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

    Neuronpedia

    INDEX
    Explanations

    years mentioned as a duration of time

    oai_token-act-pair · gpt-3.5-turbo

    references to time spans, particularly years and decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.73
    actionDate
    -0.70
    rehens
    -0.70
    cius
    -0.68
    Module
    -0.64
    urion
    -0.64
     Ment
    -0.64
    gall
    -0.63
    ensibly
    -0.63
    oÄŁ
    -0.62
    POSITIVE LOGITS
     opener
    0.72
    >]
    0.65
    ,,
    0.64
     Copyright
    0.62
    !
    0.62
     ago
    0.62
     EVER
    0.62
     (!
    0.62
     featuring
    0.61
     goodbye
    0.60
    Act Density 0.147%

    No Known Activations