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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "double" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aldea
    -0.42
     yeterli
    -0.40
     asamblea
    -0.40
     obreros
    -0.40
     CreateTagHelper
    -0.39
     alrededores
    -0.37
     fiscales
    -0.36
     periódicos
    -0.36
     nôtre
    -0.36
    InInspector
    -0.36
    POSITIVE LOGITS
     Double
    1.17
    Double
    1.08
     DOUBLE
    1.05
     double
    1.03
    double
    0.91
     Doubles
    0.84
     Triple
    0.84
    Doubles
    0.84
    DOUBLE
    0.84
     doubles
    0.82
    Act Density 0.167%

    No Known Activations