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

    Neuronpedia

    INDEX
    Explanations

    references to digital files or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.17
    2:0.07
    3:0.05
    4:0.04
    5:0.14
    6:0.09
    7:0.05
    8:0.07
    9:0.07
    10:0.04
    11:0.04
    Negative Logits
     volunt
    -1.80
    mort
    -1.71
    venants
    -1.67
    weak
    -1.66
    untary
    -1.61
    rots
    -1.61
    errors
    -1.58
    mist
    -1.58
    compan
    -1.56
    reed
    -1.54
    POSITIVE LOGITS
    Filename
    1.66
     Gothic
    1.62
     scalable
    1.60
    /#
    1.59
    -$
    1.56
    �
    1.53
     EDIT
    1.53
    デ
    1.50
     Defin
    1.48
     WB
    1.48
    Act Density 0.000%

    No Known Activations