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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that are not typical alphabetical or numerical characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ież
    -0.14
    loy
    -0.14
     loyal
    -0.14
    unden
    -0.14
     Barnett
    -0.14
     Saturn
    -0.13
     Cub
    -0.13
     Bombay
    -0.13
    é®
    -0.12
     loyalty
    -0.12
    POSITIVE LOGITS
     FO
    0.35
    FO
    0.26
     Fo
    0.26
     Freedom
    0.24
     dataset
    0.22
     Lost
    0.22
     Dataset
    0.22
    Fo
    0.21
    Freedom
    0.21
     freedom
    0.20
    Act Density 0.003%

    No Known Activations