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

    Neuronpedia

    INDEX
    Explanations

    percentages and proportions

    oai_token-act-pair · gpt-3.5-turbo

    instances of percentages in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rav
    -0.80
    kefeller
    -0.77
    icon
    -0.74
    pload
    -0.74
    aries
    -0.72
    jri
    -0.68
    inous
    -0.68
    pty
    -0.66
    ary
    -0.65
    worldly
    -0.65
    POSITIVE LOGITS
    PsyNetMessage
    0.86
     utilization
    0.78
     accuracy
    0.75
     disapprove
    0.74
     polled
    0.72
     respondents
    0.72
     approve
    0.70
    eele
    0.70
     overall
    0.69
     surveyed
    0.67
    Act Density 0.070%

    No Known Activations