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

    Neuronpedia

    INDEX
    Explanations

    words related to complex cognitive processes or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıж
    -0.17
    brick
    -0.15
    icerca
    -0.15
    iolet
    -0.15
    sil
    -0.14
    iations
    -0.14
    enheim
    -0.14
    ameleon
    -0.13
    ANDOM
    -0.13
    hee
    -0.13
    POSITIVE LOGITS
    apon
    0.15
    Ĥæķ°
    0.15
    ear
    0.15
    å®ļçļĦ
    0.14
    rias
    0.14
    áŁĴáŀ
    0.14
    ubu
    0.14
    ock
    0.14
    âu
    0.14
    pillar
    0.14
    Act Density 0.091%

    No Known Activations