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

    Neuronpedia

    INDEX
    Explanations

    terms related to roles, identifiers, and entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rah
    -0.14
    erville
    -0.14
    ãĤ¹ãĤ¿ãĥ¼
    -0.14
    rish
    -0.14
    afari
    -0.14
    isz
    -0.14
    ubber
    -0.14
    abad
    -0.14
    arrant
    -0.14
    rahim
    -0.14
    POSITIVE LOGITS
    ilar
    0.15
    ected
    0.15
    ì¹Ļ
    0.14
    á»ī
    0.14
    rippling
    0.14
    ogg
    0.14
    اÙĨا
    0.14
    aeda
    0.14
    ive
    0.14
    erti
    0.13
    Act Density 0.010%

    No Known Activations