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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.12
    2:0.10
    3:0.04
    4:0.04
    5:0.11
    6:0.05
    7:0.04
    8:0.11
    9:0.08
    10:0.05
    11:0.09
    Negative Logits
    gt
    -2.32
    minimum
    -1.91
    gd
    -1.84
    major
    -1.77
    orc
    -1.75
    entity
    -1.74
    Count
    -1.71
    bah
    -1.69
    quad
    -1.66
    intend
    -1.65
    POSITIVE LOGITS
     VIDE
    1.65
     UNCLASSIFIED
    1.63
     remix
    1.55
     SPL
    1.53
     lex
    1.53
     References
    1.52
     helic
    1.47
     propag
    1.46
     VIDEO
    1.45
     assay
    1.45
    Act Density 0.000%

    No Known Activations