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

    Neuronpedia

    INDEX
    Explanations

    references to furniture

    oai_token-act-pair · gpt-3.5-turbo

    references to furniture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceed
    -0.86
    20439
    -0.86
    awar
    -0.79
    ilitary
    -0.72
    76561
    -0.71
    mp
    -0.68
    bern
    -0.65
    zee
    -0.65
    ²¾
    -0.64
    olics
    -0.64
    POSITIVE LOGITS
     furniture
    1.03
     decoration
    0.95
    iture
    0.93
     drawer
    0.85
     decorations
    0.82
     arrang
    0.79
     accessories
    0.75
     Crate
    0.74
     shelves
    0.71
     arrangements
    0.70
    Act Density 0.036%

    No Known Activations