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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to societal divisions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sort
    -0.20
    们
    -0.14
    ãģªãģĮãĤī
    -0.14
    ãģĭãģ®
    -0.14
     Solve
    -0.13
    :eq
    -0.13
    ãģĭ
    -0.13
    ÅĻaz
    -0.12
    ãģ¾ãģŁ
    -0.12
    ãģ¨ãģ¯
    -0.12
    POSITIVE LOGITS
     which
    1.30
    which
    1.09
     Which
    0.96
     WHICH
    0.92
    Which
    0.90
     wich
    0.77
    .which
    0.72
     cui
    0.67
     które
    0.64
     który
    0.63
    Act Density 1.564%

    No Known Activations