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

    Neuronpedia

    INDEX
    Explanations

    references to system capabilities and potential for improvement or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.17
    ardon
    -0.16
    argin
    -0.16
    ath
    -0.16
    coming
    -0.15
    ê
    -0.15
    eme
    -0.15
    rou
    -0.15
    edy
    -0.14
    ábado
    -0.14
    POSITIVE LOGITS
    ities
    0.18
    sled
    0.16
    vise
    0.16
    idot
    0.16
    odore
    0.15
    orus
    0.15
    idades
    0.15
    wise
    0.15
    å¾³
    0.14
    eln
    0.14
    Act Density 0.015%

    No Known Activations