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

    Neuronpedia

    INDEX
    Explanations

    statements according to a specific source or authority

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eg
    -0.72
    obyl
    -0.69
    affe
    -0.69
    igmat
    -0.67
    ãĤ¨ãĥ«
    -0.64
    otin
    -0.64
    estern
    -0.63
    IFT
    -0.63
    riage
    -0.63
    /#
    -0.61
    POSITIVE LOGITS
     sources
    0.89
    SOURCE
    0.79
    Sources
    0.68
    Rank
    0.65
     Reuters
    0.64
     WS
    0.62
     Sources
    0.60
     contrad
    0.59
    lesiastical
    0.59
     according
    0.58
    Act Density 0.056%

    No Known Activations