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

    Neuronpedia

    INDEX
    Explanations

    words that indicate changes or fluctuations in conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udu
    -0.14
    ahu
    -0.14
     Ellen
    -0.13
     Parsons
    -0.13
    bee
    -0.13
    mpz
    -0.13
    itational
    -0.13
    еÑģÑĮ
    -0.13
    ilim
    -0.13
    thon
    -0.13
    POSITIVE LOGITS
    ICO
    0.18
    YRO
    0.16
    359
    0.15
    ematik
    0.15
    edException
    0.14
    ograd
    0.14
    alette
    0.14
    ico
    0.14
    emic
    0.14
    ONUS
    0.14
    Act Density 0.090%

    No Known Activations