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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically the name "Elizabeth."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    void
    -0.82
     put
    -0.81
     die
    -0.80
    var
    -0.78
     void
    -0.77
     sur
    -0.76
     get
    -0.76
    /*
    -0.74
    const
    -0.73
    源
    -0.73
    POSITIVE LOGITS
     maneu
    2.61
     increa
    2.60
     affor
    2.48
     strick
    2.44
     accla
    2.42
     guarante
    2.39
     disagre
    2.35
     depic
    2.34
     inev
    2.33
     shenan
    2.33
    Act Density 0.099%

    No Known Activations