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

    Neuronpedia

    INDEX
    Explanations

    geographic locations and cosmic events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.83
    rooms
    -0.81
    oway
    -0.78
    bos
    -0.77
    gage
    -0.77
    away
    -0.77
    eral
    -0.76
    abet
    -0.76
    room
    -0.75
    fare
    -0.74
    POSITIVE LOGITS
    halla
    0.67
     EDITION
    0.63
     Jarrett
    0.59
     Herz
    0.59
     msec
    0.58
     APR
    0.58
     hots
    0.58
     Ples
    0.57
     flare
    0.54
     ATK
    0.54
    Act Density 3.639%

    No Known Activations