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

    Neuronpedia

    INDEX
    Explanations

    details or specific information

    oai_token-act-pair · gpt-3.5-turbo

    significant concepts or key details in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doors
    -0.66
     favourites
    -0.66
    _>
    -0.63
    selves
    -0.61
    ummies
    -0.61
    berries
    -0.60
     Universities
    -0.58
    ilaterally
    -0.58
    ergy
    -0.58
    Known
    -0.57
    POSITIVE LOGITS
     extends
    0.84
     assumes
    0.81
     may
    0.80
     corresponds
    0.79
     encompasses
    0.78
     arose
    0.77
     represents
    0.76
     coincides
    0.76
     culmin
    0.76
     belongs
    0.76
    Act Density 0.255%

    No Known Activations