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

    Neuronpedia

    INDEX
    Explanations

    negative opinions or comments in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ructure
    -0.74
     PTS
    -0.72
    ilitation
    -0.71
    ETF
    -0.68
    Applications
    -0.68
    ourses
    -0.67
    isSpecialOrderable
    -0.67
     consolidation
    -0.67
    onductor
    -0.66
    izons
    -0.65
    POSITIVE LOGITS
     boobs
    1.13
     hilar
    1.12
     poop
    1.11
     dudes
    1.09
     dick
    1.08
     gigg
    1.07
     goof
    1.06
     jokes
    1.05
     hilarious
    1.04
     piss
    1.01
    Act Density 1.670%

    No Known Activations