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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to historical inventions and food ingredients

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sergio
    -0.77
    <bos>
    -0.77
     javier
    -0.76
     felipe
    -0.76
     fernando
    -0.68
     gabri
    -0.68
     eduardo
    -0.68
     cristina
    -0.68
     JULIO
    -0.67
     jorge
    -0.67
    POSITIVE LOGITS
     glaubte
    0.56
    underland
    0.55
     NUKAT
    0.53
     where
    0.52
     throughout
    0.52
     since
    0.50
     wherever
    0.50
     Mère
    0.49
    tamment
    0.49
    izarse
    0.48
    Act Density 0.602%

    No Known Activations