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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of highway numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific highways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.84
    tle
    -0.83
    ikarp
    -0.79
    ecast
    -0.79
    ever
    -0.79
    eries
    -0.78
    olith
    -0.76
    oing
    -0.76
    ento
    -0.75
    estamp
    -0.74
    POSITIVE LOGITS
     Highway
    1.15
     highways
    1.10
     roads
    1.02
     highway
    1.00
     Route
    0.97
     patrol
    0.96
     checkpoints
    0.91
     routes
    0.88
     Roads
    0.85
     corridors
    0.85
    Act Density 0.018%

    No Known Activations