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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social or political controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    SpaceEngineers
    -0.69
    BOX
    -0.69
     Mothers
    -0.67
    ²¾
    -0.66
    BOOK
    -0.65
     Wolves
    -0.63
     Rubin
    -0.63
    meal
    -0.63
    xon
    -0.62
    POSITIVE LOGITS
    irming
    1.38
    luence
    1.32
    ront
    1.28
    ixed
    1.21
    liction
    1.17
    irms
    1.09
    irmed
    1.07
    icion
    1.05
    ording
    1.03
    irm
    0.96
    Act Density 0.011%

    No Known Activations