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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "been."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.70
    ives
    -0.66
    achu
    -0.63
    iveness
    -0.63
    oglu
    -0.62
    ackle
    -0.62
     fray
    -0.61
    ively
    -0.61
     Extend
    -0.61
    leness
    -0.61
    POSITIVE LOGITS
     able
    1.06
    wolves
    0.99
     born
    0.91
     forgotten
    0.89
     subjected
    0.89
     asleep
    0.86
     beaten
    0.85
    cffffcc
    0.84
     bitten
    0.83
     replaced
    0.82
    Act Density 0.134%

    No Known Activations