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

    Neuronpedia

    INDEX
    Explanations

    terms associated with harm, damage, or negative consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.15
    .NewLine
    -0.15
    iveau
    -0.15
    ells
    -0.14
    PIO
    -0.14
     Äįast
    -0.14
    tober
    -0.14
    utch
    -0.14
    yah
    -0.14
    anj
    -0.14
    POSITIVE LOGITS
    asset
    0.17
    еÑĨÑĮ
    0.15
    jec
    0.14
    ngör
    0.14
    olume
    0.14
    obot
    0.13
    .sul
    0.13
    assets
    0.13
    SSERT
    0.13
    adan
    0.13
    Act Density 0.016%

    No Known Activations