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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GRES
    -0.18
    á»ģn
    -0.17
    asley
    -0.15
    ÑĢок
    -0.15
    createFrom
    -0.14
    SSERT
    -0.14
    Placement
    -0.14
     تÙĪس
    -0.14
    erno
    -0.14
    è¸
    -0.13
    POSITIVE LOGITS
     noexcept
    0.15
     bure
    0.15
    Gate
    0.14
     gate
    0.14
     Desk
    0.14
    ultz
    0.14
    ój
    0.14
    abis
    0.14
    ffe
    0.14
     Gate
    0.14
    Act Density 0.166%

    No Known Activations