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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly the names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !'
    -0.69
    .ãĢį
    -0.66
    !.
    -0.65
    .--
    -0.62
    rawdownloadcloneembedreportprint
    -0.61
    !'"
    -0.61
    +.
    -0.60
     Written
    -0.58
    .?
    -0.56
    </
    -0.56
    POSITIVE LOGITS
     should
    1.33
     shouldn
    1.33
     lacked
    1.24
     could
    1.15
     deserved
    1.14
     hadn
    1.13
     had
    1.11
     would
    1.08
     ought
    1.06
     wouldn
    1.04
    Act Density 0.524%

    No Known Activations