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

    Neuronpedia

    INDEX
    Explanations

    references to repetition or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.16
    3:0.05
    4:0.14
    5:0.03
    6:0.16
    7:0.20
    8:0.06
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
    quartered
    -1.92
     Cosponsors
    -1.40
    weight
    -1.36
    arning
    -1.32
    elected
    -1.31
     arra
    -1.28
    Compare
    -1.28
     WATCHED
    -1.26
     condem
    -1.24
    adelphia
    -1.20
    POSITIVE LOGITS
     goodies
    1.50
    bish
    1.44
    uid
    1.43
     originals
    1.37
     goodness
    1.36
    nel
    1.35
    rio
    1.35
     clutter
    1.20
    lik
    1.18
    arious
    1.18
    Act Density 0.006%

    No Known Activations