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

    Neuronpedia

    INDEX
    Explanations

    time intervals or ranges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to timeframes or intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.79
    der
    -0.70
    vous
    -0.69
    hemat
    -0.69
    gn
    -0.68
    rav
    -0.67
    brate
    -0.66
    iasis
    -0.65
    ATION
    -0.65
    gow
    -0.64
    POSITIVE LOGITS
     halves
    0.72
     rounds
    0.70
    between
    0.67
     peoples
    0.64
    urst
    0.64
    stocks
    0.63
     buddies
    0.62
     genders
    0.61
    ween
    0.61
    ieties
    0.60
    Act Density 0.042%

    No Known Activations