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

    Neuronpedia

    INDEX
    Explanations

    numerical values, specifically those related to years or dates

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

    years starting with 191

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.65
    tvguidetime
    -0.62
     FontWeight
    -0.60
    uxxxx
    -0.57
     informée
    -0.55
    ⤹
    -0.54
     PagesJaunes
    -0.52
    Erreferentziak
    -0.52
     dAtA
    -0.51
    exclu
    -0.50
    POSITIVE LOGITS
     WWI
    0.59
    大正
    0.44
     wartime
    0.44
     Kriegs
    0.39
     oorlog
    0.35
    istice
    0.34
     المعيارى
    0.34
    PRESA
    0.33
    WW
    0.33
     Iraqi
    0.32
    Act Density 0.016%

    No Known Activations