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

    Neuronpedia

    INDEX
    Explanations

    locations within city blocks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.78
    Versions
    -0.73
     oblig
    -0.72
    =-=-=-=-=-=-=-=-
    -0.67
    REP
    -0.65
    uria
    -0.64
     discipl
    -0.61
    berman
    -0.61
    NSA
    -0.59
     repertoire
    -0.59
    POSITIVE LOGITS
     flats
    0.99
     Northwest
    0.79
     Interstate
    0.76
     Boulevard
    0.74
     East
    0.73
     Northeast
    0.73
     stairs
    0.73
     Sunset
    0.73
     Lime
    0.73
     NW
    0.71
    Act Density 0.019%

    No Known Activations