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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spit
    -0.57
    //</
    -0.52
    izan
    -0.51
     nền
    -0.51
    λλη
    -0.50
    __*/
    -0.48
    äule
    -0.47
    rat
    -0.47
    ruck
    -0.47
    dater
    -0.47
    POSITIVE LOGITS
     فريبيس
    1.25
    RenderAtEndOf
    1.05
    UnsafeEnabled
    0.84
    UserScript
    0.79
    WaitGroup
    0.78
    DoubleQuotes
    0.73
     Paglinawan
    0.72
     незавершена
    0.72
     CreateTagHelper
    0.71
    AddTagHelper
    0.71
    Act Density 0.006%

    No Known Activations