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

    Neuronpedia

    INDEX
    Explanations

    mentions of flat objects or surfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of flatness, particularly in relation to the Earth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMENT
    -0.99
    externalActionCode
    -0.87
    EEK
    -0.80
    ITNESS
    -0.80
    IVERS
    -0.79
    CRIP
    -0.76
     ANGEL
    -0.74
    GBT
    -0.74
     Occupations
    -0.73
    IDA
    -0.72
    POSITIVE LOGITS
     flat
    1.15
    flat
    1.06
    tered
    0.97
    bread
    0.91
    bed
    0.91
    lined
    0.89
    lining
    0.88
     slab
    0.87
    ulously
    0.84
     tyre
    0.83
    Act Density 0.008%

    No Known Activations