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

    Neuronpedia

    INDEX
    Explanations

    phrases where an action is required as a first step

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gould
    -0.69
    holes
    -0.66
    ourge
    -0.66
     Canaver
    -0.65
    oute
    -0.61
    ucl
    -0.61
    FORMATION
    -0.60
    morph
    -0.60
    sav
    -0.57
     Tant
    -0.57
    POSITIVE LOGITS
     responders
    1.12
     baseman
    1.07
     glance
    0.81
     impressions
    0.80
     ancest
    0.80
     blush
    0.79
     lady
    0.75
     impression
    0.73
     accuser
    0.73
     glim
    0.72
    Act Density 0.064%

    No Known Activations