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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions and future plans

    oai_token-act-pair · gpt-3.5-turbo

    expressions of future expectations or aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.67
    hess
    -0.64
    jection
    -0.61
    OTOS
    -0.59
    affe
    -0.56
    ĸļ
    -0.56
    avid
    -0.54
    tained
    -0.54
    aeper
    -0.54
    asta
    -0.54
    POSITIVE LOGITS
     will
    1.51
    will
    1.43
    'll
    1.33
     someday
    1.31
     future
    1.27
     WILL
    1.24
     tomorrow
    1.17
    morrow
    1.14
    Will
    1.13
     hereafter
    1.11
    Act Density 1.717%

    No Known Activations