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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing approval, validation, or agreement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orem
    -0.87
     Activities
    -0.83
    igraph
    -0.82
    oleon
    -0.82
    iments
    -0.79
     Delivery
    -0.77
     Enhancement
    -0.77
     Killer
    -0.77
     Occupations
    -0.76
    ospace
    -0.76
    POSITIVE LOGITS
    ãĤ©
    1.23
    olded
    0.93
    named
    0.92
    mint
    0.87
     accommod
    0.84
    gged
    0.84
     positioned
    0.84
     bestowed
    0.83
    label
    0.82
     fitted
    0.82
    Act Density 1.324%

    No Known Activations