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

    Neuronpedia

    INDEX
    Explanations

    words related to political debates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of debates, particularly their frequency and context in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ridges
    -0.76
    uras
    -0.70
    aniel
    -0.64
    photos
    -0.63
    isu
    -0.61
    fits
    -0.60
    ocument
    -0.60
    metics
    -0.60
    OGR
    -0.59
    ptoms
    -0.59
    POSITIVE LOGITS
     moderators
    1.06
     moderator
    1.00
     moder
    0.91
    halla
    0.89
    ftime
    0.84
     prep
    0.78
     stump
    0.78
    Panel
    0.77
     transcript
    0.74
     raged
    0.72
    Act Density 0.047%

    No Known Activations