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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to codes or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.16
    REW
    -0.14
    "default
    -0.14
    aná
    -0.14
     sophistic
    -0.14
    aminer
    -0.14
    bilt
    -0.14
     Vict
    -0.14
     Mess
    -0.13
    SError
    -0.13
    POSITIVE LOGITS
    odes
    0.15
    ulaire
    0.13
    urr
    0.13
    odal
    0.13
    eyes
    0.13
    getattr
    0.13
    ool
    0.13
    arium
    0.13
    enu
    0.12
    лим
    0.12
    Act Density 0.006%

    No Known Activations