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

    Neuronpedia

    INDEX
    Explanations

    references to streets and related activities or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to "streets" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DK
    -0.64
    writer
    -0.63
    HER
    -0.63
    ================================================================
    -0.60
    reply
    -0.59
    nat
    -0.59
    370
    -0.58
     HH
    -0.58
    AE
    -0.58
    compatible
    -0.58
    POSITIVE LOGITS
     streets
    3.74
     Streets
    2.71
     sidewalks
    2.14
     roads
    2.13
     street
    2.10
     highways
    1.86
     neighborhoods
    1.83
    street
    1.78
     neighbourhoods
    1.74
     rooft
    1.69
    Act Density 0.017%

    No Known Activations