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

    Neuronpedia

    INDEX
    Explanations

    references to government actions and related political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.11
    3:0.07
    4:0.03
    5:0.10
    6:0.03
    7:0.08
    8:0.36
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    tsky
    -3.73
     Lv
    -3.51
     Ukrain
    -3.25
     Cavs
    -3.16
     Akron
    -3.10
     Summoner
    -3.09
     Polish
    -3.06
     Yon
    -3.06
     Bowser
    -2.98
     Ryu
    -2.98
    POSITIVE LOGITS
     Abbott
    6.38
     Canberra
    5.46
    Austral
    5.40
     Tasmania
    5.20
     Australians
    5.17
     Turnbull
    4.97
     Brisbane
    4.93
     Queensland
    4.90
    Australia
    4.82
     Australia
    4.68
    Act Density 0.026%

    No Known Activations