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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     tayo
    -0.56
    katapos
    -0.52
     namin
    -0.52
     ngayon
    -0.51
     itong
    -0.50
     kasama
    -0.49
    wyneth
    -0.49
    levelse
    -0.48
     للاسماء
    -0.48
    Hvor
    -0.47
    POSITIVE LOGITS
     sergio
    0.75
     BOG
    0.74
     jorge
    0.73
     Ig
    0.73
     Hag
    0.73
     aussitôt
    0.72
     ugg
    0.72
    pog
    0.71
     claudia
    0.71
     Pug
    0.71
    Act Density 0.635%

    No Known Activations