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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles and hashtags

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     specificity
    -0.79
     Norwich
    -0.75
     nasal
    -0.71
     tape
    -0.69
     congreg
    -0.69
     favors
    -0.68
     vaginal
    -0.68
     recording
    -0.67
     concentrate
    -0.67
     displacement
    -0.67
    POSITIVE LOGITS
    realDonaldTrump
    1.31
    username
    1.12
    thereal
    1.10
    Real
    1.07
    Coach
    1.05
    #$
    1.02
    ANI
    1.01
    Official
    1.00
    wik
    0.94
    nat
    0.94
    Act Density 0.232%

    No Known Activations