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

    Neuronpedia

    INDEX
    Explanations

    terms related to unsustainability or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.52
    хьтан
    -0.50
    ⓧ
    -0.49
    Cyfeiriadau
    -0.43
    ConverterFactory
    -0.43
    XmlEnum
    -0.43
     насељу
    -0.41
    savings
    -0.40
    principalColumn
    -0.40
    verifyException
    -0.40
    POSITIVE LOGITS
     uns
    0.85
     kn
    0.77
     knight
    0.65
     Knight
    0.65
     Kn
    0.65
    ö
    0.61
    Uns
    0.60
     Uns
    0.59
    kn
    0.57
    dm
    0.57
    Act Density 1.050%

    No Known Activations