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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote duration or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.55
     Paglinawan
    -0.43
    má
    -0.41
    期刊论文
    -0.41
    uja
    -0.39
    :✨
    -0.39
     Less
    -0.38
     específicamente
    -0.37
    Less
    -0.37
    чнее
    -0.37
    POSITIVE LOGITS
     extended
    1.21
     prolonged
    1.05
     considerable
    0.96
    extended
    0.94
     significant
    0.94
    Extended
    0.93
     substantial
    0.91
     Extended
    0.91
     appreciable
    0.85
     sizable
    0.80
    Act Density 0.483%

    No Known Activations