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

    Neuronpedia

    INDEX
    Explanations

    variables and mathematical notation within complex mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <u>
    -1.11
     أيضاً
    -0.78
    �
    -0.73
    LOGGER
    -0.70
    ===
    -0.68
    【
    -0.68
     ${{
    -0.66
    باً
    -0.65
     【
    -0.64
    ماً
    -0.64
    POSITIVE LOGITS
    ^
    1.25
    }^
    1.09
    }_
    1.05
    '^
    1.01
    )^
    0.98
    _
    0.97
     ^
    0.96
    ]^
    0.96
    }}^
    0.92
    }}_
    0.91
    Act Density 2.118%

    No Known Activations