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

    Neuronpedia

    INDEX
    Explanations

    references to flatness or two-dimensional objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "flatness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMENT
    -0.90
    IVERS
    -0.82
    externalActionCode
    -0.80
    ITNESS
    -0.77
     ANGEL
    -0.77
    GBT
    -0.77
    emonic
    -0.74
     GOODMAN
    -0.74
    OHN
    -0.72
    YN
    -0.71
    POSITIVE LOGITS
    tered
    1.01
     flat
    0.98
    bed
    0.96
    lining
    0.95
    lined
    0.92
    bread
    0.87
    flat
    0.86
    ulously
    0.84
    liner
    0.82
    sheet
    0.82
    Act Density 0.007%

    No Known Activations