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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the clarity and manner of information presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     atracción
    -0.47
     cuarta
    -0.41
     hänen
    -0.39
     salvación
    -0.38
     đãi
    -0.37
     corriendo
    -0.37
     contribución
    -0.37
     extinción
    -0.36
     intérêt
    -0.36
     vergüenza
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.73
    存于互联网档案馆
    0.60
    rungsseite
    0.59
    OGND
    0.58
     FetchType
    0.57
    WriteTagHelper
    0.56
    complexContent
    0.54
    醐
    0.52
    InputTagHelper
    0.52
     ffilmiau
    0.52
    Act Density 1.101%

    No Known Activations