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

    Neuronpedia

    INDEX
    Explanations

    phrases related to division or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekler
    -0.17
    igy
    -0.16
    worthy
    -0.15
     Ding
    -0.15
    kal
    -0.14
     footh
    -0.14
     Kerr
    -0.14
    ÏĥÏĦα
    -0.14
     Citadel
    -0.14
    full
    -0.14
    POSITIVE LOGITS
    ÙĪزÛĮ
    0.16
    ongyang
    0.16
    arus
    0.16
    orus
    0.16
     macros
    0.15
    aurus
    0.15
    å¦Ĥä¸ĭ
    0.15
     levels
    0.14
    .react
    0.14
    ButtonType
    0.14
    Act Density 0.049%

    No Known Activations