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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or claims that are not verified

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.16
     sanki
    -0.16
     пÑĢедпол
    -0.15
    emean
    -0.15
    erner
    -0.15
    imensional
    -0.14
    мовÑĸÑĢ
    -0.14
    fen
    -0.14
    acre
    -0.14
     reputed
    -0.14
    POSITIVE LOGITS
    mente
    0.23
    LY
    0.21
    ly
    0.19
    forth
    0.19
     never
    0.18
    ably
    0.18
    ance
    0.18
    ;y
    0.17
    ily
    0.17
    cy
    0.17
    Act Density 0.050%

    No Known Activations