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

    Neuronpedia

    INDEX
    Explanations

    certain word structures or patterns, especially those resembling multi-syllabic forms or suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.18
    2:0.08
    3:0.04
    4:0.05
    5:0.15
    6:0.03
    7:0.04
    8:0.06
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
    bably
    -2.22
    TABLE
    -1.82
    WH
    -1.66
    HOW
    -1.65
    WAR
    -1.65
    TOP
    -1.65
    TR
    -1.62
    BUG
    -1.62
    CR
    -1.62
    CHAR
    -1.60
    POSITIVE LOGITS
     Herz
    1.65
    ainment
    1.54
     Norton
    1.47
     Sharon
    1.44
     drawer
    1.39
     Metall
    1.38
     Noir
    1.38
     Porn
    1.37
     ire
    1.35
     Security
    1.35
    Act Density 0.005%

    No Known Activations