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

    Neuronpedia

    INDEX
    Explanations

    phrases related to readability and the act of reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igner
    -0.18
    ug
    -0.16
    usc
    -0.15
    ster
    -0.15
    ye
    -0.15
    243
    -0.14
    cf
    -0.14
     flavors
    -0.14
    give
    -0.14
    ad
    -0.14
    POSITIVE LOGITS
    bourg
    0.18
    ults
    0.17
    alie
    0.17
    ÑĤÑĢо
    0.16
    .mit
    0.16
    logen
    0.15
    achte
    0.15
    atform
    0.15
    _deinit
    0.15
     fisse
    0.14
    Act Density 0.024%

    No Known Activations