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

    Neuronpedia

    INDEX
    Explanations

    the word "know" as part of speech in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize familiarity or shared knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.74
    acco
    -0.70
    anmar
    -0.69
    BuyableInstoreAndOnline
    -0.68
    aez
    -0.67
    rang
    -0.66
    stad
    -0.63
    amic
    -0.59
    abwe
    -0.59
     enthusi
    -0.57
    POSITIVE LOGITS
     what
    0.91
    terday
    0.88
     why
    0.85
     WHAT
    0.83
     how
    0.80
     whats
    0.78
     nothing
    0.70
     somet
    0.70
    what
    0.68
    omething
    0.68
    Act Density 0.036%

    No Known Activations