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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to historical figures or events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical terms and figures related to the German Reich

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neau
    -0.70
    glers
    -0.68
    plates
    -0.66
    gdala
    -0.66
    BILITY
    -0.65
    ABLE
    -0.65
    ulton
    -0.64
    ctica
    -0.64
    ocre
    -0.64
     Tibetan
    -0.62
    POSITIVE LOGITS
    stein
    0.87
    sb
    0.85
    hardt
    0.85
    lich
    0.84
     Reich
    0.84
    swer
    0.84
    enegger
    0.79
    sle
    0.76
    itzer
    0.76
     decree
    0.75
    Act Density 0.025%

    No Known Activations