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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements, statistics, and technical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     okaza
    -0.51
     GSC
    -0.48
     Fiske
    -0.47
    warran
    -0.47
     Shenandoah
    -0.47
     Rine
    -0.47
    harmed
    -0.46
     
    -0.46
    GraphicsUnit
    -0.45
     "
    -0.45
    POSITIVE LOGITS
     silikon
    1.29
     keramik
    1.22
     alkoh
    1.20
     meras
    1.19
     karton
    1.18
     marte
    1.17
     kompres
    1.14
     kafe
    1.12
     fré
    1.10
     kaos
    1.09
    Act Density 0.036%

    No Known Activations