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

    Neuronpedia

    INDEX
    Explanations

    references to computer programming languages and related technical terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bern
    -0.79
    itized
    -0.77
    ifications
    -0.77
    ovych
    -0.74
    night
    -0.73
    ifier
    -0.73
    lift
    -0.72
    ãĤ±
    -0.72
    lime
    -0.72
    circ
    -0.72
    POSITIVE LOGITS
    OPLE
    1.16
    FILE
    0.90
    LL
    0.83
    ULAR
    0.79
    PE
    0.78
    XY
    0.78
    VO
    0.78
    ASE
    0.77
    VICE
    0.76
    ISTER
    0.76
    Act Density 0.346%

    No Known Activations