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

    Neuronpedia

    INDEX
    Explanations

    organizations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate organizational affiliations and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    always
    -0.86
    Synopsis
    -0.74
    hor
    -0.73
    perfect
    -0.71
     swe
    -0.70
    ãĤ¨ãĥ«
    -0.69
     pudding
    -0.68
    ̶
    -0.66
     brut
    -0.66
    actively
    -0.65
    POSITIVE LOGITS
     National
    1.02
     Federal
    0.97
     Regions
    0.97
     Department
    0.96
     Municipal
    0.96
     University
    0.95
     Bureau
    0.95
     Carnegie
    0.95
     Brookings
    0.94
     Cooperative
    0.93
    Act Density 0.209%

    No Known Activations