INDEX
    Explanations

    conversational phrases or cues

    instances of the word "conversation."

    New Auto-Interp
    Negative Logits
    emale
    -0.77
    rule
    -0.71
    azy
    -0.70
    ramid
    -0.68
    cheat
    -0.67
    elin
    -0.67
    rob
    -0.67
    redit
    -0.66
    GPU
    -0.65
    arah
    -0.65
    POSITIVE LOGITS
     conversation
    1.14
     conversations
    1.12
     banter
    0.99
    ogue
    0.93
     Conversation
    0.91
     Convers
    0.88
     dialogue
    0.86
     chatter
    0.86
     invitations
    0.83
     discussions
    0.83
    Act Density 0.018%

    No Known Activations