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

    Neuronpedia

    INDEX
    Explanations

    instances of template parameters in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaf
    -0.72
    γων
    -0.71
     Monfieur
    -0.63
     fhort
    -0.63
     propOrder
    -0.63
    bode
    -0.62
     Mifflin
    -0.61
     sauer
    -0.61
     perfon
    -0.60
     Chriftian
    -0.60
    POSITIVE LOGITS
     <>
    0.86
    <>
    0.82
    ViewFeatures
    0.66
     Réponses
    0.59
    ,#
    0.58
    BeNil
    0.58
    время
    0.57
    ,-
    0.57
    ArrowToggle
    0.56
     régionales
    0.56
    Act Density 0.001%

    No Known Activations