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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words with the term "hard-" at the beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a strong work ethic or dedication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.76
     Cah
    -0.75
     Wald
    -0.64
    emonium
    -0.64
     Wonderland
    -0.64
    auga
    -0.64
     Burk
    -0.64
     Kenny
    -0.63
     Dek
    -0.63
     Rica
    -0.62
    POSITIVE LOGITS
    hitting
    1.30
    coded
    1.13
    earned
    1.12
    bodied
    1.12
    pressed
    1.12
    hearted
    1.07
    won
    1.06
    edged
    1.05
    sounding
    0.99
    stem
    0.97
    Act Density 0.034%

    No Known Activations