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

    Neuronpedia

    INDEX
    Explanations

    names mentioned as knowing something or being in a specific position

    oai_token-act-pair · gpt-3.5-turbo

    instances of knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (~
    -0.76
    /,
    -0.73
     [*
    -0.70
     Anyway
    -0.69
     (>
    -0.69
     aforementioned
    -0.67
    ?]
    -0.67
     (=
    -0.65
     XD
    -0.65
     ([
    -0.65
    POSITIVE LOGITS
     sights
    0.82
     dreams
    0.81
     firsthand
    0.79
     dreamed
    0.77
     unforgettable
    0.76
     dream
    0.75
     marvel
    0.75
     unthinkable
    0.73
     nightmares
    0.71
     dreaming
    0.71
    Act Density 0.981%

    No Known Activations