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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FromClass
    -0.15
    asper
    -0.14
    igsaw
    -0.14
    ulous
    -0.14
    starter
    -0.14
    iaz
    -0.14
    DEC
    -0.13
     Sle
    -0.13
    pq
    -0.13
    _tc
    -0.13
    POSITIVE LOGITS
    .updateDynamic
    0.17
    edd
    0.16
    apı
    0.15
    809
    0.15
     Shib
    0.14
    779
    0.14
    дÑĸл
    0.14
     sobie
    0.14
    835
    0.14
     ìĭ¤í
    0.14
    Act Density 1.076%

    No Known Activations