Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    descriptions of experiences or moments in which someone is deeply engaged emotionally

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reserv
    -0.63
     Offline
    -0.60
    laus
    -0.59
     References
    -0.59
    ply
    -0.58
     premise
    -0.58
     Unlock
    -0.57
    being
    -0.57
     Teaching
    -0.57
     anticipating
    -0.57
    POSITIVE LOGITS
     trouble
    1.06
     fun
    0.94
     nightmares
    0.91
     conversations
    0.88
     intercourse
    0.84
     discussions
    0.83
     difficulty
    0.78
     difficulties
    0.77
     dinner
    0.76
     dealings
    0.75
    Act Density 0.073%

    No Known Activations