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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushima
    -0.17
    æĹıèĩªæ²»
    -0.16
    uly
    -0.16
    uesta
    -0.15
    azzi
    -0.14
    anga
    -0.14
    gal
    -0.14
    .getElementsBy
    -0.14
     gala
    -0.14
    yla
    -0.14
    POSITIVE LOGITS
    ｡
    0.16
    oy
    0.15
    bing
    0.14
     obce
    0.14
     bÃŃ
    0.14
    bone
    0.13
    olidays
    0.13
    uteur
    0.13
    _listen
    0.13
     ker
    0.13
    Act Density 0.030%

    No Known Activations