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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    wagen
    -0.74
    egu
    -0.71
     Caption
    -0.67
     responsibility
    -0.67
    erer
    -0.67
    mare
    -0.66
    ned
    -0.66
    itia
    -0.66
    ahl
    -0.65
    Cho
    -0.64
    POSITIVE LOGITS
     sake
    1.47
     purposes
    1.35
    ummies
    1.29
     reasons
    1.25
     consecutive
    1.04
     eternity
    1.02
     periods
    1.01
     Reasons
    0.99
     awhile
    0.96
     duration
    0.88
    Act Density 1.995%

    No Known Activations