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

    Neuronpedia

    INDEX
    Explanations

    frequent references to "the" and other possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !("{}",
    -0.37
     épaules
    -0.36
     específicas
    -0.34
     razu
    -0.33
     Woche
    -0.33
    สม
    -0.33
    ⋱
    -0.33
     nombreuses
    -0.32
     vetro
    -0.32
     Brunnen
    -0.32
    POSITIVE LOGITS
    SourceChecksum
    0.87
     autorytatywna
    0.68
     protoimpl
    0.57
    modelBuilder
    0.54
     queſta
    0.53
    InstrumentedTest
    0.50
     Autorisations
    0.50
     nonatomic
    0.49
     transférez
    0.48
    Parcelize
    0.48
    Act Density 0.527%

    No Known Activations