+0.300
 harms+0.298
cade+0.294
pha+0.280
Neg logit contributions
-0.395
joy-0.376
ˈ-0.376
 Twain-0.374
TPPStreamerBot-0.372
Token polling
Token ID13985
Feature activation+2.94e-01

Pos logit contributions
+0.349
joy+0.332
ˈ+0.332
 Twain+0.330
TPPStreamerBot+0.328
Neg logit contributions
alian-0.305
 rob-0.288
 harms-0.287
cade-0.283
pha-0.271
Token stations
Token ID8985
Feature activation-1.01e+00

Pos logit contributions
alian+0.183
 rob+0.176
 harms+0.175
cade+0.171
ao+0.162
Neg logit contributions
-0.225
ˈ-0.215
joy-0.214
TPPStreamerBot-0.213
 Twain-0.212
Token ahead
Token ID4058
Feature activation-3.36e-01

Pos logit contributions
+0.778
joy+0.746
ˈ+0.744
 Twain+0.741
TPPStreamerBot+0.735
Neg logit contributions
alian-0.624
 harms-0.586
 rob-0.583
cade-0.578
pha-0.556
Token of
Token ID286
Feature activation-5.51e-01

Pos logit contributions
+0.290
ˈ+0.278
joy+0.278
 Twain+0.276
TPPStreamerBot+0.275
Neg logit contributions
alian-0.177
 rob-0.165
 harms-0.165
cade-0.162
pha-0.153
Token the
Token ID262
Feature activation+8.26e-02

Pos logit contributions
+0.408
ˈ+0.388
joy+0.388
 Twain+0.385
TPPStreamerBot+0.383
Neg logit contributions
alian-0.358
 harms-0.337
 rob-0.335
cade-0.332
pha-0.320
Token '
Token ID705
Feature activation+3.28e-01

Pos logit contributions
alian+0.056
 harms+0.053
 rob+0.052
cade+0.052
pha+0.050
Neg logit contributions
-0.059
ˈ-0.056
joy-0.056
 Twain-0.056
TPPStreamerBot-0.055
Tokenb
Token ID65
Feature activation+9.28e-01

Pos logit contributions
alian+0.218
 harms+0.206
 rob+0.206
cade+0.203
pha+0.195
Neg logit contributions
-0.238
joy-0.227
ˈ-0.227
 Twain-0.225
TPPStreamerBot-0.224
Tokenanned
Token ID3577
Feature activation+1.31e+00

Pos logit contributions
alian+0.585
 rob+0.551
 harms+0.550
cade+0.543
pha+0.518
Neg logit contributions
-0.707
ˈ-0.673
joy-0.673
 Twain-0.670
TPPStreamerBot-0.665
Token'
Token ID6
Feature activation+1.38e+00

Pos logit contributions
alian+0.688
 rob+0.649
 harms+0.641
cade+0.634
ao+0.596
Neg logit contributions
-1.131
ˈ-1.087
joy-1.082
 Twain-1.078
TPPStreamerBot-1.074
Token
Token ID236
Feature activation-4.08e-01

Pos logit contributions
alian+0.384
 rob+0.368
 harms+0.368
cade+0.364
pha+0.352
Neg logit contributions
-0.238
joy-0.222
ˈ-0.222
 Twain-0.221
TPPStreamerBot-0.217
Token
Token ID141
Feature activation+6.67e-01

Pos logit contributions
+0.299
joy+0.284
ˈ+0.284
 Twain+0.282
TPPStreamerBot+0.279
Neg logit contributions
alian-0.269
 rob-0.253
 harms-0.253
cade-0.250
pha-0.239
Token
Token ID231
Feature activation-8.24e-01

Pos logit contributions
alian+0.569
 rob+0.545
 harms+0.545
cade+0.539
pha+0.521
Neg logit contributions
-0.358
ˈ-0.334
joy-0.334
 Twain-0.331
TPPStreamerBot-0.328
Tokenе
Token ID16843
Feature activation-8.77e-02

Pos logit contributions
+0.543
joy+0.514
ˈ+0.514
 Twain+0.512
TPPStreamerBot+0.505
Neg logit contributions
alian-0.600
 harms-0.571
 rob-0.571
cade-0.565
pha-0.542
Tokenе
Token ID16843
Feature activation-1.71e-01

