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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.63
    +#+#
    -0.63
    LookAnd
    -0.62
     שוליים
    -0.56
    licité
    -0.54
    ValueStyle
    -0.51
    .*")]
    -0.51
    庁
    -0.50
    RegistryLite
    -0.50
    ThroughAttribute
    -0.48
    POSITIVE LOGITS
     cannot
    2.49
    cannot
    2.21
     Cannot
    2.08
    Cannot
    2.02
     cant
    1.99
     couldn
    1.88
     CANNOT
    1.81
     unable
    1.80
     inability
    1.66
    cant
    1.65
    Act Density 0.644%

    No Known Activations