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

    Neuronpedia

    INDEX
    Explanations

    numeric values or codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.60
    iversary
    -0.60
     Lisa
    -0.58
    Picture
    -0.57
    natureconservancy
    -0.57
    ORGE
    -0.56
    Lisa
    -0.56
    Nar
    -0.56
    osaurus
    -0.55
    mie
    -0.55
    POSITIVE LOGITS
     levied
    0.64
     abound
    0.64
     etc
    0.63
     otherwise
    0.63
    volent
    0.62
    Ĥİ
    0.61
     clauses
    0.60
     alike
    0.60
    ]."
    0.60
     advers
    0.58
    Act Density 1.668%

    No Known Activations