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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols indicating non-standard or special formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¯
    -0.20
     âĢ¯
    -0.20
     âĤ¹
    -0.15
     Levin
    -0.15
    -0.15
    \/
    -0.15
     âĢķ
    -0.15
    resse
    -0.14
     âĵĺ
    -0.14
     \/
    -0.14
    POSITIVE LOGITS
    »
    0.20
    ³
    0.17
    ¿ÃĤ
    0.16
    »↵
    0.16
     »
    0.15
    _,,
    0.15
    µ
    0.15
    ãĥ
    0.15
    »↵↵
    0.15
    ÃĹ
    0.15
    Act Density 0.003%

    No Known Activations