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

    Neuronpedia

    INDEX
    Explanations

    This neuron activates on floating-point numeric literals (decimal numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    373
    -0.07
    书记
    -0.06
    said
    -0.06
     Halloween
    -0.06
     Christmas
    -0.06
    _Buffer
    -0.06
    772
    -0.06
     trustworthy
    -0.06
     *))
    -0.06
     truthful
    -0.06
    POSITIVE LOGITS
    
    0.07
    tain
    0.07
     placed
    0.06
     mấy
    0.06
     katı
    0.06
    幸福
    0.06
    (Location
    0.06
     preserve
    0.06
    	params
    0.06
     baise
    0.06
    Act Density 0.010%

    No Known Activations