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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the speaker's awareness or knowledge of a situation or topic

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I know" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isco
    -0.82
     sidx
    -0.77
    interstitial
    -0.75
    acies
    -0.73
    onding
    -0.70
     psychiat
    -0.70
    cific
    -0.68
    endar
    -0.67
    phrine
    -0.67
    ishers
    -0.67
    POSITIVE LOGITS
    ledged
    0.85
     firsthand
    0.81
    ledge
    0.73
     how
    0.72
    nothing
    0.70
     nothing
    0.70
     beforehand
    0.67
    yll
    0.66
     exactly
    0.65
    hed
    0.62
    Act Density 0.045%

    No Known Activations