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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "know"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "know" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mehran
    -0.69
     rever
    -0.62
     Pax
    -0.62
     voucher
    -0.58
    erva
    -0.57
     patronage
    -0.57
    Tur
    -0.56
     Mek
    -0.56
     Statue
    -0.55
    ciating
    -0.55
    POSITIVE LOGITS
    ledged
    1.45
    lege
    1.40
    ledge
    1.37
    LED
    1.26
    led
    1.06
    how
    0.99
    ingly
    0.98
     thy
    0.92
    your
    0.89
     how
    0.86
    Act Density 0.057%

    No Known Activations