INDEX
Explanations
the word "go" in the text
New Auto-Interp
Head Attr Weights
0:0.09
1:0.07
2:0.07
3:0.09
4:0.08
5:0.08
6:0.07
7:0.09
8:0.07
9:0.10
10:0.07
11:0.08
Negative Logits
hesda
-2.24
Activ
-2.09
orporated
-2.05
feel
-2.04
ifferent
-2.01
elta
-2.01
atories
-1.88
LOAD
-1.86
mosp
-1.85
abba
-1.85
POSITIVE LOGITS
Archdemon
2.30
peninsula
2.11
detainee
1.84
plet
1.84
answ
1.76
probe
1.76
enclave
1.75
vati
1.74
nation
1.73
lyak
1.73
Activations Density 0.000%