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

    Neuronpedia

    INDEX
    Explanations

    references to well-known individuals or concepts in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Prag
    -0.69
     Pinn
    -0.63
     Bettina
    -0.63
    TextInputLayout
    -0.61
     Winnipeg
    -0.59
     Carrick
    -0.59
     sabi
    -0.58
     Kigali
    -0.58
     Chaco
    -0.56
     Poles
    -0.56
    POSITIVE LOGITS
     Famous
    1.04
    BeginContext
    0.90
    Famous
    0.90
    famous
    0.85
     famous
    0.81
     Fame
    0.77
     للمعارف
    0.75
     fame
    0.70
    Fame
    0.68
    mphony
    0.67
    Act Density 0.008%

    No Known Activations