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

    Neuronpedia

    INDEX
    Explanations

    references to community infrastructure projects and their development timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ°ãģĭãĤĬ
    -0.20
     Almost
    -0.18
    Almost
    -0.18
     almost
    -0.17
     Nearly
    -0.16
    almost
    -0.16
     lately
    -0.16
     nearly
    -0.16
    recent
    -0.16
     Sometimes
    -0.15
    POSITIVE LOGITS
     possibly
    0.27
     maybe
    0.25
     next
    0.25
     perhaps
    0.23
     tomorrow
    0.22
    possibly
    0.21
     either
    0.20
    -нибÑĥдÑĮ
    0.20
    maybe
    0.20
     if
    0.20
    Act Density 0.993%

    No Known Activations