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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ei
    -0.17
    anness
    -0.17
    ìĸ¼
    -0.16
    riger
    -0.15
    åĭ¢
    -0.15
    erk
    -0.15
    rne
    -0.15
    erator
    -0.15
    rk
    -0.15
    rtype
    -0.14
    POSITIVE LOGITS
    lessly
    0.31
    less
    0.25
     whether
    0.24
    ful
    0.23
    full
    0.23
    fulness
    0.22
    /question
    0.21
     Whether
    0.20
     Doub
    0.20
    whether
    0.20
    Act Density 0.025%

    No Known Activations