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

    Neuronpedia

    INDEX
    Explanations

    points of significant punctuation or formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    per
    -0.16
    inth
    -0.16
    led
    -0.16
    se
    -0.15
     hors
    -0.15
    ler
    -0.14
     emp
    -0.14
    zw
    -0.14
     Wagner
    -0.14
    orth
    -0.14
    POSITIVE LOGITS
    ÄŁan
    0.17
    ACES
    0.16
    oji
    0.15
    жи
    0.15
    .SDK
    0.15
    /DD
    0.14
    aku
    0.14
    ayi
    0.14
    TestFixture
    0.14
    Enumeration
    0.14
    Act Density 0.011%

    No Known Activations