INDEX
Explanations
phrases related to the ocean
references to the ocean
New Auto-Interp
Negative Logits
Reloaded
-0.87
TI
-0.81
TOP
-0.76
POS
-0.76
nder
-0.73
DIR
-0.73
NER
-0.70
UGC
-0.69
MENTS
-0.68
======
-0.67
POSITIVE LOGITS
basin
1.02
ographer
1.00
ocean
0.98
front
0.93
liner
0.92
Ocean
0.92
circulation
0.88
oceans
0.86
ographers
0.85
waters
0.83
Activations Density 0.008%