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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values and their relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers ending in and or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
     pinulongan
    -0.56
    hyrchwyd
    -0.52
    stylers
    -0.52
    Kjelder
    -0.52
     gyhoeddwyd
    -0.50
     الرياضيه
    -0.50
     tabPage
    -0.49
    NameInMap
    -0.48
     désolés
    -0.48
    POSITIVE LOGITS
     maupun
    0.37
     Italij
    0.37
    InSection
    0.36
     šte
    0.35
     Aralık
    0.35
     zuletzt
    0.35
     picioare
    0.35
    GOTREF
    0.34
    følgelig
    0.34
    OrEqual
    0.34
    Act Density 0.263%

    No Known Activations