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

    Neuronpedia

    INDEX
    Explanations

    unique symbols or special characters within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BMW
    -0.14
     FBI
    -0.14
    mán
    -0.14
     MSNBC
    -0.13
     (“
    -0.13
     CBS
    -0.13
     MTV
    -0.13
     Maui
    -0.13
     Mormon
    -0.12
    gmt
    -0.12
    POSITIVE LOGITS
     libr
    0.31
     Libraries
    0.29
     libraries
    0.29
     Open
    0.28
     librarian
    0.27
     library
    0.27
     Library
    0.26
     repositories
    0.25
    Open
    0.25
    libraries
    0.25
    Act Density 0.003%

    No Known Activations