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

    Neuronpedia

    INDEX
    Explanations

    smooth transitions or operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     affor
    -0.79
     increa
    -0.73
     impra
    -0.72
     purcha
    -0.72
     strick
    -0.71
     Bartholo
    -0.69
     guarante
    -0.69
     Magdal
    -0.67
     gild
    -0.66
     Stretcher
    -0.66
    POSITIVE LOGITS
     smooth
    1.41
    smooth
    1.39
     Smooth
    1.20
    Smooth
    1.19
     smoother
    1.15
     smoothness
    1.12
     smoothly
    1.03
     smoothing
    0.90
     smoothed
    0.80
     seamless
    0.80
    Act Density 0.116%

    No Known Activations