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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itin
    -0.16
     Mö
    -0.15
    etten
    -0.15
    ções
    -0.14
    elden
    -0.14
    ucene
    -0.14
    ipop
    -0.14
    elon
    -0.14
    Disclosure
    -0.14
    æłª
    -0.14
    POSITIVE LOGITS
     fed
    0.15
     Alv
    0.14
    reich
    0.14
    ToPoint
    0.13
    Vu
    0.13
     Vu
    0.13
     accommod
    0.13
    mission
    0.13
    .star
    0.13
    ahu
    0.13
    Act Density 0.916%

    No Known Activations