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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating shock or disbelief

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shreve
    -0.47
     Taub
    -0.47
     Daven
    -0.45
     Karp
    -0.45
     Reiche
    -0.45
     Kinn
    -0.45
     Bayard
    -0.45
     Vogt
    -0.45
     Respectfully
    -0.45
     Byp
    -0.45
    POSITIVE LOGITS
     soggior
    0.92
     pymysql
    0.78
     appunt
    0.75
     venons
    0.71
     costumi
    0.69
     pantaloni
    0.69
     ristor
    0.68
     abiti
    0.68
     caratteri
    0.66
     sogni
    0.65
    Act Density 0.121%

    No Known Activations