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

    Neuronpedia

    INDEX
    Explanations

    references to classifications and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _compat
    -0.14
     κοι
    -0.13
    ILINE
    -0.13
     kabil
    -0.13
    ",-
    -0.13
    ľ
    -0.13
     pÅĻÃŃliÅ¡
    -0.12
     discrepan
    -0.12
    ê±°ëŀĺ
    -0.12
    -к
    -0.12
    POSITIVE LOGITS
    allon
    0.18
    -fontawesome
    0.15
    isco
    0.15
     Schro
    0.15
    inth
    0.14
    hani
    0.14
    εÏĨ
    0.14
    glyph
    0.14
    anton
    0.14
    aes
    0.13
    Act Density 0.056%

    No Known Activations