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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "double" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aldea
    -0.43
     yeterli
    -0.42
     mismos
    -0.40
     asamblea
    -0.39
     bonté
    -0.38
     paisaje
    -0.38
     pamamagitan
    -0.37
     alrededores
    -0.37
     fiscales
    -0.36
     tierras
    -0.35
    POSITIVE LOGITS
     Double
    0.89
    Double
    0.82
     DOUBLE
    0.81
     Triple
    0.79
    Triple
    0.78
    triple
    0.75
     triple
    0.73
     double
    0.71
    WithIOException
    0.71
    Doubles
    0.69
    Act Density 0.148%

    No Known Activations