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

    Neuronpedia

    INDEX
    Explanations

    terms related to social class distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.03
    3:0.05
    4:0.07
    5:0.04
    6:0.04
    7:0.07
    8:0.03
    9:0.34
    10:0.04
    11:0.16
    Negative Logits
     VIDEOS
    -2.59
     Announce
    -2.50
    igate
    -2.48
     giveaway
    -2.34
     vomit
    -2.20
     kiss
    -2.19
     apologize
    -2.19
     apologise
    -2.18
     sneak
    -2.17
     accompany
    -2.14
    POSITIVE LOGITS
    iors
    3.04
     incomes
    2.58
    ippers
    2.51
    types
    2.46
    average
    2.39
    vals
    2.37
     generations
    2.31
     populations
    2.29
    oters
    2.29
    ustomed
    2.27
    Act Density 0.006%

    No Known Activations