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

    Neuronpedia

    INDEX
    Explanations

    references to stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.18
    اÙĨÙĬØ©
    -0.15
    iddi
    -0.14
    ÙĬÙĥÙĬ
    -0.14
    etre
    -0.14
    inema
    -0.14
    ksam
    -0.13
    ended
    -0.13
    -et
    -0.13
    ANCH
    -0.13
    POSITIVE LOGITS
    иÑģÑĮ
    0.16
    éijij
    0.15
    ileo
    0.15
    -rating
    0.14
    adero
    0.14
    éĭ
    0.14
    éĵº
    0.14
    Rating
    0.13
    -rated
    0.13
    points
    0.13
    Act Density 0.006%

    No Known Activations