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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases that indicate hesitation or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    その specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     habet
    -0.50
    isNotBlank
    -0.45
     occidentalis
    -0.44
     esprits
    -0.43
     ſta
    -0.41
     ſol
    -0.40
     hinweg
    -0.40
     omnes
    -0.39
     occident
    -0.39
     quæ
    -0.39
    POSITIVE LOGITS
     nahilalakip
    0.68
     insuffisamment
    0.50
    脚注の使い方
    0.48
    >//
    0.46
    これは
    0.46
     disponibilités
    0.46
     незавершена
    0.45
     aload
    0.45
     }))
    0.45
    adaptiveStyles
    0.44
    Act Density 0.018%

    No Known Activations