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

    Neuronpedia

    INDEX
    Explanations

    sentences and phrases that include casual conversational elements or informal speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.83
     betweenstory
    -0.81
     فريبيس
    -0.68
    Personendaten
    -0.67
    ReusableCell
    -0.63
    DispatchToProps
    -0.63
    PhysRevLett
    -0.62
     campagnes
    -0.55
     Тогда
    -0.54
     dagegen
    -0.54
    POSITIVE LOGITS
     Enjoy
    1.39
    Enjoy
    1.37
     hope
    1.37
     enjoy
    1.29
    enjoy
    1.18
     sorry
    1.11
     Hope
    1.09
     ENJOY
    1.09
     apologies
    1.07
     please
    1.07
    Act Density 0.361%

    No Known Activations