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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ar"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.87
    ¬¼
    -0.79
    stakes
    -0.77
    eners
    -0.74
    ãģį
    -0.74
    hower
    -0.69
    ĨĴ
    -0.68
    iculty
    -0.65
    sylvania
    -0.63
     sterling
    -0.62
    POSITIVE LOGITS
    beit
    1.15
    ansas
    1.09
    issa
    1.08
    ithmetic
    1.06
    rival
    1.01
    thritis
    0.98
    leigh
    0.98
    lington
    0.97
    rington
    0.95
    ranging
    0.95
    Act Density 0.023%

    No Known Activations