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

    Neuronpedia

    INDEX
    Explanations

    terms associated with craftsmanship and quality in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after commas

    np_acts-logits-general · gemini-2.0-flash

    time reference and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))$.
    -0.91
    ?).
    -0.90
     }}$.
    -0.90
    "].
    -0.88
    ).\\
    -0.84
     ""))
    -0.83
    ?”.
    -0.82
    })$.
    -0.82
    ?".
    -0.82
    ]."
    -0.81
    POSITIVE LOGITS
    ,
    1.26
     but
    0.94
     והוא
    0.89
     so
    0.74
     and
    0.70
     because
    0.70
    されており
    0.68
     whereas
    0.67
    があり
    0.67
     which
    0.67
    Act Density 2.064%

    No Known Activations