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

    Neuronpedia

    INDEX
    Explanations

    repeated references to the word "these."

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

    referring to specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.82
     épaules
    -0.75
     surla
    -0.70
     lèvres
    -0.65
     vœux
    -0.64
     EconPapers
    -0.63
    findpost
    -0.60
     dieux
    -0.59
     bienfaits
    -0.56
     enfans
    -0.55
    POSITIVE LOGITS
     locations
    0.81
     areas
    0.81
     societies
    0.80
     programs
    0.77
     situations
    0.77
     kinds
    0.76
     destinations
    0.76
     companies
    0.76
     environments
    0.75
     devices
    0.75
    Act Density 0.068%

    No Known Activations