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

    Neuronpedia

    INDEX
    Explanations

    concepts related to uncertainty and stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    قاط
    -0.59
    CodeAnalysis
    -0.54
     uñas
    -0.53
     tár
    -0.52
     tailles
    -0.50
    chee
    -0.50
    Separate
    -0.47
    report
    -0.46
     Separate
    -0.45
     verho
    -0.45
    POSITIVE LOGITS
     uncertainty
    1.01
    complexContent
    0.91
     الحره
    0.91
     instability
    0.90
     Uncertainty
    0.90
    Uncertainty
    0.90
    uncertainty
    0.89
     nahilalakip
    0.88
     stability
    0.84
     predictability
    0.83
    Act Density 0.299%

    No Known Activations