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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "than"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    autions
    -1.02
    Winged
    -0.97
    ISSION
    -0.95
    ainment
    -0.94
    onomy
    -0.92
     antic
    -0.91
    imity
    -0.91
    Streamer
    -0.90
    olitical
    -0.89
     Directions
    -0.87
    POSITIVE LOGITS
     usual
    1.15
    average
    1.02
     average
    1.00
     anticipated
    0.88
    usercontent
    0.88
     expected
    0.87
    represent
    0.84
     marines
    0.83
    catch
    0.82
     processed
    0.81
    Act Density 0.601%

    No Known Activations