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

    Neuronpedia

    INDEX
    Explanations

    instances where a decision or vote has been made

    oai_token-act-pair · gpt-3.5-turbo

    instances of voting actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebin
    -0.79
    qv
    -0.78
    ptoms
    -0.76
    clair
    -0.75
    xia
    -0.73
    illin
    -0.73
    fal
    -0.72
    uras
    -0.71
    vern
    -0.68
     Mub
    -0.67
    POSITIVE LOGITS
     unanimously
    1.14
     overwhelmingly
    0.92
     voted
    0.90
     decisively
    0.79
     Leave
    0.79
     votes
    0.75
    ndum
    0.73
     approving
    0.73
     against
    0.73
     accordingly
    0.71
    Act Density 0.021%

    No Known Activations