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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĤ
    -0.15
    afil
    -0.14
     â
    -0.14
    ongan
    -0.13
    azon
    -0.13
    ummings
    -0.13
    chu
    -0.13
    ogle
    -0.12
    ensi
    -0.12
    oso
    -0.12
    POSITIVE LOGITS
     mastur
    0.12
    estli
    0.12
    ONTAL
    0.12
     CreateMap
    0.12
     há»Ĺn
    0.12
    NSNotification
    0.11
     jenter
    0.11
    istrovstvÃŃ
    0.11
    eyle
    0.11
     ìĹŃìĭľ
    0.11
    Act Density 0.324%

    No Known Activations