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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "double" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yeterli
    -0.38
     aldea
    -0.36
     mismos
    -0.35
     Ambiental
    -0.34
     tierras
    -0.34
     obreros
    -0.34
     paisaje
    -0.32
     asamblea
    -0.32
     dernières
    -0.31
     alrededores
    -0.31
    POSITIVE LOGITS
    WithIOException
    0.76
     sided
    0.72
     decker
    0.71
    triple
    0.71
    Triple
    0.69
     jeopardy
    0.68
     Triple
    0.68
     digit
    0.68
     entendre
    0.66
    decker
    0.66
    Act Density 0.228%

    No Known Activations