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

    Neuronpedia

    INDEX
    Explanations

    quantitative data points related to visitors, fatality rates, and organizational meeting metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pong
    -0.16
    acey
    -0.16
    addir
    -0.15
    lew
    -0.14
    immel
    -0.14
    OLON
    -0.14
    ium
    -0.14
    .Selenium
    -0.14
     Driving
    -0.13
    umlu
    -0.13
    POSITIVE LOGITS
     each
    0.32
     per
    0.32
     every
    0.30
    æ¯ı
    0.27
     má»Ĺi
    0.25
     æ¯ı
    0.25
     annually
    0.25
     chaque
    0.24
    each
    0.24
    every
    0.23
    Act Density 0.131%

    No Known Activations