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

    Neuronpedia

    INDEX
    Explanations

    phrases that express curiosity or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.17
    aina
    -0.15
    emon
    -0.14
    á¹
    -0.14
    ear
    -0.14
    ienia
    -0.13
    GIN
    -0.13
    _DR
    -0.13
    DEX
    -0.13
    igner
    -0.13
    POSITIVE LOGITS
    æģ¯
    0.16
    ATEGORIES
    0.14
    upo
    0.14
    quete
    0.14
    ington
    0.14
    zeÅĦ
    0.14
     Tato
    0.14
    ckett
    0.14
    /tiny
    0.13
    æľīä»Ģä¹Ī
    0.13
    Act Density 0.019%

    No Known Activations