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

    Neuronpedia

    INDEX
    Explanations

    statements about generalizations or common experiences across various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĤе
    -0.15
    ainless
    -0.15
    laz
    -0.14
    ioned
    -0.14
    iate
    -0.14
    agra
    -0.14
    óg
    -0.13
    ilo
    -0.13
     Neh
    -0.13
    enas
    -0.13
    POSITIVE LOGITS
    ÙħاÙĨ
    0.16
    ãĤ´ãĥª
    0.16
    ãģĸ
    0.15
    ména
    0.14
    ÑĢоп
    0.13
     ÑħоÑĤел
    0.13
    canf
    0.13
    /svg
    0.13
    ARING
    0.13
     bufio
    0.13
    Act Density 0.225%

    No Known Activations