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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to energy concepts and their efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     muñecas
    -0.49
     cartón
    -0.47
     Bupati
    -0.43
     capucha
    -0.43
     rodillas
    -0.41
    Vezi
    -0.41
    <bos>
    -0.40
     calcetines
    -0.40
     tornillos
    -0.40
    Rhestr
    -0.40
    POSITIVE LOGITS
     Energy
    1.63
     energy
    1.63
    Energy
    1.63
    ENERGY
    1.56
     ENERGY
    1.56
    energy
    1.55
     Energie
    1.34
     energia
    1.27
     Energies
    1.25
     energie
    1.23
    Act Density 0.091%

    No Known Activations