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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and criticisms related to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prochaines
    -0.76
    ]--;
    -0.62
     Recent
    -0.60
     recent
    -0.60
     prochain
    -0.58
     GenerationType
    -0.57
     EconPapers
    -0.55
     kaynağından
    -0.55
     اخیر
    -0.55
     heapq
    -0.55
    POSITIVE LOGITS
     then
    2.41
     damals
    2.40
     тогда
    2.19
     allora
    2.05
     entonces
    2.03
     damaligen
    1.99
    当时
    1.97
    當時
    1.96
    当时的
    1.93
     wtedy
    1.90
    Act Density 0.574%

    No Known Activations