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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions and exclamatory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uml
    -0.16
    blink
    -0.15
    ovel
    -0.15
    ael
    -0.15
    undred
    -0.14
    zl
    -0.14
    νή
    -0.14
     zas
    -0.14
     enr
    -0.14
    ndl
    -0.13
    POSITIVE LOGITS
    izzo
    0.15
    untas
    0.15
    cot
    0.15
    idders
    0.14
    ÑĢоз
    0.14
    ainen
    0.14
    quires
    0.14
    ariat
    0.14
    _PWR
    0.14
     ãĢľ
    0.14
    Act Density 0.150%

    No Known Activations