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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and their roles within the House of Representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.03
    6:0.22
    7:0.35
    8:0.03
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    nown
    -1.69
     stash
    -1.54
    dates
    -1.53
    idious
    -1.51
    fman
    -1.51
    erion
    -1.46
    opian
    -1.45
    anchez
    -1.45
    umbnails
    -1.42
     inventions
    -1.41
    POSITIVE LOGITS
     chorus
    1.66
     Lansing
    1.63
    aca
    1.57
    Song
    1.43
    の�
    1.38
    horn
    1.37
    division
    1.37
     Shade
    1.34
    current
    1.32
     Congress
    1.32
    Act Density 0.002%

    No Known Activations