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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month day, year

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically the month and day

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hindsight
    -0.79
     arrang
    -0.67
     spoiler
    -0.65
     descendants
    -0.65
    Reviewer
    -0.64
     heirs
    -0.62
     tray
    -0.60
     mathemat
    -0.59
     predec
    -0.58
     pals
    -0.57
    POSITIVE LOGITS
     27
    1.00
     29
    1.00
     28
    0.97
     26
    0.97
     04
    0.96
     09
    0.96
    Ñı
    0.96
     07
    0.93
     05
    0.93
     01
    0.93
    Act Density 0.033%

    No Known Activations