INDEX
Explanations
phrases containing the word "King" as a common thematic element
references to the word "King."
New Auto-Interp
Negative Logits
TING
-0.82
ATIONAL
-0.71
Ö¼
-0.69
ted
-0.67
ters
-0.66
ATIONS
-0.66
REM
-0.65
uated
-0.65
ename
-0.64
eria
-0.63
POSITIVE LOGITS
pin
1.24
uin
1.20
pins
1.12
doms
1.04
dom
0.98
Kong
0.96
killer
0.94
fish
0.90
STON
0.90
Abdullah
0.90
Activations Density 0.040%