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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically decades and centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JsonIgnore
    -0.46
    saraba
    -0.45
    CLICK
    -0.43
    isContained
    -0.43
    ({_
    -0.41
    爆
    -0.40
     ped
    -0.40
     Separ
    -0.40
     fresh
    -0.40
     sched
    -0.40
    POSITIVE LOGITS
     decades
    2.78
     centuries
    2.39
     décadas
    2.28
     century
    2.03
     decade
    2.02
     siglos
    1.98
     years
    1.88
    decade
    1.77
     siècles
    1.75
     Centuries
    1.75
    Act Density 0.193%

    No Known Activations