Pos logit contributions
+0.064
ˈ+0.061
joy+0.061
 Twain+0.061
TPPStreamerBot+0.060
Neg logit contributions
alian-0.058
 rob-0.054
 harms-0.054
cade-0.054
pha-0.051
Token
Token ID12466
Feature activation-2.25e-01

Pos logit contributions
+0.131
ˈ+0.125
joy+0.125
 Twain+0.124
TPPStreamerBot+0.124
Neg logit contributions
alian-0.106
 rob-0.100
 harms-0.099
cade-0.098
pha-0.094
Token
Token ID109
Feature activation+2.23e-01

Pos logit contributions
+0.118
ˈ+0.110
joy+0.110
 Twain+0.109
TPPStreamerBot+0.108
Neg logit contributions
alian-0.196
 harms-0.187
 rob-0.187
cade-0.185
pha-0.179
Tokenо�
Token ID25443
Feature activation-1.12e+00

Pos logit contributions
alian+0.155
 rob+0.147
 harms+0.146
cade+0.145
pha+0.139
Neg logit contributions
-0.155
joy-0.147
ˈ-0.147
 Twain-0.146
TPPStreamerBot-0.145
Token
Token ID119
Feature activation-7.63e-01

Pos logit contributions
+0.581
ˈ+0.542
joy+0.541
 Twain+0.536
TPPStreamerBot+0.531
Neg logit contributions
alian-0.985
 harms-0.941
 rob-0.940
cade-0.930
pha-0.898
Tokenь
Token ID45367
Feature activation+6.57e-01

Pos logit contributions
+0.410
ˈ+0.381
joy+0.381
 Twain+0.378
TPPStreamerBot+0.372
Neg logit contributions
alian-0.652
 rob-0.624
 harms-0.624
cade-0.618
pha-0.597
Token
Token ID141
Feature activation+2.45e-01

Pos logit contributions
alian+0.455
 rob+0.432
 harms+0.429
cade+0.423
pha+0.409
Neg logit contributions
-0.454
joy-0.436
ˈ-0.435
 Twain-0.433
TPPStreamerBot-0.428
Token_
Token ID62
Feature activation+3.99e-01

Pos logit contributions
alian+0.038
 rob+0.035
 harms+0.035
cade+0.035
pha+0.033
Neg logit contributions
-0.063
ˈ-0.060
joy-0.060
 Twain-0.059
TPPStreamerBot-0.059
Token00
Token ID405
Feature activation+4.61e-01

Pos logit contributions
alian+0.326
 rob+0.311
 harms+0.311
cade+0.308
pha+0.297
Neg logit contributions
-0.229
ˈ-0.215
joy-0.215
 Twain-0.213
TPPStreamerBot-0.211
Token61
Token ID5333
Feature activation+3.96e-01

Pos logit contributions
alian+0.331
 rob+0.314
 harms+0.313
cade+0.311
pha+0.299
Neg logit contributions
-0.311
ˈ-0.293
joy-0.292
 Twain-0.291
TPPStreamerBot-0.289
TokenE
Token ID36
Feature activation-9.00e-02

Pos logit contributions
alian+0.285
 rob+0.271
 harms+0.270
cade+0.267
pha+0.256
Neg logit contributions
-0.266
joy-0.251
ˈ-0.251
 Twain-0.250
TPPStreamerBot-0.248
Token,
Token ID11
Feature activation-3.12e-01

Pos logit contributions
+0.072
joy+0.069
ˈ+0.069
 Twain+0.068
TPPStreamerBot+0.068
Neg logit contributions
alian-0.053
 rob-0.050
 harms-0.050
cade-0.049
pha-0.047
TokenDP
Token ID6322
Feature activation-3.51e-01

Pos logit contributions
+0.259
joy+0.248
ˈ+0.248
 Twain+0.247
TPPStreamerBot+0.245
Neg logit contributions
alian-0.174
 rob-0.163
 harms-0.163
cade-0.160
pha-0.152
Token02
Token ID2999
Feature activation+6.56e-02

