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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding political viewpoints and their differences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.58
     ATTENTION
    -0.53
     factorial
    -0.52
     NSCoder
    -0.52
    WebServlet
    -0.51
     >=",
    -0.50
     Moun
    -0.50
     FetchType
    -0.49
     vuitton
    -0.49
     Attention
    -0.48
    POSITIVE LOGITS
     beliefs
    0.75
    ⓧ
    0.67
     creencias
    0.67
     Party
    0.63
    transQ
    0.60
     views
    0.60
    party
    0.59
     opinions
    0.58
    WithIOException
    0.57
     party
    0.57
    Act Density 0.226%

    No Known Activations