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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical actions or events happening in a specific location

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.63
     Brach
    -0.61
     acqu
    -0.59
     nerve
    -0.58
     heartbeat
    -0.57
     Essential
    -0.56
     consolidated
    -0.56
     Ore
    -0.56
    cious
    -0.56
    entle
    -0.54
    POSITIVE LOGITS
    fitted
    1.34
    stretched
    1.13
    doors
    1.07
    ta
    1.01
    wards
    0.98
    posts
    0.92
    smart
    0.92
    door
    0.91
    bound
    0.90
    skirts
    0.88
    Act Density 0.059%

    No Known Activations