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

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with authority or professional positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.09
    5:0.03
    6:0.42
    7:0.06
    8:0.03
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    ashtra
    -1.92
    NetMessage
    -1.79
    tten
    -1.49
    ibaba
    -1.44
    staking
    -1.41
     Archdemon
    -1.39
     Canaver
    -1.38
    hett
    -1.37
    allery
    -1.34
    wagen
    -1.33
    POSITIVE LOGITS
    ellectual
    1.46
     Irwin
    1.26
     Sierra
    1.21
     Text
    1.21
    rette
    1.17
    UTF
    1.17
    Charges
    1.17
    ress
    1.15
     Intellectual
    1.15
    letters
    1.14
    Act Density 0.006%

    No Known Activations