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

    Neuronpedia

    INDEX
    Explanations

    statements expressing uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olute
    -0.15
     unofficial
    -0.15
    itis
    -0.14
    .hxx
    -0.14
    æĺİçĻ½
    -0.14
     interim
    -0.14
     attract
    -0.14
    IES
    -0.14
    è«ĸ
    -0.14
    ymm
    -0.13
    POSITIVE LOGITS
     hadn
    0.37
     ignorance
    0.35
     never
    0.35
    ä¸įçŁ¥éģĵ
    0.33
     unaware
    0.33
     ignorant
    0.32
     descon
    0.28
     unfamiliar
    0.27
     Never
    0.27
     haven
    0.27
    Act Density 0.268%

    No Known Activations