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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal preferences and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tras
    -0.15
    wang
    -0.15
    ERIC
    -0.14
    ependency
    -0.14
    ARB
    -0.13
    ameda
    -0.13
    imiz
    -0.13
    oro
    -0.13
    nore
    -0.13
    ppo
    -0.13
    POSITIVE LOGITS
    ayne
    0.16
    KeyDown
    0.16
    attery
    0.16
    elon
    0.16
    μι
    0.15
    ety
    0.15
    _MINOR
    0.14
    ainted
    0.14
    cház
    0.14
    embr
    0.14
    Act Density 0.010%

    No Known Activations