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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and political debates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siber
    -0.64
    Nav
    -0.64
    translation
    -0.60
    WIND
    -0.58
    details
    -0.57
    Sequ
    -0.57
    Lv
    -0.56
    ãĤª
    -0.56
    ãĤŃ
    -0.54
     Accessed
    -0.54
    POSITIVE LOGITS
     deserve
    0.87
     tended
    0.85
     were
    0.84
     fame
    0.81
     are
    0.80
     have
    0.76
     succumbed
    0.76
     ought
    0.76
     contend
    0.76
     rejoice
    0.75
    Act Density 2.585%

    No Known Activations