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

    Neuronpedia

    INDEX
    Explanations

    references to railway stations and associated terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qrstuvwxyz
    -0.64
    WriteTagHelper
    -0.62
    strator
    -0.61
    SCAPE
    -0.60
    argb
    -0.59
     Grecs
    -0.58
     Dorado
    -0.56
     corrig
    -0.56
     Mandy
    -0.56
    likace
    -0.56
    POSITIVE LOGITS
     trains
    1.46
     railway
    1.42
     train
    1.40
     Train
    1.36
     Trains
    1.34
    Trains
    1.33
     railways
    1.31
     Rail
    1.31
     railroad
    1.31
     rail
    1.30
    Act Density 0.154%

    No Known Activations