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

    Neuronpedia

    INDEX
    Explanations

    dates and events in history

    oai_token-act-pair · gpt-3.5-turbo

    dates and historical time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therap
    -0.74
     explan
    -0.70
     agre
    -0.70
     manageable
    -0.66
    efficients
    -0.65
     priced
    -0.65
     giveaways
    -0.64
    nesday
    -0.63
     tack
    -0.63
     teamwork
    -0.61
    POSITIVE LOGITS
     Died
    1.28
    )[
    1.14
    Born
    1.10
    )]
    1.08
    )—
    1.05
    )'
    1.03
     Born
    1.01
     ?)
    1.01
    -)
    0.96
     died
    0.96
    Act Density 0.104%

    No Known Activations