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

    Neuronpedia

    INDEX
    Explanations

    dates and recurring time intervals

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring events and their frequencies in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.93
    tymology
    -0.83
    ells
    -0.75
    ieg
    -0.75
    argon
    -0.74
    ect
    -0.74
    cellence
    -0.70
    alach
    -0.68
    artisan
    -0.68
    ydia
    -0.67
    POSITIVE LOGITS
     thereafter
    0.81
    night
    0.73
    atonin
    0.66
     bulletin
    0.65
     imaginable
    0.64
    except
    0.62
     dime
    0.61
    Subscribe
    0.60
     throughout
    0.59
     Supplement
    0.59
    Act Density 0.072%

    No Known Activations