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

    Neuronpedia

    INDEX
    Explanations

    blanks or fill-in-the-blank structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oz
    -0.15
    ãĥªãĥ¼ãĤº
    -0.14
     EXEMPLARY
    -0.14
     Heading
    -0.14
    .liferay
    -0.14
    erge
    -0.14
    *sp
    -0.14
    ادÙĬ
    -0.14
     gep
    -0.13
    ahun
    -0.13
    POSITIVE LOGITS
    vore
    0.18
    ela
    0.15
    utton
    0.15
     horns
    0.15
    mage
    0.14
     demi
    0.14
    ptom
    0.14
    pler
    0.14
    .NewRequest
    0.14
    722
    0.13
    Act Density 0.005%

    No Known Activations