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

    Neuronpedia

    INDEX
    Explanations

    facial hair descriptions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Pharma
    -0.78
    uden
    -0.75
    claimer
    -0.72
    geist
    -0.72
    aday
    -0.70
    hedon
    -0.69
    rote
    -0.68
    world
    -0.68
     Blackwell
    -0.66
    én
    -0.65
    POSITIVE LOGITS
     hair
    1.01
     expressions
    0.97
     muscles
    0.90
     recognition
    0.90
     portraits
    0.89
     impressions
    0.88
     facial
    0.85
     Hair
    0.82
     expression
    0.81
     hairs
    0.79
    Act Density 5.455%

    No Known Activations