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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkle
    -0.16
    ober
    -0.16
     Mond
    -0.14
    rier
    -0.14
    usercontent
    -0.14
    inkel
    -0.14
    powered
    -0.14
    ingo
    -0.14
    onomy
    -0.14
     k
    -0.14
    POSITIVE LOGITS
    ERCHANT
    0.15
    cko
    0.15
    ahy
    0.15
    ASHBOARD
    0.14
    TestFixture
    0.14
    mps
    0.14
     insecure
    0.13
    kul
    0.13
    heel
    0.13
    MBER
    0.13
    Act Density 0.002%

    No Known Activations