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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attends to the second token in mathematical equations from the first token in the previous sentences or components.

    oai_attention-head · gpt-4o-miniTriggered by @pigeonzow
    New Auto-Interp
    Negative Logits
    --)
    -0.50
     виправивши
    -0.48
    _;
    -0.46
    '`
    -0.45
    =@"
    -0.45
    béco
    -0.42
     }),
    -0.42
     applications
    -0.42
    näm
    -0.42
     hiệp
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    1.07
    Geplaatst
    0.87
     Roskov
    0.85
    DockStyle
    0.75
    paign
    0.70
     InputDecoration
    0.69
    CodedInputStream
    0.68
     consultato
    0.67
    complexContent
    0.66
     ChromeDriver
    0.66
    Act Density 1.132%

    No Known Activations