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

    Neuronpedia

    INDEX
    Explanations

    references to methods of transportation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    strong
    -0.68
    pair
    -0.64
    woman
    -0.63
     Tradable
    -0.62
    Į
    -0.61
     reins
    -0.60
     moder
    -0.60
     LIMITED
    -0.59
    Statement
    -0.59
    mask
    -0.59
    POSITIVE LOGITS
     destinations
    1.18
     wherever
    0.92
     meet
    0.92
     avoid
    0.87
     destination
    0.87
     reach
    0.86
     whichever
    0.85
     maximize
    0.85
     shore
    0.85
     Mecca
    0.84
    Act Density 0.195%

    No Known Activations