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

    Neuronpedia

    INDEX
    Explanations

    references to national governance and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veloper
    -0.16
     Cent
    -0.15
    Cent
    -0.15
    æķı
    -0.15
    ç´
    -0.14
     Conserv
    -0.14
     Flame
    -0.14
    cent
    -0.14
    zÄĻ
    -0.14
     Pun
    -0.14
    POSITIVE LOGITS
    ãģª
    0.15
    nak
    0.15
    oman
    0.15
    igrams
    0.14
    rove
    0.14
    swer
    0.14
     ãĥ«
    0.14
     ÄIJÃłi
    0.14
    omo
    0.14
    av
    0.14
    Act Density 0.039%

    No Known Activations