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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experience or opinions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.73
    twimg
    -0.71
    PyExc
    -0.69
     EconPapers
    -0.63
    Geplaatst
    -0.61
    Kjelder
    -0.59
    تقاوى
    -0.59
     незавершена
    -0.56
    titleMargin
    -0.56
     ErrIntOverflow
    -0.54
    POSITIVE LOGITS
     uh
    0.73
     whoſe
    0.59
     vídeo
    0.59
     Uh
    0.57
     um
    0.56
    تيجة
    0.56
     video
    0.55
     stappen
    0.54
     Um
    0.52
     presentation
    0.52
    Act Density 0.273%

    No Known Activations