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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "Bastard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    анÑĤаж
    -0.17
    alet
    -0.17
    æ°¸ä¹ħ
    -0.16
    دÛĮ
    -0.16
    aal
    -0.16
    itaire
    -0.15
    aft
    -0.15
    rý
    -0.14
    ract
    -0.14
    crets
    -0.14
    POSITIVE LOGITS
    ardu
    0.21
    eful
    0.21
    ürk
    0.21
    rop
    0.20
    urma
    0.20
    efully
    0.19
    ard
    0.19
    ech
    0.19
    ogne
    0.19
    ards
    0.19
    Act Density 0.014%

    No Known Activations