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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantity or amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.11
    2:0.08
    3:0.06
    4:0.08
    5:0.09
    6:0.08
    7:0.09
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     prelim
    -3.17
     Recon
    -3.08
     Orche
    -3.04
    ゴン
    -2.84
    quished
    -2.82
     Puppet
    -2.77
     Vaj
    -2.72
     Donation
    -2.71
     prepar
    -2.69
     Orchestra
    -2.67
    POSITIVE LOGITS
    GB
    3.07
    bed
    2.98
    erb
    2.75
    laws
    2.73
    sworth
    2.67
    gary
    2.65
    Lex
    2.63
    east
    2.56
    WD
    2.54
    icut
    2.54
    Act Density 0.000%

    No Known Activations