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

    Neuronpedia

    INDEX
    Explanations

    prominent brands, names, or institutions associated with entertainment and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azo
    -0.15
    ãĥªãĤ¹
    -0.15
    aura
    -0.14
    enha
    -0.14
    θη
    -0.14
    ÑĥлÑİ
    -0.13
    Ù
    -0.13
    ewe
    -0.13
     Jako
    -0.13
    Benchmark
    -0.12
    POSITIVE LOGITS
     itself
    0.28
     herself
    0.24
     themselves
    0.19
     Himself
    0.19
     himself
    0.18
    æľ¬
    0.17
     own
    0.17
     yourself
    0.16
     aforementioned
    0.16
    èĩªå·±
    0.16
    Act Density 0.118%

    No Known Activations