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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to being the first or initial in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gould
    -0.83
     Canaver
    -0.72
    morph
    -0.68
     Nadu
    -0.63
    vor
    -0.61
    endo
    -0.60
    ucl
    -0.59
     Tant
    -0.59
    holes
    -0.58
    amus
    -0.58
    POSITIVE LOGITS
     responders
    1.20
     baseman
    1.12
     glance
    0.89
     lady
    0.78
     timers
    0.77
     impressions
    0.72
     impression
    0.71
     blush
    0.71
     step
    0.70
     instinct
    0.68
    Act Density 0.080%

    No Known Activations