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

    Neuronpedia

    INDEX
    Explanations

    terms related to railways

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rail transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    66666666
    -0.76
     Ambrose
    -0.76
     Homo
    -0.75
     Kinnikuman
    -0.72
    Gene
    -0.70
     Izan
    -0.69
     Libre
    -0.68
     Metatron
    -0.68
     Retrieved
    -0.68
    âĶĢâĶĢ
    -0.67
    POSITIVE LOGITS
    roads
    1.64
    ways
    1.08
    road
    1.01
    craft
    1.00
    cars
    0.93
    ulic
    0.92
     locom
    0.86
    planes
    0.84
     Transit
    0.83
    track
    0.82
    Act Density 0.011%

    No Known Activations