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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or specific symbols commonly used in mathematical or formal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Menon
    -0.74
     Mann
    -0.72
    FACT
    -0.71
     EdgeInsets
    -0.71
    zhou
    -0.69
     بيها
    -0.66
     Morrison
    -0.65
     bottom
    -0.65
    cilla
    -0.64
     man
    -0.64
    POSITIVE LOGITS
    expandindo
    1.25
    )),
    1.22
    ]),
    1.21
    ()),
    1.19
    ),
    1.19
    >),
    1.18
    ])),
    1.17
    }),
    1.16
    ))),
    1.12
    ])):
    1.10
    Act Density 0.222%

    No Known Activations