INDEX
Explanations
blood-related imagery and expressions
terms related to bleeding and cuts
New Auto-Interp
Negative Logits
å§«
-0.87
wcsstore
-0.84
BOOK
-0.80
aterasu
-0.79
Policy
-0.76
ECH
-0.76
ernel
-0.73
entric
-0.72
ENTION
-0.72
ancouver
-0.71
POSITIVE LOGITS
bleed
0.97
bleeding
0.95
hemorrh
0.87
thro
0.81
wounds
0.78
transf
0.77
prof
0.76
blood
0.73
drop
0.72
©¶æ¥µ
0.72
Activations Density 0.018%