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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anta
    -0.15
    atism
    -0.14
    enta
    -0.14
    alm
    -0.14
    oh
    -0.14
    autiful
    -0.14
    æŃ©
    -0.14
     ÙĪÙħا
    -0.13
    'util
    -0.13
    iesz
    -0.13
    POSITIVE LOGITS
    ensis
    0.15
    pter
    0.14
    iban
    0.14
    conditionally
    0.14
    wie
    0.14
    еÑģÑı
    0.14
    weigh
    0.14
    reshold
    0.14
    ByExample
    0.14
    Smarty
    0.14
    Act Density 0.032%

    No Known Activations