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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Alexander" and variations of the name "Alex."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Rourke
    -0.90
     UIFont
    -0.83
    Rüyada
    -0.81
    ServiceModel
    -0.79
     jPanel
    -0.78
    CodedInputStream
    -0.77
    __*/
    -0.77
     Habit
    -0.75
     Cof
    -0.75
     HomeComponent
    -0.73
    POSITIVE LOGITS
     Alex
    1.26
     Alexander
    1.24
     Alexand
    1.18
    Alex
    1.12
    Alexander
    1.05
     Alexandre
    1.03
    Alexandre
    1.03
    ALEX
    1.03
     alexander
    1.03
    Alexand
    0.99
    Act Density 0.007%

    No Known Activations