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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving parentheses and certain symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    νή
    -0.52
    ellyn
    -0.50
    vencia
    -0.49
     sint
    -0.45
     bao
    -0.45
    ssons
    -0.43
     thứ
    -0.42
    по
    -0.42
    resión
    -0.42
    pertise
    -0.42
    POSITIVE LOGITS
    ">)</
    1.18
    ())))
    1.17
    ')))
    1.17
    ")))
    1.16
    )))
    1.16
    )))
    1.13
    })),
    1.12
    ))
    1.11
    )])
    1.10
    ]))
    1.10
    Act Density 1.073%

    No Known Activations