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

    Neuronpedia

    INDEX
    Explanations

    HTML table elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.89
    ✨:
    -0.77
    Geplaatst
    -0.73
    таратура
    -0.72
    BeginContext
    -0.69
    ByteBuf
    -0.68
    دانشنامهٔ
    -0.68
     Kaplan
    -0.66
     touch
    -0.65
    ValueGeneration
    -0.65
    POSITIVE LOGITS
    th
    1.38
    TH
    0.96
    Th
    0.83
    thu
    0.78
     Leth
    0.74
     ISNI
    0.74
     colspan
    0.67
    ths
    0.66
    thr
    0.65
     Chon
    0.63
    Act Density 0.041%

    No Known Activations