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

    Neuronpedia

    INDEX
    Explanations

    keywords related to diversity and variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.04
    4:0.09
    5:0.03
    6:0.46
    7:0.06
    8:0.02
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    mobi
    -1.39
    TEXTURE
    -1.30
    earch
    -1.30
    CW
    -1.25
    PDATE
    -1.23
     exting
    -1.21
     retake
    -1.20
    ゴ
    -1.20
    isSpecialOrderable
    -1.20
    amo
    -1.20
    POSITIVE LOGITS
    sheets
    1.44
    sectional
    1.35
    ths
    1.34
    herer
    1.27
    gypt
    1.26
    flow
    1.25
    intestinal
    1.25
    grain
    1.25
    genre
    1.25
    ties
    1.25
    Act Density 0.006%

    No Known Activations