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

    Neuronpedia

    INDEX
    Explanations

    specific years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    semble
    -0.64
    BuyableInstoreAndOnline
    -0.57
     ])
    -0.54
    ociate
    -0.54
     likeness
    -0.54
     hypocr
    -0.52
     dignity
    -0.52
     restraint
    -0.52
    hibited
    -0.51
     foregoing
    -0.51
    POSITIVE LOGITS
    when
    1.54
     when
    1.54
     WHEN
    1.02
     wherein
    0.96
     whenever
    0.90
     where
    0.90
     whereby
    0.87
    When
    0.83
     When
    0.79
     after
    0.77
    Act Density 0.246%

    No Known Activations