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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to geographic locations, such as cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.95
    ĨĴ
    -0.88
    ¬¼
    -0.87
    éĹĺ
    -0.67
    assetsadobe
    -0.64
     Fortune
    -0.64
    ĪĴ
    -0.64
     recip
    -0.60
    urized
    -0.60
     pies
    -0.59
    POSITIVE LOGITS
    beit
    1.18
    aja
    1.08
    ashtra
    1.00
    riage
    0.98
    ctica
    0.97
    thur
    0.97
    allel
    0.95
    acters
    0.95
    unning
    0.93
    acter
    0.93
    Act Density 0.036%

    No Known Activations