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

    Neuronpedia

    INDEX
    Explanations

    streets and locations mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of streets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.97
    merce
    -0.92
    arians
    -0.85
    arian
    -0.84
    mingham
    -0.79
    berman
    -0.75
    unity
    -0.73
    isman
    -0.73
    ividual
    -0.72
    abase
    -0.72
    POSITIVE LOGITS
     Tunnel
    0.89
     Fighter
    0.85
     Address
    0.84
     Crossing
    0.83
    cars
    0.82
     Street
    0.81
    street
    0.81
    fare
    0.80
    Street
    0.78
    bridge
    0.77
    Act Density 0.022%

    No Known Activations