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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of formal documentation or specific guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yo
    -0.16
     Consort
    -0.15
    witter
    -0.15
    ched
    -0.15
    ankan
    -0.15
    lover
    -0.14
    yl
    -0.14
    kového
    -0.13
    @protocol
    -0.13
    APSHOT
    -0.13
    POSITIVE LOGITS
    uder
    0.17
    omo
    0.15
    dere
    0.14
    nu
    0.14
    ücken
    0.14
    rus
    0.14
    azo
    0.14
    sak
    0.14
    illet
    0.14
    orts
    0.13
    Act Density 4.641%

    No Known Activations