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

    Neuronpedia

    INDEX
    Explanations

    text related to items or products

    oai_token-act-pair · gpt-3.5-turbo

    end-of-document markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsius
    -0.67
     entirety
    -0.63
     Qiao
    -0.62
    ¿½
    -0.61
    Ö¼
    -0.60
    aucas
    -0.60
     prol
    -0.59
    ividual
    -0.58
    haar
    -0.57
     qualitative
    -0.56
    POSITIVE LOGITS
     Buster
    0.59
     Galile
    0.58
    hoe
    0.58
    fortune
    0.57
     Mandal
    0.56
     MMO
    0.55
     Tycoon
    0.55
     ''
    0.54
    Neal
    0.53
    semble
    0.53
    Act Density 1.475%

    No Known Activations