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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of reduction or minimizing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.69
    uxxxx
    -0.66
    ]!='
    -0.66
     doInBackground
    -0.64
    upol
    -0.63
    érité
    -0.63
     AssemblyCompany
    -0.63
    ofire
    -0.62
    cupa
    -0.61
    []>(
    -0.59
    POSITIVE LOGITS
     redu
    1.01
     Reduced
    0.95
     réduire
    0.93
     Reduce
    0.92
     REDUC
    0.92
     reduced
    0.92
     reduc
    0.89
     reduce
    0.89
    Reduced
    0.86
     Reduces
    0.86
    Act Density 0.225%

    No Known Activations