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

    Neuronpedia

    INDEX
    Explanations

    terms related to technological products and features

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unlucky
    -0.86
    terday
    -0.77
    tsky
    -0.77
    hement
    -0.71
     inward
    -0.71
     captcha
    -0.70
    ividual
    -0.68
    inous
    -0.67
     apost
    -0.66
     tremend
    -0.64
    POSITIVE LOGITS
    Overview
    0.80
    76561
    0.79
     Available
    0.78
    Minimum
    0.77
    ccording
    0.76
    hemat
    0.74
    ============
    0.73
    ------------------------
    0.73
    ":["
    0.73
     Dimensions
    0.72
    Act Density 0.234%

    No Known Activations