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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oubles
    -0.16
    _almost
    -0.15
    ymm
    -0.15
    utdown
    -0.15
    ongoose
    -0.13
    oldem
    -0.13
    =title
    -0.13
    åŀ
    -0.13
    æĺİçĻ½
    -0.13
    tual
    -0.13
    POSITIVE LOGITS
    ä¸įçŁ¥éģĵ
    0.40
     don
    0.37
     unknown
    0.32
     descon
    0.32
    unknown
    0.31
    don
    0.31
     doesn
    0.29
     unsure
    0.29
     Don
    0.29
     DON
    0.29
    Act Density 0.281%

    No Known Activations