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

    Neuronpedia

    INDEX
    Explanations

    words related to glass objects

    oai_token-act-pair · gpt-3.5-turbo

    references to glass materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRED
    -0.83
    ired
    -0.76
    unct
    -0.75
    Express
    -0.73
    CVE
    -0.71
    NPR
    -0.70
    DAY
    -0.69
    AF
    -0.67
    ilitary
    -0.67
    avez
    -0.66
    POSITIVE LOGITS
    glass
    1.09
     bottles
    1.01
     shards
    0.97
     glass
    0.95
     beads
    0.92
     glasses
    0.92
    ware
    0.88
     champagne
    0.87
    works
    0.86
     bead
    0.85
    Act Density 0.009%

    No Known Activations