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

    Neuronpedia

    INDEX
    Explanations

    themes related to governance, law, and authority structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tees
    -0.15
    orca
    -0.15
    ãĥ¢ãĥ³
    -0.14
    _Checked
    -0.14
    throp
    -0.14
    iyim
    -0.14
    xdc
    -0.13
     geile
    -0.13
    udas
    -0.13
    inho
    -0.13
    POSITIVE LOGITS
    bes
    0.16
     Challenger
    0.15
     weights
    0.15
    atabase
    0.15
     wil
    0.14
     vacuum
    0.14
     mar
    0.14
     Forum
    0.13
    æļ
    0.13
    forum
    0.13
    Act Density 0.129%

    No Known Activations