Pos logit contributions
+0.212
ˈ+0.200
joy+0.200
 Twain+0.198
TPPStreamerBot+0.196
Neg logit contributions
alian-0.276
 rob-0.263
 harms-0.263
cade-0.260
pha-0.251
Token_
Token ID62
Feature activation+4.05e-01

Pos logit contributions
alian+0.035
 rob+0.032
 harms+0.032
cade+0.032
pha+0.030
Neg logit contributions
-0.057
ˈ-0.054
joy-0.054
 Twain-0.054
TPPStreamerBot-0.054
Token00
Token ID405
Feature activation+4.14e-01

Pos logit contributions
alian+0.331
 rob+0.316
 harms+0.316
cade+0.312
pha+0.302
Neg logit contributions
-0.232
joy-0.217
ˈ-0.217
 Twain-0.215
TPPStreamerBot-0.213
Token62
Token ID5237
Feature activation-2.51e-01

Pos logit contributions
alian+0.305
 rob+0.290
 harms+0.289
cade+0.287
pha+0.276
Neg logit contributions
-0.271
ˈ-0.256
joy-0.255
 Twain-0.254
TPPStreamerBot-0.252
TokenE
Token ID36
Feature activation-3.18e-01

Pos logit contributions
+0.171
joy+0.161
ˈ+0.161
 Twain+0.160
TPPStreamerBot+0.160
Neg logit contributions
alian-0.178
 rob-0.169
 harms-0.169
cade-0.167
pha-0.161
Token,
Token ID11
Feature activation-7.41e-01

Pos logit contributions
alian+0.221
 rob+0.207
 harms+0.207
cade+0.203
pha+0.193
Neg logit contributions
-0.304
joy-0.292
ˈ-0.291
 Twain-0.290
TPPStreamerBot-0.288
Token a
Token ID257
Feature activation+5.19e-02

Pos logit contributions
+0.518
joy+0.493
ˈ+0.493
 Twain+0.491
TPPStreamerBot+0.486
Neg logit contributions
alian-0.510
 rob-0.483
 harms-0.482
cade-0.476
pha-0.457
Token Facebook
Token ID3203
Feature activation+8.49e-01

Pos logit contributions
alian+0.037
 rob+0.035
 harms+0.035
cade+0.035
pha+0.033
Neg logit contributions
-0.035
ˈ-0.033
joy-0.033
 Twain-0.033
TPPStreamerBot-0.033
Token spokesman
Token ID6523
Feature activation-1.36e+00

Pos logit contributions
alian+0.529
 rob+0.499
 harms+0.497
cade+0.490
ao+0.465
Neg logit contributions
-0.661
ˈ-0.625
joy-0.622
 Twain-0.619
TPPStreamerBot-0.617
Token,
Token ID11
Feature activation-3.13e-01

Pos logit contributions
+1.105
joy+1.069
ˈ+1.062
 Twain+1.061
TPPStreamerBot+1.051
Neg logit contributions
alian-0.775
 harms-0.730
 rob-0.729
cade-0.717
pha-0.684
Token said
Token ID531
Feature activation-5.59e-01

Pos logit contributions
+0.235
ˈ+0.222
joy+0.221
 Twain+0.220
TPPStreamerBot+0.219
Neg logit contributions
alian-0.203
 rob-0.192
 harms-0.191
cade-0.188
pha-0.180
Token the
Token ID262
Feature activation-5.82e-01

Pos logit contributions
+0.418
joy+0.400
ˈ+0.399
 Twain+0.398
TPPStreamerBot+0.394
Neg logit contributions
alian-0.358
 rob-0.337
 harms-0.336
cade-0.332
pha-0.318
Token company
Token ID1664
Feature activation-2.64e-01

Pos logit contributions
+0.372
ˈ+0.350
joy+0.349
 Twain+0.345
TPPStreamerBot+0.344
Neg logit contributions
alian-0.440
 rob-0.421
 harms-0.420
cade-0.413
ao-0.397
Token had
Token ID550
Feature activation-2.80e-01

Pos logit contributions
+0.214
joy+0.204
ˈ+0.204
 Twain+0.203
TPPStreamerBot+0.202
Neg logit contributions
alian-0.154
 rob-0.144
 harms-0.144
cade-0.141
pha-0.134
Token tried
Token ID3088
Feature activation+7.92e-01

