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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating beginning actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CPtr
    -0.42
    mtliche
    -0.35
     Slag
    -0.34
     permanently
    -0.34
     forever
    -0.34
    ublic
    -0.33
    Actual
    -0.33
     gobern
    -0.33
    Ass
    -0.32
    Mess
    -0.32
    POSITIVE LOGITS
    そろそろ
    0.63
     langsam
    0.53
    :✨
    0.53
    tagHelperRunner
    0.52
     gradually
    0.52
    徐々に
    0.51
    少しずつ
    0.50
    ngths
    0.50
     allmäh
    0.49
     mulai
    0.49
    Act Density 0.320%

    No Known Activations