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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or potential actions in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owi
    -0.16
    çĦ¡æĸĻ
    -0.16
    ymi
    -0.15
    rz
    -0.14
    arently
    -0.14
    ORE
    -0.14
    à¤Ŀ
    -0.14
    зÑĮ
    -0.14
    usu
    -0.14
    rir
    -0.14
    POSITIVE LOGITS
     even
    0.20
    åIJ§
    0.17
     algún
    0.16
     slightly
    0.16
    bol
    0.15
     sogar
    0.15
     qualche
    0.15
     ought
    0.15
     maybe
    0.15
     indeed
    0.15
    Act Density 0.054%

    No Known Activations