Pos logit contributions
+0.209
joy+0.198
ˈ+0.197
TPPStreamerBot+0.194
 Twain+0.194
Neg logit contributions
alian-0.182
 rob-0.174
 harms-0.173
cade-0.169
ao-0.163
Token outsourcing
Token ID44333
Feature activation+1.46e+00

Pos logit contributions
alian+0.478
 rob+0.451
 harms+0.450
cade+0.441
pha+0.421
Neg logit contributions
-0.625
ˈ-0.595
joy-0.595
 Twain-0.591
TPPStreamerBot-0.588
Token
Token ID1399
Feature activation-9.27e-01

Pos logit contributions
alian+0.648
 rob+0.620
 harms+0.617
cade+0.606
ao+0.584
Neg logit contributions
-0.602
ˈ-0.567
joy-0.565
 Twain-0.561
TPPStreamerBot-0.559
Token I
Token ID314
Feature activation+4.56e-02

Pos logit contributions
+0.643
joy+0.613
ˈ+0.611
 Twain+0.607
TPPStreamerBot+0.602
Neg logit contributions
alian-0.644
 rob-0.609
 harms-0.608
cade-0.602
pha-0.577
Token
Token ID1399
Feature activation-1.56e-01

Pos logit contributions
alian+0.030
 rob+0.028
 harms+0.028
cade+0.028
pha+0.027
Neg logit contributions
-0.033
joy-0.032
ˈ-0.032
 Twain-0.032
TPPStreamerBot-0.031
Token
Token ID198
Feature activation-6.32e-01

Pos logit contributions
+0.103
ˈ+0.097
joy+0.097
 Twain+0.097
TPPStreamerBot+0.096
Neg logit contributions
alian-0.115
 rob-0.109
 harms-0.109
cade-0.107
pha-0.103
Token
Token ID198
Feature activation-4.85e-01

Pos logit contributions
+0.477
ˈ+0.447
joy+0.446
 Twain+0.445
TPPStreamerBot+0.442
Neg logit contributions
alian-0.408
 rob-0.388
 harms-0.385
cade-0.382
pha-0.364
Token
Token ID447
Feature activation-5.40e-01

Pos logit contributions
+0.349
ˈ+0.331
joy+0.331
 Twain+0.329
TPPStreamerBot+0.327
Neg logit contributions
alian-0.325
 rob-0.308
 harms-0.307
cade-0.303
pha-0.290
Token
Token ID250
Feature activation-1.73e-01

Pos logit contributions
+0.247
joy+0.228
ˈ+0.228
 Twain+0.225
TPPStreamerBot+0.223
Neg logit contributions
alian-0.504
 rob-0.484
 harms-0.484
cade-0.479
pha-0.465
TokenNa
Token ID26705
Feature activation+1.16e+00

Pos logit contributions
+0.122
ˈ+0.116
joy+0.116
 Twain+0.115
TPPStreamerBot+0.114
Neg logit contributions
alian-0.119
 rob-0.113
 harms-0.112
cade-0.111
pha-0.106
Tokenof
Token ID1659
Feature activation-1.93e-01

Pos logit contributions
alian+0.635
 rob+0.588
 harms+0.587
cade+0.576
ao+0.553
Neg logit contributions
-0.996
ˈ-0.943
joy-0.943
 Twain-0.942
TPPStreamerBot-0.938
Tokenumi
Token ID12994
Feature activation-2.51e-01

Pos logit contributions
+0.165
joy+0.156
ˈ+0.156
 Twain+0.156
TPPStreamerBot+0.154
Neg logit contributions
alian-0.106
 rob-0.097
 harms-0.097
cade-0.096
pha-0.092
Token-
Token ID12
Feature activation-8.46e-01

Pos logit contributions
+0.204
ˈ+0.194
joy+0.194
 Twain+0.193
TPPStreamerBot+0.192
Neg logit contributions
alian-0.146
 rob-0.137
 harms-0.137
cade-0.135
pha-0.128
Token that
Token ID326
Feature activation+8.64e-02

