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

    Neuronpedia

    INDEX
    Explanations

    start tokens in a text, often indicating the beginning of a new segment or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dynamically
    -0.45
    gha
    -0.44
     technically
    -0.43
     dri
    -0.43
    luke
    -0.43
    AddAttribute
    -0.42
    lons
    -0.42
    ENSIS
    -0.41
    claimer
    -0.41
     dynamic
    -0.41
    POSITIVE LOGITS
    InstrumentedTest
    0.93
    #+#
    0.85
    पया
    0.79
    الإنجليزية
    0.78
    SequentialGroup
    0.77
     '\\;'
    0.77
     <>",
    0.77
     MonoBehaviour
    0.76
    Autoritní
    0.75
    Personensuche
    0.75
    Act Density 0.016%

    No Known Activations