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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions and their related formats within technical or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.95
     kasarigan
    -0.93
     Efq
    -0.92
     Normdatei
    -0.88
    IUrlHelper
    -0.85
     itſelf
    -0.84
    الحياه
    -0.83
     الاطلاع
    -0.83
     Anſ
    -0.83
     podjela
    -0.83
    POSITIVE LOGITS
    蹤
    0.45
     sc
    0.42
     (
    0.41
     mach
    0.41
     A
    0.40
     SC
    0.39
     I
    0.39
    .
    0.39
     con
    0.39
     up
    0.39
    Act Density 0.754%

    No Known Activations