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

    Neuronpedia

    INDEX
    Explanations

    references to murders and assassinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awning
    -0.15
    /Application
    -0.13
    sey
    -0.13
    PCS
    -0.13
    ofs
    -0.13
    मत
    -0.13
     Alexis
    -0.13
    ilan
    -0.13
     Sesso
    -0.13
    quine
    -0.13
    POSITIVE LOGITS
    ardware
    0.15
    inize
    0.15
    OpenHelper
    0.14
    licken
    0.14
    -peer
    0.14
     Matrix
    0.14
    rios
    0.13
     zast
    0.13
    arding
    0.13
    Merge
    0.13
    Act Density 0.048%

    No Known Activations