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

    Neuronpedia

    INDEX
    Explanations

    descriptions of car interiors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.98
    chers
    -0.81
    fortune
    -0.81
    urai
    -0.80
    yip
    -0.79
    astically
    -0.78
    tle
    -0.77
    fleet
    -0.72
    umbs
    -0.72
    unin
    -0.71
    POSITIVE LOGITS
     decoration
    1.03
     ministry
    1.00
     decor
    0.90
     workings
    0.85
     renovations
    0.84
    most
    0.83
     Designer
    0.83
     renovation
    0.81
     interior
    0.79
     decorations
    0.79
    Act Density 0.022%

    No Known Activations