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

    Neuronpedia

    INDEX
    Explanations

    mentions of legislative actions related to public demonstrations and laws targeting protesters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    00007
    -0.80
    ridor
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    alion
    -0.68
     Boyle
    -0.67
     WAS
    -0.66
    INAL
    -0.65
    beck
    -0.64
    NESS
    -0.64
    001
    -0.63
    POSITIVE LOGITS
     genres
    0.86
     denominations
    0.81
     dearly
    0.80
     varying
    0.80
     festivals
    0.79
     showcased
    0.78
     avail
    0.78
     populate
    0.77
     besides
    0.76
     vying
    0.76
    Act Density 11.665%

    No Known Activations