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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    references to military honors and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryu
    -0.69
    gypt
    -0.66
    merce
    -0.61
    PF
    -0.60
    Ku
    -0.58
    ington
    -0.58
    cock
    -0.58
    waters
    -0.57
    perse
    -0.57
    sie
    -0.56
    POSITIVE LOGITS
    ardless
    0.70
    ̶
    0.63
    istration
    0.63
     mathemat
    0.62
    ãĥĺ
    0.62
    ottesville
    0.60
     Dare
    0.58
    andise
    0.57
    agne
    0.57
     Mandatory
    0.57
    Act Density 0.308%

    No Known Activations