Pos logit contributions
+0.259
ˈ+0.247
joy+0.246
 Twain+0.244
TPPStreamerBot+0.243
Neg logit contributions
alian-0.215
 rob-0.203
 harms-0.202
cade-0.199
pha-0.190
Token may
Token ID743
Feature activation-1.18e+00

Pos logit contributions
alian+0.053
 rob+0.050
 harms+0.050
cade+0.049
pha+0.047
Neg logit contributions
-0.067
ˈ-0.064
joy-0.064
 Twain-0.064
TPPStreamerBot-0.063
Token or
Token ID393
Feature activation-3.92e-01

Pos logit contributions
+0.873
ˈ+0.840
joy+0.839
 Twain+0.833
TPPStreamerBot+0.820
Neg logit contributions
alian-0.761
 harms-0.710
 rob-0.707
cade-0.706
pha-0.682
Token may
Token ID743
Feature activation+3.63e-01

Pos logit contributions
+0.290
joy+0.286
ˈ+0.285
 Twain+0.281
TPPStreamerBot+0.279
Neg logit contributions
alian-0.247
 rob-0.229
cade-0.228
 harms-0.225
pha-0.217
Token not
Token ID407
Feature activation+5.74e-01

Pos logit contributions
alian+0.222
 rob+0.209
 harms+0.208
cade+0.205
pha+0.196
Neg logit contributions
-0.282
ˈ-0.270
joy-0.270
 Twain-0.268
TPPStreamerBot-0.266
Token agree
Token ID4236
Feature activation-3.02e+00

Pos logit contributions
alian+0.362
 rob+0.341
 harms+0.340
cade+0.336
pha+0.321
Neg logit contributions
-0.436
joy-0.416
ˈ-0.416
 Twain-0.413
TPPStreamerBot-0.410
Token with
Token ID351
Feature activation-4.66e-01

Pos logit contributions
+2.163
 Twain+2.068
joy+2.064
ˈ+2.059
TPPStreamerBot+2.034
Neg logit contributions
alian-1.998
 rob-1.890
 harms-1.883
cade-1.868
pha-1.801
Token my
Token ID616
Feature activation+4.89e-01

Pos logit contributions
+0.333
ˈ+0.316
joy+0.316
 Twain+0.314
TPPStreamerBot+0.312
Neg logit contributions
alian-0.316
 rob-0.300
 harms-0.299
cade-0.295
pha-0.282
Token own
Token ID898
Feature activation+7.15e-02

Pos logit contributions
alian+0.346
 rob+0.330
 harms+0.330
cade+0.325
ao+0.311
Neg logit contributions
-0.334
ˈ-0.317
joy-0.316
 Twain-0.313
TPPStreamerBot-0.311
Token views
Token ID5009
Feature activation-3.48e-01

Pos logit contributions
alian+0.052
 rob+0.049
 harms+0.049
cade+0.049
pha+0.047
Neg logit contributions
-0.048
ˈ-0.045
joy-0.045
 Twain-0.045
TPPStreamerBot-0.044
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
+0.281
ˈ+0.269
joy+0.269
 Twain+0.267
TPPStreamerBot+0.265
Neg logit contributions
alian-0.202
 rob-0.189
 harms-0.189
cade-0.186
pha-0.177
Token finally
Token ID3443
Feature activation-1.85e+00

Pos logit contributions
+0.036
joy+0.034
ˈ+0.034
 Twain+0.034
TPPStreamerBot+0.034
Neg logit contributions
alian-0.029
 rob-0.028
 harms-0.027
cade-0.027
pha-0.026
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
+1.449
joy+1.403
 Twain+1.394
ˈ+1.388
TPPStreamerBot+1.365
Neg logit contributions
alian-1.098
 harms-1.031
cade-1.017
 rob-1.017
pha-0.967
Token please
Token ID3387
Feature activation-1.67e+00

Pos logit contributions
+0.794
joy+0.763
ˈ+0.759
 Twain+0.759
TPPStreamerBot+0.748
Neg logit contributions
alian-0.683
 harms-0.643
 rob-0.641
cade-0.635
pha-0.606
Token have
Token ID423
Feature activation-1.29e+00

