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

    Neuronpedia

    INDEX
    Explanations

    references to performance evaluations and societal criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »
    -0.16
    TimeString
    -0.15
     hers
    -0.15
    arent
    -0.14
     زÙĨÛĮ
    -0.14
    .readString
    -0.14
     person
    -0.13
    ushima
    -0.13
    ardo
    -0.13
    ä¸Ģ个人
    -0.13
    POSITIVE LOGITS
     these
    0.44
    these
    0.36
    è¿ĻäºĽ
    0.36
     them
    0.31
    These
    0.29
     those
    0.29
    éĤ£äºĽ
    0.29
     These
    0.28
     ÑįÑĤиÑħ
    0.26
     THESE
    0.26
    Act Density 0.669%

    No Known Activations