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

    Neuronpedia

    INDEX
    Explanations

    quantitative data points expressed as percentages

    oai_token-act-pair · gpt-3.5-turbo

    percentage values or statistical data in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exposition
    -0.70
     smugglers
    -0.67
    ĸļ
    -0.67
     feats
    -0.67
     successors
    -0.66
     cliff
    -0.63
     thorn
    -0.62
     flashbacks
    -0.62
     bombardment
    -0.62
     reinvent
    -0.60
    POSITIVE LOGITS
    percent
    1.05
    approximately
    1.03
    excluding
    1.03
    %)
    1.02
    56
    0.97
    46
    0.96
    76
    0.96
    57
    0.95
    74
    0.95
    55
    0.93
    Act Density 0.088%

    No Known Activations