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

    Neuronpedia

    INDEX
    Explanations

    information related to political events and official statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    essment
    -0.61
    putes
    -0.59
     måneder
    -0.59
    esserts
    -0.59
    ]--;
    -0.59
    vocable
    -0.59
    larged
    -0.59
     purée
    -0.58
    quitous
    -0.58
    cipline
    -0.57
    POSITIVE LOGITS
     Khart
    1.50
     Keny
    1.40
     Juf
    1.39
     soulign
    1.33
     accla
    1.32
     simplif
    1.31
     volunte
    1.28
     confé
    1.28
     Kün
    1.27
     pleins
    1.27
    Act Density 0.242%

    No Known Activations