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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political structures and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outright
    -0.16
    chal
    -0.15
    ormsg
    -0.15
    ammed
    -0.14
     Walter
    -0.14
    oten
    -0.14
    æº
    -0.14
    dia
    -0.14
    ihil
    -0.14
    oleon
    -0.13
    POSITIVE LOGITS
    aldi
    0.15
     cul
    0.15
    oley
    0.14
    inton
    0.14
     Bridges
    0.14
    Monkey
    0.13
     Invest
    0.13
     Bris
    0.13
    _EXTRA
    0.13
    æķ·
    0.13
    Act Density 0.102%

    No Known Activations