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

    Neuronpedia

    INDEX
    Explanations

    references to facial features

    oai_token-act-pair · gpt-3.5-turbo

    references to facial features and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aday
    -0.82
    cham
    -0.75
    uden
    -0.74
     Recomm
    -0.73
    MQ
    -0.73
     Provided
    -0.73
    æ©Ł
    -0.70
    world
    -0.70
     Pharma
    -0.69
    ensable
    -0.68
    POSITIVE LOGITS
     hair
    1.07
     expressions
    1.04
     muscles
    0.96
     recognition
    0.96
     expression
    0.95
     portraits
    0.92
     makeup
    0.87
     prost
    0.86
     impressions
    0.86
     tissues
    0.86
    Act Density 0.023%

    No Known Activations