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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss governance and political systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.08
    3:0.07
    4:0.07
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
     guiActive
    -1.92
     millenn
    -1.83
    okemon
    -1.79
     Stim
    -1.68
     Rosenthal
    -1.66
    ITCH
    -1.64
     Rider
    -1.63
     Greater
    -1.63
    omet
    -1.61
    ★★
    -1.60
    POSITIVE LOGITS
     cabin
    1.81
    uments
    1.72
    sama
    1.71
    Untitled
    1.67
    osures
    1.65
     favors
    1.60
    mates
    1.60
     drafts
    1.59
    estation
    1.56
    avy
    1.54
    Act Density 0.000%

    No Known Activations