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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles, within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.16
    infeld
    -0.15
    طار
    -0.15
    ois
    -0.14
    alta
    -0.14
    aign
    -0.14
    ountain
    -0.14
    clist
    -0.13
     Ellison
    -0.13
     fellowship
    -0.13
    POSITIVE LOGITS
    pane
    0.17
    anka
    0.17
    IntegerField
    0.15
    cki
    0.14
    onymous
    0.14
    ansk
    0.14
    cky
    0.14
    ackages
    0.14
    AMENT
    0.14
     è©ķ
    0.13
    Act Density 0.123%

    No Known Activations