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

    Neuronpedia

    INDEX
    Explanations

    references to secret agents or espionage within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡ÃŃ
    -0.17
    entar
    -0.16
    inqu
    -0.14
     Stretch
    -0.14
    emark
    -0.14
    .motion
    -0.14
     McGregor
    -0.14
    Stretch
    -0.14
     maduras
    -0.13
     mindful
    -0.13
    POSITIVE LOGITS
    (M
    0.26
     MM
    0.24
     MMM
    0.23
    .MM
    0.23
     MT
    0.23
     MB
    0.21
    |M
    0.21
    [M
    0.21
    /MM
    0.20
     MU
    0.20
    Act Density 0.076%

    No Known Activations