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

    Neuronpedia

    INDEX
    Explanations

    references to historical political figures and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NATO
    -0.16
    abyrin
    -0.15
    apos
    -0.14
    ikki
    -0.14
    pls
    -0.14
    ibil
    -0.14
    ikit
    -0.14
    ivation
    -0.14
    à¥Ģà¤ķरण
    -0.14
    aspers
    -0.13
    POSITIVE LOGITS
     Gand
    0.28
     Independence
    0.25
     Gandhi
    0.24
     Quit
    0.23
     freedom
    0.23
     Freedom
    0.23
     Partition
    0.22
    Partition
    0.21
     Neh
    0.21
     Congress
    0.20
    Act Density 0.077%

    No Known Activations