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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angl
    -0.17
    ucz
    -0.16
    icas
    -0.16
    upo
    -0.15
    ÑĻ
    -0.14
    hoo
    -0.14
    uter
    -0.14
    ialis
    -0.14
    chter
    -0.14
     prostitut
    -0.14
    POSITIVE LOGITS
    net
    0.15
    thal
    0.14
    ضÛĮ
    0.13
    etty
    0.13
    باÙĨ
    0.13
    trap
    0.13
    Verse
    0.13
    بÛĮÙĨ
    0.13
    ÑĢой
    0.13
    spots
    0.13
    Act Density 0.058%

    No Known Activations