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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astify
    -0.72
    SharedCtor
    -0.64
    Datuak
    -0.58
    xFFFFFF
    -0.55
    nalités
    -0.54
    OrCreate
    -0.52
    urfs
    -0.50
     ods
    -0.49
    Itoa
    -0.49
    indelijk
    -0.47
    POSITIVE LOGITS
     miſ
    0.62
    PhysRev
    0.59
     diſt
    0.58
     marié
    0.57
     ſmall
    0.57
     vertes
    0.56
     Ανακτήθηκε
    0.56
    Билгалдахарш
    0.56
     juſt
    0.56
     cinematogra
    0.56
    Act Density 0.108%

    No Known Activations