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

    Neuronpedia

    INDEX
    Explanations

    statistical and numerical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     marte
    -1.02
     robus
    -0.93
     anse
    -0.93
     spion
    -0.91
     fasc
    -0.90
     monaster
    -0.90
     monast
    -0.89
     juf
    -0.88
     paillettes
    -0.86
     strass
    -0.86
    POSITIVE LOGITS
     estimates
    0.56
     average
    0.56
     averages
    0.53
     total
    0.52
     estimated
    0.50
     frecuente
    0.50
     rates
    0.50
     further
    0.50
     another
    0.48
     counting
    0.48
    Act Density 0.391%

    No Known Activations