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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or sequences related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ۰۰
    -0.52
     XXX
    -0.47
     للاسماء
    -0.47
    Havolalar
    -0.46
    fromnode
    -0.45
     архивлан
    -0.44
     hundred
    -0.43
    Према
    -0.41
    IntoConstraints
    -0.41
     wide
    -0.40
    POSITIVE LOGITS
    9
    0.60
    7
    0.60
    8
    0.59
    6
    0.56
    0
    0.55
    4
    0.52
    5
    0.51
    3
    0.51
    1
    0.50
    2
    0.47
    Act Density 1.009%

    No Known Activations