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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation related to subscripts and superscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.74
    rubin
    -0.73
     MOC
    -0.73
    }_{
    -0.68
     Mendez
    -0.67
    DPI
    -0.67
     Waugh
    -0.66
     McMillan
    -0.65
    ########.
    -0.65
     Greenberg
    -0.65
    POSITIVE LOGITS
    _{\
    2.07
     }_{\
    1.70
    )_{\
    1.57
    }_{\
    1.57
     _{\
    1.47
    }}_{\
    1.33
    ]_{\
    1.19
    \|_{\
    1.16
     $_{\
    1.05
    |_{\
    0.95
    Act Density 0.325%

    No Known Activations