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

    Neuronpedia

    INDEX
    Explanations

    street names

    oai_token-act-pair · gpt-3.5-turbo

    the names of specific roads and streets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oaded
    -0.79
    emort
    -0.74
     discipl
    -0.72
    ãģĦ
    -0.69
     reproduce
    -0.68
    duino
    -0.67
    rogram
    -0.66
     mathemat
    -0.64
     rehe
    -0.64
    ãĥķãĤ©
    -0.63
    POSITIVE LOGITS
     Rd
    1.07
     Corridor
    0.99
     Extension
    0.94
     Avenue
    0.94
     Junction
    0.93
     Parkway
    0.91
    wy
    0.90
     Lane
    0.90
    stead
    0.89
     Blvd
    0.88
    Act Density 0.079%

    No Known Activations