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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating difficulty or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ddit
    -0.15
    onom
    -0.15
    uko
    -0.14
    ppers
    -0.14
    undy
    -0.14
    utomation
    -0.14
    pper
    -0.13
    abet
    -0.13
    inalg
    -0.13
    intl
    -0.13
    POSITIVE LOGITS
    729
    0.16
    enton
    0.14
    ehen
    0.14
    æ£ļ
    0.14
     prelim
    0.14
    zew
    0.13
     Mall
    0.13
     è©ķ価
    0.13
    akh
    0.13
    833
    0.13
    Act Density 0.056%

    No Known Activations