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

    Neuronpedia

    INDEX
    Explanations

    significant historical dates marked by anniversaries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of ordinal numbers and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.70
    bows
    -0.65
     encour
    -0.65
    elines
    -0.62
     fists
    -0.61
    itri
    -0.60
    cur
    -0.60
    skirts
    -0.58
    illas
    -0.57
     ¯
    -0.57
    POSITIVE LOGITS
     anniversary
    1.13
     Anniversary
    1.06
     installment
    1.02
     Amendment
    1.02
    ousand
    0.97
     percentile
    0.97
     century
    0.92
    degree
    0.89
    irteen
    0.86
     Annual
    0.85
    Act Density 0.038%

    No Known Activations