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

    Neuronpedia

    INDEX
    Explanations

    terms related to wastefulness and inefficiency

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.61
    NavController
    -0.56
    GeneratedCode
    -0.54
    accepte
    -0.54
    splice
    -0.51
     mandated
    -0.51
     חיצוניים
    -0.51
    cientos
    -0.51
     وتسجيلات
    -0.51
     hậu
    -0.50
    POSITIVE LOGITS
     wasted
    1.23
     wasting
    1.10
     waste
    1.08
     wastes
    0.97
     Waste
    0.96
    waste
    0.96
    Waste
    0.95
     WASTE
    0.93
     wasteful
    0.90
     useless
    0.85
    Act Density 0.081%

    No Known Activations