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

    Neuronpedia

    INDEX
    Explanations

    statistical or numerical ratios and comparisons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    glers
    -0.73
    sites
    -0.72
    Ü
    -0.71
    ez
    -0.71
    tics
    -0.70
    ibilities
    -0.68
    groups
    -0.68
    dict
    -0.67
     devils
    -0.67
    rovers
    -0.66
    POSITIVE LOGITS
     ounce
    0.99
     capita
    0.91
     dollar
    0.91
     thousand
    0.86
     pound
    0.86
     additional
    0.84
     conceivable
    0.83
     cubic
    0.82
     gallon
    0.82
     successive
    0.82
    Act Density 0.080%

    No Known Activations