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

    Neuronpedia

    INDEX
    Explanations

    inspirational figures that someone looks up to

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.70
    apo
    -0.69
    pload
    -0.69
    kefeller
    -0.66
    BIT
    -0.62
    avery
    -0.61
     Antar
    -0.60
    Cu
    -0.60
    nesday
    -0.59
    berus
    -0.59
    POSITIVE LOGITS
    river
    0.77
    raised
    0.69
     acron
    0.69
     aloud
    0.66
     favorably
    0.63
    imation
    0.62
    shine
    0.62
    enance
    0.62
    onyms
    0.62
    rights
    0.61
    Act Density 0.019%

    No Known Activations