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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is being regulated or examined for compliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being governed, regulated, or affected by authority or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.66
     sake
    -0.65
     novel
    -0.64
     Cream
    -0.60
     invented
    -0.57
     flows
    -0.57
    ints
    -0.56
    andel
    -0.56
     torches
    -0.55
     Families
    -0.55
    POSITIVE LOGITS
    ascript
    0.83
    untarily
    0.81
    ptin
    0.79
    actionDate
    0.79
    Reviewer
    0.79
    ombat
    0.76
    itably
    0.75
    thumbnails
    0.73
    graded
    0.73
    Compl
    0.70
    Act Density 0.114%

    No Known Activations