Pos logit contributions
+1.092
joy+1.042
ˈ+1.041
 Twain+1.034
TPPStreamerBot+1.017
Neg logit contributions
alian-1.220
 harms-1.161
 rob-1.151
cade-1.149
pha-1.107
Token a
Token ID257
Feature activation-9.90e-01

Pos logit contributions
+0.902
joy+0.863
ˈ+0.858
 Twain+0.857
TPPStreamerBot+0.844
Neg logit contributions
alian-0.892
 rob-0.845
 harms-0.844
cade-0.836
pha-0.800
Token look
Token ID804
Feature activation-3.03e+00

Pos logit contributions
+0.643
joy+0.611
ˈ+0.608
 Twain+0.606
TPPStreamerBot+0.599
Neg logit contributions
alian-0.732
 harms-0.695
 rob-0.694
cade-0.687
pha-0.660
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
+1.951
joy+1.895
ˈ+1.861
 Twain+1.860
TPPStreamerBot+1.800
Neg logit contributions
alian-2.202
 harms-2.103
 rob-2.095
cade-2.087
pha-1.991
Token the
Token ID262
Feature activation-5.94e-01

Pos logit contributions
+0.744
joy+0.716
 Twain+0.714
ˈ+0.713
TPPStreamerBot+0.699
Neg logit contributions
alian-0.648
 harms-0.610
 rob-0.607
cade-0.601
pha-0.573
Token new
Token ID649
Feature activation-5.90e-01

Pos logit contributions
+0.431
joy+0.412
ˈ+0.411
 Twain+0.410
TPPStreamerBot+0.404
Neg logit contributions
alian-0.393
 harms-0.371
 rob-0.370
cade-0.365
pha-0.349
Token.
Token ID764
Feature activation-1.06e+00

Pos logit contributions
+0.459
joy+0.441
ˈ+0.440
 Twain+0.439
TPPStreamerBot+0.433
Neg logit contributions
alian-0.359
 harms-0.336
 rob-0.335
cade-0.329
pha-0.314
Token Released
Token ID28728
Feature activation+6.96e-01

Pos logit contributions
+0.845
joy+0.814
ˈ+0.812
 Twain+0.811
TPPStreamerBot+0.800
Neg logit contributions
alian-0.625
 harms-0.588
 rob-0.586
cade-0.577
pha-0.546
Token today
Token ID1909
Feature activation+7.70e-01

Pos logit contributions
alian+0.172
 rob+0.161
 harms+0.161
cade+0.158
pha+0.150
Neg logit contributions
-0.258
joy-0.247
ˈ-0.247
 Twain-0.245
TPPStreamerBot-0.244
Token!
Token ID0
Feature activation-2.89e-01

Pos logit contributions
alian+0.440
 rob+0.412
 harms+0.410
cade+0.401
pha+0.382
Neg logit contributions
-0.635
ˈ-0.605
joy-0.603
 Twain-0.601
TPPStreamerBot-0.599
Token
Token ID198
Feature activation-6.85e-01

Pos logit contributions
+0.201
ˈ+0.191
joy+0.191
 Twain+0.190
TPPStreamerBot+0.188
Neg logit contributions
alian-0.201
 rob-0.190
 harms-0.190
cade-0.188
pha-0.180
Token
Token ID198
Feature activation-6.97e-01

Pos logit contributions
+0.512
ˈ+0.481
joy+0.481
 Twain+0.480
TPPStreamerBot+0.477
Neg logit contributions
alian-0.446
 rob-0.423
 harms-0.420
cade-0.416
pha-0.397
TokenChe
Token ID7376
Feature activation-1.98e+00

Pos logit contributions
+0.475
ˈ+0.450
joy+0.449
 Twain+0.447
TPPStreamerBot+0.443
Neg logit contributions
alian-0.495
 rob-0.470
 harms-0.468
cade-0.463
pha-0.445
Tokeners
Token ID364
Feature activation-3.33e+00

Pos logit contributions
+1.177
joy+1.121
ˈ+1.115
 Twain+1.104
TPPStreamerBot+1.095
Neg logit contributions
alian-1.559
 harms-1.487
 rob-1.485
cade-1.463
pha-1.412
Token to
Token ID284
Feature activation-7.72e-01

