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

    Neuronpedia

    INDEX
    Explanations

    dates and specific times written in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.79
    spread
    -0.74
    abled
    -0.71
    buster
    -0.70
    ascript
    -0.68
    Names
    -0.68
    itability
    -0.68
    blade
    -0.68
    Bet
    -0.67
    itri
    -0.65
    POSITIVE LOGITS
     earnest
    0.77
     Gutenberg
    0.75
     scratch
    0.69
     dusk
    0.68
     daylight
    0.68
     anew
    0.63
     1963
    0.62
     Helsinki
    0.61
     Gerr
    0.61
     kindergarten
    0.60
    Act Density 0.165%

    No Known Activations