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

    Neuronpedia

    INDEX
    Explanations

    references to technical procedures and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.71
    MessageOf
    -0.61
    idance
    -0.53
    __*/
    -0.53
    stadt
    -0.50
     يتيمه
    -0.50
     Conventional
    -0.50
    ]();
    -0.48
     abbandon
    -0.48
    ilibr
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.47
    UPI
    0.46
    ague
    0.46
    MMV
    0.45
    iläum
    0.45
    ANDS
    0.45
    velmente
    0.44
    roids
    0.44
    ئات
    0.44
    APORE
    0.44
    Act Density 1.529%

    No Known Activations