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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to varied topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     encount
    -0.76
    Franc
    -0.73
    ÃĥÃĤÃĥÃĤ
    -0.66
    Wan
    -0.66
    ét
    -0.65
     charact
    -0.65
    emort
    -0.63
    abe
    -0.63
    Tes
    -0.63
     destro
    -0.63
    POSITIVE LOGITS
     Miscellaneous
    0.88
     Conclusion
    0.86
     Diary
    0.79
     Annotations
    0.78
     Discussion
    0.77
     Composite
    0.75
     Installation
    0.75
     Presents
    0.74
     Date
    0.73
     partName
    0.73
    Act Density 0.061%

    No Known Activations