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

    Neuronpedia

    INDEX
    Explanations

    references to escape characters in programming or text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    escape sequences and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     topper
    -0.45
     Leto
    -0.41
     Freestyle
    -0.40
    ########.
    -0.39
     Genome
    -0.39
     ATOM
    -0.39
     Langu
    -0.39
    Muk
    -0.39
    ^(@
    -0.38
     Chum
    -0.38
    POSITIVE LOGITS
    UrlResolution
    0.73
     escaped
    0.68
     escape
    0.68
     escaping
    0.67
     ویکی‌پدی
    0.65
     escapes
    0.60
     intptr
    0.58
     Италијани
    0.57
    escaping
    0.57
    findpost
    0.56
    Act Density 0.046%

    No Known Activations