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

    Neuronpedia

    INDEX
    Explanations

    mentions of political leadership and judicial authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auffi
    -1.07
     Monfieur
    -0.96
     Efq
    -0.94
     ſtate
    -0.91
     itſelf
    -0.91
     myſelf
    -0.91
     iſt
    -0.89
     Jefus
    -0.88
     ſind
    -0.87
     faſt
    -0.87
    POSITIVE LOGITS
    <eos>
    0.68
    lawayo
    0.58
     …
    0.55
     […]
    0.54
     “
    0.53
     P
    0.52
     M
    0.51
     V
    0.49
     Le
    0.49
     ...
    0.48
    Act Density 0.106%

    No Known Activations