Pos logit contributions
+2.628
joy+2.569
 Twain+2.534
ˈ+2.533
TPPStreamerBot+2.474
Neg logit contributions
alian-1.933
 harms-1.813
cade-1.789
 rob-1.784
pha-1.713
Token our
Token ID674
Feature activation-6.73e-01

Pos logit contributions
+0.550
joy+0.523
ˈ+0.523
 Twain+0.520
TPPStreamerBot+0.515
Neg logit contributions
alian-0.523
 rob-0.495
 harms-0.495
cade-0.488
pha-0.468
Token sponsors
Token ID18073
Feature activation+1.64e+00

Pos logit contributions
+0.485
joy+0.461
ˈ+0.461
 Twain+0.458
TPPStreamerBot+0.455
Neg logit contributions
alian-0.451
 rob-0.426
 harms-0.425
cade-0.420
pha-0.402
Token,
Token ID11
Feature activation-7.31e-01

Pos logit contributions
alian+0.894
 rob+0.836
 harms+0.830
cade+0.817
pha+0.774
Neg logit contributions
-1.388
ˈ-1.330
joy-1.327
 Twain-1.319
TPPStreamerBot-1.317
Token like
Token ID588
Feature activation+3.08e-01

Pos logit contributions
+0.531
joy+0.506
ˈ+0.506
 Twain+0.503
TPPStreamerBot+0.498
Neg logit contributions
alian-0.485
 rob-0.458
 harms-0.458
cade-0.452
pha-0.433
Token
Token ID198
Feature activation+4.97e-02

Pos logit contributions
alian+0.182
 rob+0.173
 harms+0.171
cade+0.170
ao+0.162
Neg logit contributions
-0.220
ˈ-0.204
 Twain-0.204
joy-0.204
TPPStreamerBot-0.203
TokenAnd
Token ID1870
Feature activation+2.84e-01

Pos logit contributions
alian+0.032
 rob+0.030
cade+0.030
 harms+0.030
ao+0.029
Neg logit contributions
-0.037
ˈ-0.035
 Twain-0.035
joy-0.035
TPPStreamerBot-0.034
Token that
Token ID326
Feature activation-1.10e+00

Pos logit contributions
alian+0.174
 rob+0.165
 harms+0.164
cade+0.161
pha+0.153
Neg logit contributions
-0.223
ˈ-0.212
joy-0.211
TPPStreamerBot-0.209
 Twain-0.208
Token's
Token ID338
Feature activation-1.49e+00

Pos logit contributions
+0.959
joy+0.921
ˈ+0.920
 Twain+0.916
TPPStreamerBot+0.910
Neg logit contributions
alian-0.576
 rob-0.535
 harms-0.534
cade-0.526
pha-0.497
Token the
Token ID262
Feature activation-9.92e-01

Pos logit contributions
+1.102
joy+1.051
ˈ+1.050
 Twain+1.046
TPPStreamerBot+1.037
Neg logit contributions
alian-0.961
 rob-0.906
 harms-0.904
cade-0.893
pha-0.855
Token problem
Token ID1917
Feature activation-2.64e+00

Pos logit contributions
+0.709
ˈ+0.672
joy+0.671
 Twain+0.665
TPPStreamerBot+0.662
Neg logit contributions
alian-0.672
 rob-0.640
 harms-0.638
cade-0.628
pha-0.601
Token.
Token ID13
Feature activation-1.94e-02

Pos logit contributions
+2.060
 Twain+2.005
joy+1.992
ˈ+1.960
TPPStreamerBot+1.955
Neg logit contributions
alian-1.584
 rob-1.472
 harms-1.471
cade-1.454
pha-1.393
Token Clinton
Token ID2605
Feature activation-2.18e-01

Pos logit contributions
+0.015
ˈ+0.014
joy+0.014
TPPStreamerBot+0.014
 Twain+0.013
Neg logit contributions
alian-0.013
 rob-0.012
 harms-0.012
cade-0.012
pha-0.011
Token
Token ID960
Feature activation-4.95e-01

