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

    Neuronpedia

    INDEX
    Explanations

    patterns of ending punctuation in mathematical expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gai
    -0.54
     jadi
    -0.52
     til
    -0.52
     mes
    -0.51
     Levine
    -0.50
     qua
    -0.49
     wa
    -0.49
     da
    -0.47
     stric
    -0.47
     hum
    -0.46
    POSITIVE LOGITS
    )$
    2.61
    \}$
    1.82
    ]$
    1.66
    )$}
    1.47
    )$,
    1.37
     )$
    1.33
    )]$
    1.29
    )$-
    1.28
    )\}$
    1.28
    ))$
    1.19
    Act Density 0.160%

    No Known Activations