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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or attention within textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ïĥη
    -0.15
    еви
    -0.14
    ndon
    -0.14
     Chapel
    -0.14
    MG
    -0.14
    èĬĻ
    -0.14
    iani
    -0.14
    ä¸ģ
    -0.13
    Ed
    -0.13
    Translated
    -0.13
    POSITIVE LOGITS
    alet
    0.17
    obao
    0.17
    orr
    0.16
    ÏģÎŃ
    0.15
    odega
    0.15
    ê°IJ
    0.15
    imony
    0.15
    arkan
    0.14
     kraj
    0.14
    ork
    0.14
    Act Density 0.001%

    No Known Activations