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

    Neuronpedia

    INDEX
    Explanations

    references to academic citation formats and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lef
    -0.18
    ints
    -0.18
    Codes
    -0.15
    IAS
    -0.15
    avy
    -0.15
    ordin
    -0.15
    ccoli
    -0.15
     Noel
    -0.14
    igen
    -0.14
    ìķ¡
    -0.14
    POSITIVE LOGITS
    _vue
    0.15
    uien
    0.14
     Vill
    0.14
     Reflect
    0.14
    TestFixture
    0.14
     lined
    0.14
     Ske
    0.14
    igham
    0.14
    Äįky
    0.14
    :@""
    0.13
    Act Density 0.016%

    No Known Activations