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

    Neuronpedia

    INDEX
    Explanations

    cooking and baking utensils or tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.11
    3:0.11
    4:0.07
    5:0.05
    6:0.05
    7:0.14
    8:0.04
    9:0.04
    10:0.21
    11:0.08
    Negative Logits
    Sov
    -1.97
     compositions
    -1.54
     subsistence
    -1.50
     dresses
    -1.49
     repentance
    -1.45
     divest
    -1.45
     veget
    -1.44
     wholesale
    -1.44
     dress
    -1.43
     horm
    -1.43
    POSITIVE LOGITS
     "$:/
    1.86
    Adams
    1.58
     scanner
    1.54
    chet
    1.53
    Reader
    1.51
     EDITION
    1.46
    coni
    1.45
    ito
    1.45
     Reader
    1.44
     SC
    1.42
    Act Density 0.000%

    No Known Activations