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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or statistical references in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.33
    1:0.04
    2:0.03
    3:0.07
    4:0.05
    5:0.12
    6:0.05
    7:0.02
    8:0.15
    9:0.06
    10:0.02
    11:0.02
    Negative Logits
     deserts
    -1.81
    livion
    -1.69
     Ruin
    -1.66
     Default
    -1.60
    ocalypse
    -1.58
     scams
    -1.58
    vertising
    -1.57
    azo
    -1.55
    adra
    -1.52
    Interstitial
    -1.52
    POSITIVE LOGITS
     adherents
    2.07
     delegates
    1.91
     gathered
    1.90
     authority
    1.85
     electors
    1.84
    ENTS
    1.81
     witnesses
    1.74
    scient
    1.73
    elf
    1.68
    武
    1.68
    Act Density 0.001%

    No Known Activations