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

    Neuronpedia

    INDEX
    Explanations

    content labeled as "Uncategorized."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acre
    -0.15
    usz
    -0.14
    finger
    -0.14
    ฤษ
    -0.14
    Hang
    -0.14
    ourke
    -0.14
     Seks
    -0.14
    ibal
    -0.14
    ContextHolder
    -0.14
    ussen
    -0.14
    POSITIVE LOGITS
    èĪ¬
    0.16
    owy
    0.16
    olean
    0.15
    ellaneous
    0.15
    ites
    0.15
    ç´ł
    0.14
    層
    0.14
    arness
    0.14
     Rath
    0.14
    -initialized
    0.14
    Act Density 0.004%

    No Known Activations