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

    Neuronpedia

    INDEX
    Explanations

    references to responsibilities and accusations of murder or harm towards specific groups or individuals

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

    sentence starters following "the" or "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.57
     betweenstory
    -0.52
    ValueStyle
    -0.52
     مشين
    -0.51
    点此举报
    -0.48
    featureID
    -0.48
     ostavi
    -0.47
    thâu
    -0.47
     հղումներ
    -0.46
     PeEnEo
    -0.45
    POSITIVE LOGITS
     list
    2.47
     List
    1.88
    list
    1.88
     lista
    1.86
     lists
    1.80
     LIST
    1.70
     Liste
    1.67
     liste
    1.66
    List
    1.64
     список
    1.58
    Act Density 0.036%

    No Known Activations