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

    Neuronpedia

    INDEX
    Explanations

    capitalized names or initialisms related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.19
    abouts
    -0.15
     Jennings
    -0.14
    swers
    -0.14
    oola
    -0.14
    607
    -0.14
    uncate
    -0.14
    ptype
    -0.14
    -or
    -0.13
    curacy
    -0.13
    POSITIVE LOGITS
    &A
    0.16
    &a
    0.16
    iland
    0.14
     Singleton
    0.14
    ÐŁÐļ
    0.14
     Sly
    0.13
    atat
    0.13
    &o
    0.13
    zers
    0.13
    cron
    0.13
    Act Density 0.212%

    No Known Activations