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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to completion or finality in statements and the name Clare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.87
    urated
    -0.85
    inson
    -0.80
    ä½ľ
    -0.80
    çĶŁ
    -0.79
    é¾įå¥ij士
    -0.78
    ĸļ
    -0.77
    owers
    -0.76
    ographs
    -0.76
    ÑĮ
    -0.75
    POSITIVE LOGITS
     Done
    1.26
    Done
    0.99
     Dame
    0.93
    lean
    0.84
    orry
    0.82
    done
    0.81
     Mayo
    0.79
    cale
    0.79
    ggies
    0.79
    nces
    0.76
    Act Density 0.015%

    No Known Activations