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

    Neuronpedia

    INDEX
    Explanations

    statements revealing surprising outcomes or realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    harapkan
    -0.62
     Besøkt
    -0.59
    NewUrlParser
    -0.59
     sandero
    -0.58
     Griechen
    -0.56
     Wikimedijinoj
    -0.55
    especie
    -0.55
    ukur
    -0.54
    ThroughAttribute
    -0.54
    dziew
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.78
     bleek
    0.63
    原来
    0.61
    原來
    0.59
     שוליים
    0.59
     AssemblyCulture
    0.57
    SpringBootTest
    0.56
     blijkt
    0.56
     CreateTagHelper
    0.54
    EnableWeb
    0.52
    Act Density 0.289%

    No Known Activations