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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -0.86
     vägen
    -0.83
    QMetaType
    -0.76
     supérieurs
    -0.76
    ########.
    -0.75
     militaires
    -0.73
     démocr
    -0.71
     commerciaux
    -0.71
     comerciais
    -0.70
     مرئيه
    -0.67
    POSITIVE LOGITS
     violence
    0.54
    hetto
    0.52
     inner
    0.51
    waukee
    0.48
     crime
    0.46
     violent
    0.46
    HasAnnotation
    0.46
     ghetto
    0.45
     stig
    0.44
     lyk
    0.44
    Act Density 0.347%

    No Known Activations