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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms that indicate a specific subject or category, often emphasizing the significance of those subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rade
    -0.17
    erc
    -0.16
    isku
    -0.15
    rides
    -0.15
    tem
    -0.14
    ovsky
    -0.14
    yah
    -0.14
    oku
    -0.13
    rado
    -0.13
    itect
    -0.13
    POSITIVE LOGITS
     following
    0.21
     present
    0.20
     Dün
    0.17
    strup
    0.17
     purpose
    0.16
    following
    0.16
     concept
    0.15
     aim
    0.15
    purpose
    0.15
     Department
    0.15
    Act Density 0.407%

    No Known Activations