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

    Neuronpedia

    INDEX
    Explanations

    words related to percentages or statistical figures

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tags
    -0.62
    rament
    -0.60
     razor
    -0.60
    venge
    -0.59
    access
    -0.59
    DragonMagazine
    -0.59
    æ³
    -0.58
    imen
    -0.58
     marqu
    -0.57
     garg
    -0.57
    POSITIVE LOGITS
    alion
    0.72
     respondents
    0.71
     surveyed
    0.71
     undecided
    0.70
    %).
    0.67
    ecided
    0.65
     Females
    0.65
     apiece
    0.64
     overall
    0.64
    %),
    0.63
    Act Density 0.113%

    No Known Activations