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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate alternatives or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sville
    -0.15
    lik
    -0.15
    ãĤ¡
    -0.15
    itsu
    -0.15
     Heller
    -0.14
    atos
    -0.14
    ubl
    -0.14
    .TabStop
    -0.14
    hurst
    -0.14
    oa
    -0.14
    POSITIVE LOGITS
    OwnProperty
    0.14
    gate
    0.14
    uler
    0.14
    elerden
    0.14
     UIL
    0.14
    ewise
    0.14
    archs
    0.13
    ippers
    0.13
     Ik
    0.13
     ÑģÑħод
    0.13
    Act Density 0.037%

    No Known Activations