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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.93
    FunctionFlags
    -0.91
    FieldBuilder
    -0.91
    #
    -0.88
    /**
    -0.88
     <<<<<<<<<<<<<<
    -0.87
     дописавши
    -0.85
    Personendaten
    -0.85
     Мексичка
    -0.84
    rawDesc
    -0.84
    POSITIVE LOGITS
    ↵
    0.65
    ↵↵
    0.58
     […]
    0.52
    ...
    0.52
     St
    0.45
     ...
    0.45
    </blockquote>
    0.43
    ,
    0.43
     \
    0.40
     and
    0.39
    Act Density 0.182%

    No Known Activations