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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations related to complex equations or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.88
    rimidine
    -0.81
    IUrlHelper
    -0.80
     Jarvis
    -0.79
    ]^{
    -0.78
     propOrder
    -0.76
    CTX
    -0.76
    \}^{
    -0.74
     Grau
    -0.73
     Maitland
    -0.72
    POSITIVE LOGITS
    ^{\
    2.00
     }^{\
    1.77
    )^{\
    1.69
    }^{\
    1.68
     ^{\
    1.34
     }}^{\
    1.28
    }}^{\
    1.27
    ]^{\
    1.27
     $^{\
    1.06
    $^{\
    1.05
    Act Density 0.232%

    No Known Activations