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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax related to mathematical expressions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </blockquote>
    -0.78
    </h2>
    -0.43
    DockStyle
    -0.38
    </h5>
    -0.38
     Paglinawan
    -0.37
    ));
    -0.36
     Pol
    -0.36
    توض
    -0.35
    oneofs
    -0.35
     Bus
    -0.34
    POSITIVE LOGITS
     }^{
    1.19
     }^{\
    1.08
     }^{*}$
    0.94
     }^{(
    0.91
     }_{
    0.91
     }^{*
    0.90
     }^{*}
    0.90
     }^{[
    0.85
     }_{\
    0.84
     }^{-
    0.84
    Act Density 0.236%

    No Known Activations