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

    Neuronpedia

    INDEX
    Explanations

    specific locations mentioned in a news or crime-related text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     reperto
    -0.85
     oblig
    -0.77
     submar
    -0.74
     discipl
    -0.72
    orian
    -0.72
     repertoire
    -0.72
     ignor
    -0.66
     indisp
    -0.64
     pron
    -0.63
    />
    -0.63
    POSITIVE LOGITS
     flats
    0.94
     Interstate
    0.92
     Northeast
    0.80
     Boulevard
    0.79
     Sunset
    0.78
     stairs
    0.78
     Northwest
    0.77
     Rue
    0.77
     Commissioners
    0.75
     Avenue
    0.75
    Act Density 0.066%

    No Known Activations