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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Good"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Good."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hars
    -0.65
     pent
    -0.65
    apse
    -0.64
    ptin
    -0.62
    opers
    -0.61
    ounter
    -0.61
    isive
    -0.61
    ãĢij
    -0.60
     succeeding
    -0.60
    natureconservancy
    -0.59
    POSITIVE LOGITS
    reads
    1.30
    bye
    1.21
    enough
    1.20
    luck
    1.16
     Samar
    1.05
    night
    1.03
    morning
    1.02
    friend
    1.00
    spr
    0.98
    will
    0.97
    Act Density 0.021%

    No Known Activations