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

    Neuronpedia

    INDEX
    Explanations

    negative values in mathematical expressions or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.77
    Jeografia
    -0.66
    localctx
    -0.64
    WriteTagHelper
    -0.61
     CascadeType
    -0.59
    ValueStyle
    -0.59
     initComponents
    -0.56
    ंदीखरीदारी
    -0.56
    hObject
    -0.56
    uskas
    -0.56
    POSITIVE LOGITS
    -\
    1.61
     -\
    1.10
    =\
    0.98
    +\
    0.93
     himſelf
    0.85
     againſt
    0.85
     itſelf
    0.83
    )-\
    0.80
    ^{-\
    0.79
     whoſe
    0.78
    Act Density 0.145%

    No Known Activations