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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal critique and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.79
    Geplaatst
    -0.73
     дописавши
    -0.67
     pettico
    -0.64
     CreateTagHelper
    -0.61
    BASEPATH
    -0.60
     sherds
    -0.58
     daisies
    -0.56
    antMatchers
    -0.56
     betek
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.63
     =>
    0.61
    \}=
    0.59
     lenguas
    0.51
     sujeito
    0.50
    прочем
    0.49
    )]
    0.49
    )))
    0.48
    ‌اند
    0.48
    ]),
    0.48
    Act Density 3.341%

    No Known Activations