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

    Neuronpedia

    INDEX
    Explanations

    locations and directions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     diapers
    -0.74
    papers
    -0.71
     dolls
    -0.69
     mishand
    -0.67
    onom
    -0.67
    ealous
    -0.65
    rogram
    -0.64
    otypes
    -0.64
    confidence
    -0.64
     morale
    -0.64
    POSITIVE LOGITS
     Route
    1.40
     Highway
    1.38
    Route
    1.36
     Interstate
    1.29
     highways
    1.19
     east
    1.18
     highway
    1.17
     intersection
    1.15
     corridor
    1.15
     west
    1.14
    Act Density 0.658%

    No Known Activations