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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.10
    3:0.06
    4:0.09
    5:0.07
    6:0.08
    7:0.11
    8:0.08
    9:0.07
    10:0.07
    11:0.09
    Negative Logits
     fret
    -1.62
     stray
    -1.62
    raised
    -1.58
    "},"
    -1.57
    lier
    -1.55
    vez
    -1.54
    uni
    -1.51
    ilipp
    -1.51
    cker
    -1.50
    ussy
    -1.48
    POSITIVE LOGITS
    ゴン
    1.68
     Maw
    1.68
     Starts
    1.66
    の�
    1.62
    �
    1.60
    �
    1.50
     Occupations
    1.49
    ESSION
    1.47
    上
    1.45
    ASY
    1.44
    Act Density 0.000%

    No Known Activations