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

    Neuronpedia

    INDEX
    Explanations

    references to Nazism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andon
    -0.18
    quil
    -0.15
    itzer
    -0.15
    aiser
    -0.15
    .brand
    -0.15
    elts
    -0.15
    alar
    -0.15
    ovah
    -0.15
    edReader
    -0.14
    :animated
    -0.14
    POSITIVE LOGITS
    areth
    0.34
    ional
    0.24
    ionale
    0.22
    ionales
    0.18
     ÐĿаз
    0.17
    urally
    0.17
    daq
    0.17
    DAQ
    0.16
    arius
    0.15
    IOC
    0.15
    Act Density 0.006%

    No Known Activations