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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations, particularly streets and corners

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.67
     repertoire
    -0.66
     aboard
    -0.65
     environments
    -0.64
     indisp
    -0.63
     orchestr
    -0.63
     reperto
    -0.63
     coating
    -0.63
     awa
    -0.62
    Versions
    -0.61
    POSITIVE LOGITS
     Route
    1.03
     Interstate
    1.02
     Sunset
    0.93
     Hyde
    0.91
     Rue
    0.90
     Highway
    0.90
     Boulevard
    0.89
     Avenue
    0.86
     Broadway
    0.83
     Northeast
    0.82
    Act Density 0.062%

    No Known Activations