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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "knew"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "knew" indicating awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulum
    -0.72
    orio
    -0.71
     ILCS
    -0.70
    phrine
    -0.70
    otion
    -0.69
    interstitial
    -0.68
    utations
    -0.65
     retri
    -0.65
    pex
    -0.64
    anco
    -0.63
    POSITIVE LOGITS
     beforehand
    1.02
     instinctively
    0.81
    ledged
    0.79
    footed
    0.77
     nothing
    0.73
    nothing
    0.72
    lege
    0.70
    bones
    0.69
    ledge
    0.69
    lessly
    0.69
    Act Density 0.046%

    No Known Activations