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

    Neuronpedia

    INDEX
    Explanations

    quoted dialogue or speech within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.62
    DockStyle
    -0.56
    KURZBESCHREIBUNG
    -0.55
     vPvB
    -0.54
    StoryboardSegue
    -0.54
    AsNil
    -0.53
     EClass
    -0.51
     arbitrage
    -0.51
    KindOfClass
    -0.50
     quiz
    -0.50
    POSITIVE LOGITS
    The
    0.90
    As
    0.84
    Re
    0.82
    I
    0.82
    At
    0.81
    All
    0.80
    A
    0.79
    And
    0.78
    An
    0.78
    No
    0.78
    Act Density 1.360%

    No Known Activations