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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of common pronouns and connecting words in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jo
    -0.14
    /navbar
    -0.14
    -peer
    -0.14
     Maze
    -0.13
    MMdd
    -0.13
    jos
    -0.13
     peer
    -0.13
    iors
    -0.13
    lake
    -0.13
    Æ°ng
    -0.13
    POSITIVE LOGITS
    alion
    0.17
    atürk
    0.16
    ascus
    0.15
     Perkins
    0.15
    é¡»
    0.15
    oppers
    0.14
    Ỽ
    0.14
    odic
    0.14
    chner
    0.14
    æ´²
    0.14
    Act Density 0.002%

    No Known Activations