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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related words

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kef
    -0.69
    */(
    -0.65
    ciating
    -0.65
    advertisement
    -0.61
    wcsstore
    -0.61
     ESC
    -0.58
    eyed
    -0.58
    cientious
    -0.58
     caption
    -0.57
     Impossible
    -0.57
    POSITIVE LOGITS
     onwards
    0.86
     onward
    0.76
     arrives
    0.75
    terms
    0.70
    east
    0.67
     arrivals
    0.66
    lishes
    0.65
    ione
    0.65
     arrival
    0.64
     drafts
    0.64
    Act Density 0.168%

    No Known Activations