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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly in the context of authority or expert opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    598
    -0.15
    Ask
    -0.14
    ask
    -0.14
    urus
    -0.14
    ulsion
    -0.14
    ulus
    -0.14
    569
    -0.14
    annie
    -0.13
    FP
    -0.13
    mar
    -0.13
    POSITIVE LOGITS
     said
    0.28
     added
    0.28
    added
    0.25
    .scalablytyped
    0.22
     Added
    0.21
    -added
    0.21
    said
    0.20
    Added
    0.19
     Said
    0.18
    continued
    0.18
    Act Density 0.031%

    No Known Activations