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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time durations or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.60
    bard
    -0.60
    Lot
    -0.59
    imir
    -0.58
    oided
    -0.57
    uer
    -0.57
    itors
    -0.57
     tyr
    -0.56
     misunder
    -0.56
     dearly
    -0.55
    POSITIVE LOGITS
    aneously
    0.87
     thereof
    0.83
     of
    0.80
     thereafter
    0.74
     increments
    0.73
     confines
    0.70
    threatening
    0.69
    pace
    0.65
     span
    0.64
     Ples
    0.64
    Act Density 0.066%

    No Known Activations