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

    Neuronpedia

    INDEX
    Explanations

    terms associated with breaking or cracking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    crack, jokes, reactor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.57
    ﷺ
    -0.40
    AddTagHelper
    -0.36
    原始内容存档于
    -0.35
     IService
    -0.35
    Rujuakan
    -0.35
     pere
    -0.35
    lijf
    -0.34
    Kanpo
    -0.34
     hort
    -0.34
    POSITIVE LOGITS
     cracked
    1.35
     crack
    1.32
     cracking
    1.31
     Cracking
    1.23
    crack
    1.22
    cracked
    1.18
    Crack
    1.13
     Crack
    1.13
     CRACK
    1.11
     cracks
    1.02
    Act Density 0.009%

    No Known Activations