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

    Neuronpedia

    INDEX
    Explanations

    instances where a vote is happening or expected to happen

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vote"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ults
    -0.85
    ::::::::
    -0.75
    Gy
    -0.74
    uilt
    -0.72
    Pixel
    -0.71
    ENTION
    -0.70
    £
    -0.69
    ACT
    -0.68
    949
    -0.68
    ï¸ı
    -0.67
    POSITIVE LOGITS
     behalf
    1.60
    erous
    0.97
    yx
    0.95
    etheless
    0.93
    eness
    0.92
     Capitol
    0.92
     Wednesday
    0.87
    etime
    0.84
     approving
    0.83
    shore
    0.83
    Act Density 0.169%

    No Known Activations