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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a complete or absolute action or decision

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hao
    -0.69
    nan
    -0.67
    yers
    -0.67
     Fulton
    -0.64
    hma
    -0.64
     Julio
    -0.62
    appa
    -0.61
     ANGEL
    -0.60
    claimed
    -0.58
    penter
    -0.58
    POSITIVE LOGITS
     disarm
    0.76
     guiActiveUn
    0.72
     Unlimited
    0.71
     altogether
    0.70
    BuyableInstoreAndOnline
    0.70
    loo
    0.70
    MpServer
    0.70
    çĶ°
    0.67
     ç¥ŀ
    0.65
    ADRA
    0.65
    Act Density 0.003%

    No Known Activations