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

    Neuronpedia

    INDEX
    Explanations

    expressions of criticism towards societal norms and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    бÑĭ
    -0.15
    ycz
    -0.15
     ÙħÙĨÙĩ
    -0.15
    uche
    -0.15
    ilar
    -0.14
    داد
    -0.14
    ongyang
    -0.14
    ooo
    -0.14
     canh
    -0.14
    μοί
    -0.13
    POSITIVE LOGITS
     ones
    0.16
    inson
    0.15
    olk
    0.15
    erus
    0.14
    eria
    0.14
    ãĥ³ãĤº
    0.14
    TA
    0.13
     Lup
    0.13
     Lob
    0.13
    ones
    0.13
    Act Density 0.519%

    No Known Activations