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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases denoting choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swer
    -0.16
    eyi
    -0.14
    gle
    -0.14
    elez
    -0.14
    gles
    -0.14
    Ľ
    -0.14
    å¢
    -0.13
    δα
    -0.13
    ahun
    -0.13
    Å¡em
    -0.13
    POSITIVE LOGITS
     more
    0.43
     MORE
    0.34
     less
    0.33
    more
    0.32
    æĽ´å¤ļ
    0.31
     More
    0.29
    -more
    0.29
    _more
    0.29
    .more
    0.29
     lebih
    0.28
    Act Density 0.041%

    No Known Activations