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
    __':
    -0.91
    \{\\
    -0.87
    AddTagHelper
    -0.84
    SourceChecksum
    -0.81
     unknownFields
    -0.79
    )";
    -0.79
    enumii
    -0.78
    __":
    -0.78
    AndEndTag
    -0.78
    __':
    -0.77
    POSITIVE LOGITS
    <eos>
    0.48
     G
    0.46
    </em>
    0.45
     absolument
    0.44
     timp
    0.44
     v
    0.44
      
    0.42
     V
    0.42
    BeanFactory
    0.41
    of
    0.41
    Act Density 0.056%

    No Known Activations