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

    Neuronpedia

    INDEX
    Explanations

    specific symbols and formatting related to coding syntax or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gentry
    -0.79
     Stella
    -0.78
     Huxley
    -0.74
     APO
    -0.74
     Chu
    -0.73
     Abby
    -0.73
    Chu
    -0.69
     Chiang
    -0.68
    Abby
    -0.67
     Holt
    -0.67
    POSITIVE LOGITS
     Veronica
    0.90
     Elias
    0.85
     Lynd
    0.82
     Morgan
    0.81
     LIS
    0.81
    Veronica
    0.80
    LIS
    0.79
     Cedric
    0.78
     Heather
    0.77
     Wul
    0.77
    Act Density 1.765%

    No Known Activations