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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to guidelines or procedural instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alles
    -0.16
    obus
    -0.16
    pone
    -0.15
    .digest
    -0.15
    ÙħÛĮÙĦ
    -0.15
     Fowler
    -0.14
     Hava
    -0.14
    .removeChild
    -0.14
    _Function
    -0.14
    ÏĦικ
    -0.13
    POSITIVE LOGITS
    leton
    0.15
    stad
    0.15
    usch
    0.14
    illez
    0.14
    ModelProperty
    0.14
    á»ij
    0.14
    aget
    0.14
    TINGS
    0.14
    .adv
    0.14
    aven
    0.13
    Act Density 0.026%

    No Known Activations