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

    Neuronpedia

    INDEX
    Explanations

    nested quotations and statements that convey authority or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.63
     unterkunft
    -0.52
     extranjera
    -0.52
     desmotivaciones
    -0.51
     Persönlichkeit
    -0.47
    harapkan
    -0.47
     dégâts
    -0.45
     Botschaft
    -0.44
     lecciones
    -0.44
     málaga
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.94
    rungsseite
    0.78
     Wikimedijinoj
    0.77
     للمعارف
    0.69
    bitField
    0.66
     CreateTagHelper
    0.66
     فريبيس
    0.64
    WEBPACK
    0.64
     EdgeInsets
    0.64
    SharedDtor
    0.63
    Act Density 2.612%

    No Known Activations