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

    Neuronpedia

    INDEX
    Explanations

    references to diplomatic or international agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XF
    -0.15
     Äij
    -0.15
     tam
    -0.15
    antha
    -0.15
    setDefault
    -0.15
     kn
    -0.15
     ‘
    -0.14
     Ting
    -0.14
     pon
    -0.14
     flo
    -0.14
    POSITIVE LOGITS
    adem
    0.15
    еÑģÑı
    0.15
    sse
    0.15
    plib
    0.14
    олÑİ
    0.14
     Pavilion
    0.14
    ãĥĪãĥ«
    0.14
     Rubin
    0.14
    NCY
    0.14
     ($("#
    0.14
    Act Density 0.521%

    No Known Activations