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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.57
    Ùĩ
    -0.30
    in
    -0.22
    sian
    -0.22
    sburg
    -0.21
    d
    -0.21
    sik
    -0.20
    h
    -0.20
    à¸Ĺ
    -0.20
    ÏĤ
    -0.20
    POSITIVE LOGITS
    [
    0.15
    "
    0.15
    arat
    0.15
    Ïĥμα
    0.15
     """.
    0.14
    icare
    0.14
    æĢ§çļĦ
    0.14
    -dat
    0.14
    vron
    0.13
    ""↵
    0.13
    Act Density 0.201%

    No Known Activations