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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elias
    -0.82
     Veronica
    -0.81
     Mog
    -0.81
     Morgan
    -0.80
     Nath
    -0.78
    Mog
    -0.77
     Lynd
    -0.77
     LIS
    -0.76
     Wul
    -0.75
     RH
    -0.75
    POSITIVE LOGITS
     Stella
    0.83
     Gentry
    0.81
     Abby
    0.78
     Chu
    0.74
     Huxley
    0.73
    Stella
    0.72
     Olson
    0.72
     Holt
    0.70
     APO
    0.70
    Abby
    0.70
    Act Density 1.944%

    No Known Activations