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

    Neuronpedia

    INDEX
    Explanations

    numeric values or mentions of time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amus
    -0.17
     Kirby
    -0.16
    ibel
    -0.15
    uman
    -0.14
     гÑĥб
    -0.14
    rift
    -0.14
    esse
    -0.14
    åĨĴ
    -0.14
     Geg
    -0.13
    ardy
    -0.13
    POSITIVE LOGITS
    fold
    0.17
    orra
    0.16
     Challenge
    0.15
    dni
    0.14
     Scre
    0.14
    ToOne
    0.14
    .extension
    0.14
     Austral
    0.14
    erras
    0.13
    æ³Ĭ
    0.13
    Act Density 0.122%

    No Known Activations