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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements enclosed in special characters (e.g., Ċ) within text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of different formats of citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derby
    -0.69
     Thornton
    -0.68
    lled
    -0.67
     lifes
    -0.66
     afar
    -0.65
     administrative
    -0.64
     laun
    -0.62
     relegation
    -0.61
     brunt
    -0.61
     drums
    -0.61
    POSITIVE LOGITS
    "âĢ¦
    1.03
    "...
    0.95
    Liter
    0.92
    Dialogue
    0.86
    ""
    0.83
     "âĢ¦
    0.81
    Friend
    0.81
    âĺħ
    0.79
    Quote
    0.79
     "...
    0.79
    Act Density 0.206%

    No Known Activations