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

    Neuronpedia

    INDEX
    Explanations

    frequency and quantity-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.08
    3:0.09
    4:0.11
    5:0.03
    6:0.35
    7:0.07
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    dinand
    -1.63
    eele
    -1.34
    amera
    -1.33
     neutrality
    -1.33
    olor
    -1.31
    aba
    -1.31
    ntil
    -1.30
    gemony
    -1.26
    roximately
    -1.25
    quartered
    -1.22
    POSITIVE LOGITS
     imaginable
    1.49
     increments
    1.44
     Bundy
    1.42
    physical
    1.31
    ctory
    1.28
    crop
    1.24
     conceivable
    1.23
    ean
    1.22
    sky
    1.20
    sites
    1.19
    Act Density 0.027%

    No Known Activations