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

    Neuronpedia

    INDEX
    Explanations

    phrases that characterize unique and exceptional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.32
    æĺ¯ä¸Ģ个
    -0.18
     its
    -0.18
     Ñıке
    -0.16
     Loose
    -0.15
    erea
    -0.15
    inder
    -0.15
    æĺ¯ä¸ª
    -0.15
     Its
    -0.15
     Noon
    -0.15
    POSITIVE LOGITS
     themselves
    0.51
     thems
    0.26
     their
    0.22
    Their
    0.20
     are
    0.20
     aren
    0.19
     Their
    0.19
    their
    0.19
     leurs
    0.18
     Ñģами
    0.17
    Act Density 0.530%

    No Known Activations