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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate functions, categories, or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addon
    -0.17
    anton
    -0.16
    uida
    -0.15
    ongan
    -0.15
    liga
    -0.15
    ese
    -0.15
    hani
    -0.14
    :disable
    -0.14
    opher
    -0.14
    oods
    -0.14
    POSITIVE LOGITS
    344
    0.16
     unreachable
    0.15
     zdroj
    0.15
    ResponseStatus
    0.15
     Kaynak
    0.14
     backdrop
    0.14
    source
    0.14
    apı
    0.14
    pires
    0.14
    semb
    0.14
    Act Density 0.312%

    No Known Activations