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

    Neuronpedia

    INDEX
    Explanations

    specific road names and locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of street names or road references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irements
    -0.73
    arians
    -0.73
    emort
    -0.70
     pes
    -0.69
    illian
    -0.67
    rator
    -0.67
    glers
    -0.66
    arian
    -0.66
    ropolitan
    -0.66
     Pengu
    -0.66
    POSITIVE LOGITS
    stead
    1.02
    side
    0.97
     Rd
    0.88
     Road
    0.87
     Roads
    0.86
    blocks
    0.83
    ways
    0.82
    course
    0.82
     Racer
    0.81
     junction
    0.81
    Act Density 0.016%

    No Known Activations