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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Sam" associated with other names or titles in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.05
    ĨĴ
    -0.91
    assetsadobe
    -0.86
    éĹĺ
    -0.82
    ¬¼
    -0.81
    EStream
    -0.74
    milo
    -0.70
    urized
    -0.67
    ĪĴ
    -0.67
     pies
    -0.66
    POSITIVE LOGITS
    beit
    1.12
    riage
    1.07
    aja
    1.02
    ctica
    1.00
    thur
    1.00
    acter
    0.95
    acters
    0.90
    ithmetic
    0.90
    issa
    0.88
    unning
    0.88
    Act Density 0.032%

    No Known Activations