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

    Neuronpedia

    INDEX
    Explanations

    negative values represented in various contexts, possibly indicating ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayer
    -0.16
    _sdk
    -0.15
    rh
    -0.14
    egend
    -0.14
    á»iji
    -0.14
    hey
    -0.14
    upal
    -0.14
    .sdk
    -0.14
    irect
    -0.13
    _MISC
    -0.13
    POSITIVE LOGITS
    BuilderInterface
    0.15
    Independ
    0.15
    gba
    0.14
    nsic
    0.14
    zung
    0.14
    ê·
    0.14
     Enlight
    0.14
    mlin
    0.14
    entar
    0.14
    à¸ģà¸ķ
    0.13
    Act Density 0.002%

    No Known Activations