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

    Neuronpedia

    INDEX
    Explanations

    expressions related to ambiguity and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pro
    -0.15
     ÙħتÙĨ
    -0.15
    CKER
    -0.15
    INK
    -0.14
     uncomp
    -0.14
    quisite
    -0.14
     ofs
    -0.14
    aña
    -0.14
     strictly
    -0.13
     process
    -0.13
    POSITIVE LOGITS
    olla
    0.17
    ottle
    0.16
    fuse
    0.15
    arda
    0.15
    oulos
    0.14
    asil
    0.14
    漫
    0.14
    rie
    0.14
    itto
    0.14
    ogany
    0.14
    Act Density 0.032%

    No Known Activations