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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political voting and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" associated with dates or voting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bus
    -0.81
    ults
    -0.80
    MODE
    -0.78
    SourceFile
    -0.78
    Gy
    -0.77
    ©¶æ¥µ
    -0.76
    ACT
    -0.74
    949
    -0.74
    ::::::::
    -0.74
    Wan
    -0.73
    POSITIVE LOGITS
     behalf
    1.54
    yx
    0.95
    eday
    0.95
    etime
    0.94
    shore
    0.93
     board
    0.92
    eness
    0.91
    erous
    0.90
     Capitol
    0.90
     Wednesday
    0.87
    Act Density 0.222%

    No Known Activations