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

    Neuronpedia

    INDEX
    Explanations

    information being relayed or reported by different sources

    oai_token-act-pair · gpt-3.5-turbo

    statements made by spokespersons or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.87
     ILCS
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    aband
    -0.77
     sidx
    -0.75
    ample
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    adesh
    -0.69
    isol
    -0.68
    apy
    -0.67
    POSITIVE LOGITS
     BuzzFeed
    1.12
     HuffPost
    1.05
     reporters
    1.03
     us
    0.96
     VICE
    0.96
     Newsweek
    0.94
     me
    0.94
     Quartz
    0.94
     CNN
    0.93
     Reuters
    0.93
    Act Density 0.067%

    No Known Activations