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

    Neuronpedia

    INDEX
    Explanations

    references to democracy and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gonic
    -0.67
    KEYCODE
    -0.64
    weeted
    -0.63
     SAE
    -0.61
    tvguidetime
    -0.60
    سك
    -0.60
    期刊论文
    -0.58
     Lovell
    -0.58
    //
    -0.58
    =>'
    -0.57
    POSITIVE LOGITS
     democracy
    0.93
     West
    0.86
    West
    0.83
     Democracy
    0.65
    RTLI
    0.65
     WEST
    0.61
     ویکی‌پدیا
    0.60
    ềm
    0.59
    WEST
    0.57
     defaultstate
    0.57
    Act Density 0.052%

    No Known Activations