Pos logit contributions
+0.182
ˈ+0.174
joy+0.174
 Twain+0.173
TPPStreamerBot+0.172
Neg logit contributions
alian-0.122
 rob-0.114
 harms-0.114
cade-0.112
pha-0.106
Tokenand
Token ID392
Feature activation+5.91e-01

Pos logit contributions
+0.356
ˈ+0.338
joy+0.338
 Twain+0.336
TPPStreamerBot+0.333
Neg logit contributions
alian-0.333
 rob-0.315
 harms-0.315
cade-0.311
pha-0.298
Token most
Token ID749
Feature activation+4.23e-01

Pos logit contributions
alian+0.389
 rob+0.372
 harms+0.369
cade+0.364
ao+0.347
Neg logit contributions
-0.436
ˈ-0.412
joy-0.409
TPPStreamerBot-0.406
 Twain-0.403
Token
Token ID198
Feature activation+3.28e-01

Pos logit contributions
alian+0.315
 rob+0.301
 harms+0.297
cade+0.295
kai+0.281
Neg logit contributions
-0.385
ˈ-0.357
joy-0.356
 Twain-0.356
TPPStreamerBot-0.355
TokenPHOTOS
Token ID42709
Feature activation+1.79e-01

Pos logit contributions
alian+0.211
 rob+0.199
 harms+0.198
cade+0.196
pha+0.187
Neg logit contributions
-0.245
ˈ-0.233
joy-0.233
 Twain-0.232
TPPStreamerBot-0.230
Token:
Token ID25
Feature activation-8.07e-01

Pos logit contributions
alian+0.105
 rob+0.099
 harms+0.099
cade+0.097
pha+0.092
Neg logit contributions
-0.144
joy-0.137
ˈ-0.137
 Twain-0.137
TPPStreamerBot-0.136
Token Top
Token ID5849
Feature activation+4.88e-02

Pos logit contributions
+0.577
joy+0.554
 Twain+0.554
ˈ+0.552
TPPStreamerBot+0.540
Neg logit contributions
alian-0.541
 harms-0.511
 rob-0.510
cade-0.503
pha-0.482
Token Gr
Token ID1902
Feature activation-1.35e+00

Pos logit contributions
alian+0.036
 rob+0.034
 harms+0.034
cade+0.034
pha+0.033
Neg logit contributions
-0.032
joy-0.030
ˈ-0.030
 Twain-0.030
TPPStreamerBot-0.029
Tokenads
Token ID5643
Feature activation-2.76e+00

Pos logit contributions
+1.041
joy+1.023
ˈ+1.015
 Twain+1.000
TPPStreamerBot+0.990
Neg logit contributions
alian-0.804
 harms-0.755
 rob-0.754
cade-0.733
pha-0.710
Token of
Token ID286
Feature activation-1.05e+00

Pos logit contributions
+2.017
joy+1.992
 Twain+1.992
ˈ+1.971
TPPStreamerBot+1.915
Neg logit contributions
alian-1.746
 harms-1.646
 rob-1.621
cade-1.612
pha-1.561
Token YouTube
Token ID7444
Feature activation+1.22e+00

Pos logit contributions
+0.753
 Twain+0.730
joy+0.728
ˈ+0.728
TPPStreamerBot+0.706
Neg logit contributions
alian-0.702
 harms-0.664
 rob-0.661
cade-0.646
pha-0.625
Token U
Token ID471
Feature activation-9.19e-01

Pos logit contributions
alian+0.629
 rob+0.584
 harms+0.580
cade+0.573
pha+0.539
Neg logit contributions
-1.081
ˈ-1.031
joy-1.029
 Twain-1.024
TPPStreamerBot-1.022
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
+0.736
joy+0.709
ˈ+0.706
 Twain+0.696
TPPStreamerBot+0.691
Neg logit contributions
alian-0.538
 harms-0.507
 rob-0.503
cade-0.497
kai-0.468
Token
Token ID198
Feature activation-1.90e-01

Pos logit contributions
+0.317
ˈ+0.298
joy+0.297
 Twain+0.296
TPPStreamerBot+0.295
Neg logit contributions
alian-0.274
 rob-0.260
 harms-0.258
cade-0.256
pha-0.244