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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or URLs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.07
    4:0.10
    5:0.02
    6:0.06
    7:0.21
    8:0.02
    9:0.04
    10:0.18
    11:0.08
    Negative Logits
    perm
    -1.92
    pex
    -1.77
    ciation
    -1.55
    FTWARE
    -1.54
    elist
    -1.52
    cific
    -1.50
    rators
    -1.46
    thood
    -1.45
    utor
    -1.41
    ptions
    -1.40
    POSITIVE LOGITS
     spotlight
    1.51
     Bust
    1.46
    Topic
    1.33
     charism
    1.31
    黒
    1.31
    Iss
    1.29
     boobs
    1.29
     Bloody
    1.28
     Benedict
    1.28
     Rachel
    1.28
    Act Density 0.001%

    No Known Activations