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

    Neuronpedia

    INDEX
    Explanations

    references to internal processes and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erge
    -0.16
    emia
    -0.15
    ookies
    -0.15
    ़
    -0.15
    WithEmail
    -0.14
    pus
    -0.14
    hiro
    -0.14
    ema
    -0.14
    eling
    -0.14
    osa
    -0.14
    POSITIVE LOGITS
    most
    0.23
    /Internal
    0.20
    ities
    0.18
    /internal
    0.18
    halb
    0.18
    ized
    0.17
    /embed
    0.17
    mente
    0.17
    pool
    0.16
    ised
    0.15
    Act Density 0.014%

    No Known Activations