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

    Neuronpedia

    INDEX
    Explanations

    references to political actions and statements surrounding elections and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.08
    3:0.09
    4:0.03
    5:0.10
    6:0.03
    7:0.04
    8:0.06
    9:0.14
    10:0.14
    11:0.16
    Negative Logits
     independ
    -1.00
    inav
    -0.96
     avail
    -0.94
    riv
    -0.93
    lite
    -0.90
     attain
    -0.89
     *.
    -0.88
     flavour
    -0.86
    lease
    -0.85
    inction
    -0.84
    POSITIVE LOGITS
     HuffPost
    1.17
     Called
    1.14
    Morning
    1.11
     "@
    1.02
     Asked
    1.00
     Palest
    1.00
     Klux
    0.99
    ccording
    0.95
     Stab
    0.94
     Amid
    0.94
    Act Density 0.266%

    No Known Activations