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

    Neuronpedia

    INDEX
    Explanations

    references to railway systems and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    carriage
    -0.52
     Carriage
    -0.51
     carriages
    -0.47
     carriage
    -0.47
     kasarigan
    -0.47
     pouvoit
    -0.45
     AssemblyTitle
    -0.44
    enderror
    -0.43
     veicolo
    -0.43
     Wagon
    -0.42
    POSITIVE LOGITS
     switching
    0.61
     Norfolk
    0.54
     swit
    0.53
     Switching
    0.52
     yard
    0.48
     cabo
    0.48
     switch
    0.48
    Norfolk
    0.47
     UP
    0.47
    switching
    0.47
    Act Density 0.565%

    No Known Activations