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

    Neuronpedia

    INDEX
    Explanations

    political and social topics, particularly focusing on controversies and government actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Ruk
    -0.78
     Aman
    -0.70
     Bris
    -0.68
     Stard
    -0.68
     Kitt
    -0.67
     Jeanne
    -0.67
     Qiao
    -0.67
     Maurit
    -0.66
     Belg
    -0.65
     Sieg
    -0.64
    POSITIVE LOGITS
    ª
    0.91
    possibly
    0.91
    very
    0.88
    yet
    0.86
    urion
    0.85
    ordinary
    0.84
    Ĵ
    0.83
    ittal
    0.83
    virtual
    0.83
    ¹
    0.82
    Act Density 4.160%

    No Known Activations