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

    Neuronpedia

    INDEX
    Explanations

    names of people and places, particularly in relation to scandals or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.03
    3:0.07
    4:0.03
    5:0.03
    6:0.07
    7:0.02
    8:0.03
    9:0.55
    10:0.03
    11:0.03
    Negative Logits
     Wald
    -3.33
     Chrom
    -3.22
    Clark
    -3.05
     uncon
    -3.01
     Booth
    -2.97
     Ups
    -2.93
     Bro
    -2.90
     Conway
    -2.90
    黒
    -2.87
     Gro
    -2.85
    POSITIVE LOGITS
    i
    5.53
    ici
    5.08
    iris
    5.03
    gi
    4.89
    igi
    4.75
    iji
    4.65
    ti
    4.65
    mi
    4.59
    isi
    4.58
    hi
    4.51
    Act Density 0.143%

    No Known Activations