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

    Neuronpedia

    INDEX
    Explanations

    references to the second person "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    can
    -0.55
     may
    -0.52
     will
    -0.52
     might
    -0.51
     can
    -0.46
    ).
    -0.45
    ‘
    -0.42
    -
    -0.42
    )
    -0.42
    <eos>
    -0.42
    POSITIVE LOGITS
    UserScript
    1.13
    Tikang
    0.99
    UnitTesting
    0.98
    LabelTagHelper
    0.94
    localctx
    0.94
     يتيمه
    0.93
    AsUp
    0.93
    SharedDtor
    0.92
    ValueStyle
    0.91
     cherchés
    0.91
    Act Density 0.090%

    No Known Activations