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

    Neuronpedia

    INDEX
    Explanations

    references to government policies and their implications, especially related to economic and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Purple
    -0.17
     Pane
    -0.16
    Purple
    -0.15
     æ½
    -0.15
     Pes
    -0.14
     Pyramid
    -0.14
    447
    -0.14
    æ½
    -0.14
     Pag
    -0.14
     Primitive
    -0.14
    POSITIVE LOGITS
     policy
    1.01
    policy
    0.90
     Policy
    0.88
    Policy
    0.82
    _policy
    0.78
    -policy
    0.76
     policies
    0.75
    æĶ¿çŃĸ
    0.73
    .policy
    0.71
     pol
    0.63
    Act Density 0.235%

    No Known Activations