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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.81
    abama
    -0.77
    MpServer
    -0.69
    displayText
    -0.67
    english
    -0.66
     cabinets
    -0.66
    minecraft
    -0.66
     grapes
    -0.65
     levy
    -0.65
    */(
    -0.64
    POSITIVE LOGITS
    OGR
    0.80
     Niet
    0.63
     Trace
    0.62
    GY
    0.62
    ATIONAL
    0.60
    Kn
    0.60
     Ascension
    0.59
    gression
    0.59
    agin
    0.59
    NR
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.