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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or categorizations of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çļĦä¸Ģ个
    -0.19
    umont
    -0.16
    velle
    -0.15
    .range
    -0.14
    heed
    -0.14
    otts
    -0.14
    ìĿ´ìķ¼
    -0.14
    affles
    -0.14
    lington
    -0.14
    irts
    -0.14
    POSITIVE LOGITS
     respectively
    0.40
     respective
    0.27
     alike
    0.26
    åĪĨåĪ«
    0.24
     ÑģооÑĤвеÑĤ
    0.22
     ê°ģê°ģ
    0.22
     모ëijIJ
    0.21
    among
    0.21
     among
    0.21
     keys
    0.21
    Act Density 0.261%

    No Known Activations