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

    Neuronpedia

    INDEX
    Explanations

    words indicating recent events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éndolo
    -0.65
    ftagPool
    -0.62
     cauza
    -0.62
     célè
    -0.62
    这份
    -0.62
     revanche
    -0.60
     épais
    -0.59
     humaines
    -0.59
     nicio
    -0.58
    hwa
    -0.58
    POSITIVE LOGITS
     recently
    1.53
    recently
    1.49
     Recently
    1.42
    Recently
    1.33
     recientemente
    1.15
     недавно
    1.05
     lately
    1.02
     recentemente
    1.01
     kürzlich
    1.01
     previously
    1.00
    Act Density 0.091%

    No Known Activations