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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and associated entities

    oai_token-act-pair · gpt-3.5-turbo

    references to news outlets and media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.79
    Ö¼
    -0.65
     Malfoy
    -0.61
     Voldemort
    -0.60
     Adolf
    -0.59
     Draco
    -0.59
     Neville
    -0.58
     phyl
    -0.57
    hower
    -0.57
     Cadillac
    -0.57
    POSITIVE LOGITS
    Daily
    1.16
    aretz
    1.10
    CNN
    1.04
    WN
    1.03
    Journal
    1.03
    News
    1.01
    NBC
    1.01
    DN
    1.00
    daily
    0.99
     WEEK
    0.97
    Act Density 0.155%

    No Known Activations