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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or subjective evaluations

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

    for the record FWIW

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tracce
    -0.36
    BorderFactory
    -0.32
     délé
    -0.32
    awtextra
    -0.32
    SharedCtor
    -0.32
    passion
    -0.31
     need
    -0.29
     συγκ
    -0.29
    replacement
    -0.28
    তথ্যসূত্র
    -0.28
    POSITIVE LOGITS
     Geſch
    0.55
     Geiſt
    0.53
    FWIW
    0.52
    )++;
    0.51
    出版年
    0.51
    brigens
    0.51
    PreferredItem
    0.50
     Waſſer
    0.50
    älv
    0.49
     Penh
    0.48
    Act Density 0.020%

    No Known Activations