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

    Neuronpedia

    INDEX
    Explanations

    words associated with professions, roles, and identify artists or performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.16
    ilee
    -0.15
    leigh
    -0.15
    atron
    -0.14
    elia
    -0.14
    quel
    -0.14
    plex
    -0.14
    REFERRED
    -0.13
    mür
    -0.13
    Ã
    -0.13
    POSITIVE LOGITS
     Jr
    0.22
    III
    0.18
     III
    0.18
    ioned
    0.15
    II
    0.15
    orgot
    0.14
    ëĭĪëĭ¤
    0.14
    åįļ士
    0.14
     Bul
    0.14
    vala
    0.14
    Act Density 0.189%

    No Known Activations