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

    Neuronpedia

    INDEX
    Explanations

    dates or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly months, weeks, and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.71
    emort
    -0.68
    plete
    -0.68
     competent
    -0.67
    atars
    -0.66
    bidden
    -0.63
    verified
    -0.62
     poles
    -0.61
     horizontal
    -0.61
     vertical
    -0.61
    POSITIVE LOGITS
    nings
    0.88
    dream
    0.74
     opener
    0.73
    ovie
    0.70
    adan
    0.67
     outing
    0.66
    night
    0.63
    ivan
    0.62
     Debbie
    0.62
    poke
    0.62
    Act Density 0.146%

    No Known Activations