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

    Neuronpedia

    INDEX
    Explanations

    odd characters and special markings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     frontline
    -0.80
     eleph
    -0.77
     tram
    -0.72
     driving
    -0.70
     prec
    -0.70
     petrol
    -0.69
     neighb
    -0.69
     elect
    -0.67
     spitting
    -0.67
     scrap
    -0.67
    POSITIVE LOGITS
    Reviewer
    1.38
    Advertisements
    1.36
    Contents
    1.34
    Reviewed
    1.31
    Advertisement
    1.26
    By
    1.24
    Rated
    1.24
    Trivia
    1.24
    This
    1.23
    If
    1.23
    Act Density 0.380%

    No Known Activations