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

    Neuronpedia

    INDEX
    Explanations

    references to "Alice in Wonderland" and related literary elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strike
    -0.15
    velt
    -0.15
    LEX
    -0.14
     kiss
    -0.14
    AttributeName
    -0.14
    [".
    -0.14
    slick
    -0.14
    Ì
    -0.14
    odega
    -0.14
    Segue
    -0.14
    POSITIVE LOGITS
     Alice
    0.50
    Alice
    0.44
     Wonderland
    0.42
     alice
    0.40
     Lewis
    0.36
    alice
    0.32
    Lewis
    0.32
     Carroll
    0.27
     Alic
    0.25
     Jab
    0.25
    Act Density 0.009%

    No Known Activations