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

    Neuronpedia

    INDEX
    Explanations

    statements about events and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.93
    IndentedString
    -0.90
    RegressionTest
    -0.80
    astify
    -0.80
     nakalista
    -0.76
     createState
    -0.71
     Réponses
    -0.68
    modelBuilder
    -0.67
    ніципалі
    -0.67
    abetes
    -0.65
    POSITIVE LOGITS
     about
    1.87
    about
    1.34
     ABOUT
    1.19
     About
    1.16
     tentang
    1.16
    About
    1.15
     aimed
    1.03
     meant
    0.96
    关于
    0.96
     intended
    0.95
    Act Density 0.395%

    No Known Activations