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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and their placement within sentences

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

    concluding phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.48
    ьаж
    -0.43
     multimeter
    -0.43
    ReusableCell
    -0.42
    Parce
    -0.41
    Amateur
    -0.41
    vician
    -0.41
     Extragalactic
    -0.40
    commented
    -0.40
     uLocal
    -0.39
    POSITIVE LOGITS
     therefore
    0.73
    จึง
    0.64
    Поэтому
    0.62
     consequently
    0.59
     Somit
    0.58
     hence
    0.58
    Therefore
    0.57
     thus
    0.57
     Therefore
    0.56
     pertanto
    0.56
    Act Density 0.052%

    No Known Activations