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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    Twitter handles or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bradford
    -0.74
     specificity
    -0.72
     Norwich
    -0.69
     Pyramid
    -0.69
     Leone
    -0.66
     ordinance
    -0.65
     choir
    -0.65
     lipstick
    -0.65
     Romanian
    -0.65
     tracts
    -0.64
    POSITIVE LOGITS
    realDonaldTrump
    1.07
    #$
    0.94
    @@@@@@@@
    0.94
    nat
    0.89
    hidden
    0.87
    username
    0.86
    groups
    0.85
    ANI
    0.83
    thereal
    0.83
    dot
    0.82
    Act Density 0.024%

    No Known Activations