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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their corresponding verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIAF
    -0.64
    LLocation
    -0.61
    Personendaten
    -0.60
    SharedDtor
    -0.56
    ModelBuilder
    -0.55
    RetentionPolicy
    -0.54
     calendriers
    -0.54
    RTLE
    -0.53
    InstrumentedTest
    -0.52
     виправивши
    -0.52
    POSITIVE LOGITS
     seldom
    0.59
     habitually
    0.59
     dare
    0.59
     usually
    0.58
     متحده
    0.55
     deliberately
    0.55
     BoxDecoration
    0.55
     rarely
    0.55
     bluntly
    0.54
     dared
    0.53
    Act Density 0.041%

    No Known Activations