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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens containing the period character from tokens that follow any character

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.17
    2:0.05
    3:0.04
    4:0.08
    5:0.42
    6:0.04
    7:0.06
    Negative Logits
     AssemblyTitle
    -0.59
    ftrag
    -0.56
    RectangleBorder
    -0.54
    getColumnIndex
    -0.52
    harusnya
    -0.52
    eeeeee
    -0.52
    CCCC
    -0.50
    FFIX
    -0.49
    xygen
    -0.48
    Fantas
    -0.48
    POSITIVE LOGITS
    multer
    0.59
    LookAnd
    0.53
    ์ตูน
    0.49
    Kag
    0.46
     समीक्षक
    0.46
    maßen
    0.45
     Trails
    0.45
    ?”
    0.45
     sauvages
    0.45
     translateY
    0.45
    Act Density 0.027%

    No Known Activations