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

    Neuronpedia

    INDEX
    Explanations

    references to involvement in political, social, or community activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.00
    2:0.10
    3:0.06
    4:0.11
    5:0.03
    6:0.05
    7:0.35
    8:0.02
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
    iture
    -1.86
    items
    -1.77
    marked
    -1.63
    ishable
    -1.63
    pection
    -1.60
    pict
    -1.59
    iencies
    -1.58
    pex
    -1.52
    evidence
    -1.51
    phe
    -1.50
    POSITIVE LOGITS
     bandwagon
    2.21
     enthusiastically
    1.78
     fray
    1.76
     corpor
    1.75
     chorus
    1.68
     ferv
    1.59
     passionately
    1.58
     coh
    1.55
     participate
    1.54
     psy
    1.51
    Act Density 0.003%

    No Known Activations