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

    Neuronpedia

    INDEX
    Explanations

    word pairs with repetition for emphasis or accuracy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orthy
    -0.90
    uga
    -0.84
    atis
    -0.80
     Authors
    -0.78
    Stage
    -0.76
    dor
    -0.75
    onso
    -0.74
    icans
    -0.74
    erves
    -0.71
    esta
    -0.70
    POSITIVE LOGITS
     ratio
    1.11
     comparisons
    1.06
     conversion
    1.04
     ratios
    1.00
     correspondence
    1.00
     conversions
    0.98
     converter
    0.91
     transmission
    0.89
     approach
    0.88
     comparison
    0.88
    Act Density 0.145%

    No Known Activations