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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe the manner in which actions are performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    見た
    -0.58
     immediate
    -0.57
    出た
    -0.57
     definite
    -0.56
     Immediate
    -0.55
    わかった
    -0.54
    出る
    -0.54
    早い
    -0.54
     ultimate
    -0.53
    Immediate
    -0.53
    POSITIVE LOGITS
     quietly
    2.21
     safely
    2.15
     peacefully
    2.13
     comfortably
    2.10
     silently
    2.07
     calmly
    2.01
     smoothly
    2.01
     confidently
    2.00
     aggressively
    2.00
     casually
    1.98
    Act Density 0.414%

    No Known Activations