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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "ban" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    klass
    -0.16
    chten
    -0.14
    elig
    -0.14
    wards
    -0.14
    aÄŁ
    -0.14
    lesia
    -0.14
    วà¸ĩ
    -0.14
    baum
    -0.14
    chia
    -0.14
    sep
    -0.13
    POSITIVE LOGITS
    ishment
    0.29
    ished
    0.28
    quets
    0.28
    offee
    0.27
    ishing
    0.25
    eful
    0.23
    quet
    0.23
    tering
    0.22
    ruptcy
    0.22
    quette
    0.22
    Act Density 0.015%

    No Known Activations