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

    Neuronpedia

    INDEX
    Explanations

    references to women and their contributions or roles in society throughout history

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

    used to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.79
    became
    -0.74
     became
    -0.71
     okaza
    -0.66
     decided
    -0.66
    XmlAccessType
    -0.65
     Became
    -0.65
    BagLayout
    -0.63
    LabelTagHelper
    -0.62
    decided
    -0.60
    POSITIVE LOGITS
     existed
    0.53
     بوده
    0.47
     always
    0.46
     operated
    0.43
     relied
    0.42
     depended
    0.41
     loved
    0.40
     geweest
    0.40
     lived
    0.40
     selalu
    0.38
    Act Density 0.126%

    No Known Activations