INDEX
Explanations
locations and positions, specifically described with relation to people or events
locations and contextual references related to events or actions
New Auto-Interp
Negative Logits
}.
-0.81
$.
-0.73
};
-0.72
}}}
-0.72
%.
-0.71
},
-0.71
}}
-0.70
onga
-0.70
attRot
-0.69
.}
-0.69
POSITIVE LOGITS
intending
0.70
extensively
0.64
successfully
0.60
briefly
0.60
twice
0.59
expecting
0.59
yesterday
0.58
ldon
0.55
aback
0.55
imore
0.53
Activations Density 1.198%