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

    Neuronpedia

    INDEX
    Explanations

    references to academic or organizational titles and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dio
    -0.15
    ж
    -0.15
    BITS
    -0.14
    _RS
    -0.14
    indi
    -0.14
     Ori
    -0.14
    ä»ĺ
    -0.13
     Cooke
    -0.13
    ácil
    -0.13
     Gab
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.18
    uma
    0.17
    .Formatter
    0.15
    Deadline
    0.15
    oftware
    0.15
    xbb
    0.15
    Magnitude
    0.14
    oteric
    0.14
    ACL
    0.14
    æı
    0.14
    Act Density 0.413%

    No Known Activations