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

    Neuronpedia

    INDEX
    Explanations

    references to specific sections or parts of a longer document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.80
    olk
    -0.76
    yah
    -0.75
    opter
    -0.74
    fortune
    -0.74
    enegger
    -0.72
    lda
    -0.69
    rought
    -0.68
    tle
    -0.68
    aler
    -0.68
    POSITIVE LOGITS
     parentheses
    0.77
    vert
    0.72
     workings
    0.71
     bedrooms
    0.69
     latex
    0.69
     walls
    0.67
     Mansion
    0.66
     diameter
    0.66
     chambers
    0.65
     Yosemite
    0.65
    Act Density 0.055%

    No Known Activations