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

    Neuronpedia

    INDEX
    Explanations

    descriptions of technology products and their features

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Äĩ
    -1.09
    ensual
    -0.98
     wore
    -0.84
    PsyNetMessage
    -0.83
    maid
    -0.82
    izu
    -0.82
    tm
    -0.82
    iment
    -0.81
    aris
    -0.80
    izable
    -0.80
    POSITIVE LOGITS
    react
    0.90
     Rampage
    0.88
     nowhere
    0.87
     shelf
    0.87
    paying
    0.87
     hill
    0.87
     notch
    0.84
     proverbial
    0.82
    Stack
    0.82
     earners
    0.82
    Act Density 0.580%

    No Known Activations