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

    Neuronpedia

    INDEX
    Explanations

    phrases or names with the name "Bert."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orah
    -0.80
     Pulse
    -0.80
     Cassidy
    -0.78
     palette
    -0.75
     Pillar
    -0.74
     Shade
    -0.74
     Wa
    -0.72
     Crowley
    -0.71
    Pal
    -0.71
     Hawaii
    -0.70
    POSITIVE LOGITS
    İ
    2.19
     Bert
    1.96
     Soy
    1.32
     soy
    1.27
     pert
    1.13
     exert
    1.10
    ert
    0.98
     Guang
    0.87
     Blanc
    0.86
     Meng
    0.83
    Act Density 0.034%

    No Known Activations