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

    Neuronpedia

    INDEX
    Explanations

    references to official organizations and chapters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    омен
    -0.16
    Łèĥ½
    -0.16
    unta
    -0.16
    erif
    -0.15
    дам
    -0.15
    jah
    -0.14
    arto
    -0.14
    itch
    -0.14
    sj
    -0.14
    ppe
    -0.14
    POSITIVE LOGITS
    redentials
    0.15
    osaur
    0.14
     Quinn
    0.14
     spies
    0.14
    езд
    0.14
    bach
    0.14
    eba
    0.14
    ted
    0.14
    ched
    0.14
     Edition
    0.14
    Act Density 0.070%

    No Known Activations