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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "where."

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

    clauses introduced by "where"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.56
    참고
    -0.53
     CommonModule
    -0.47
     PagesJaunes
    -0.46
     River
    -0.46
     MES
    -0.46
     चीज़ों
    -0.45
     river
    -0.43
     BU
    -0.43
     comprom
    -0.43
    POSITIVE LOGITS
     חיצוניים
    0.54
     Bewußt
    0.53
     soñar
    0.52
     juridiques
    0.52
     embarazadas
    0.48
     duquel
    0.47
    GraphicsUnit
    0.47
     Rücks
    0.46
     Chwiliwch
    0.45
     Gewerks
    0.45
    Act Density 0.030%

    No Known Activations