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

    Neuronpedia

    INDEX
    Explanations

    This neuron activates on floating-point number literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     favored
    -0.07
    <Node
    -0.07
     corn
    -0.07
     infusion
    -0.07
    (lua
    -0.07
    �
    -0.06
     grade
    -0.06
     powdered
    -0.06
     Brewer
    -0.06
    ognition
    -0.06
    POSITIVE LOGITS
    submit
    0.06
     bizi
    0.06
     ~/.
    0.06
     DataLoader
    0.06
    createView
    0.06
     Talking
    0.06
    \Repository
    0.06
     omp
    0.06
    awesome
    0.06
     parchment
    0.06
    Act Density 0.020%

    No Known Activations