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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     prest
    -0.65
     destro
    -0.60
     advoc
    -0.59
     glim
    -0.59
     Vaugh
    -0.56
    avorite
    -0.56
    oppable
    -0.53
     corrid
    -0.53
     psychiat
    -0.53
     Niet
    -0.52
    POSITIVE LOGITS
     |
    0.65
     reacts
    0.62
     ):
    0.61
     Released
    0.61
     ][
    0.60
     Originally
    0.60
     ]
    0.60
     Says
    0.59
     âĢº
    0.57
     Website
    0.57
    Act Density 0.548%

    No Known Activations