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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual named Sarai or related terms in various contexts

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

    "Sar" token, often followed by "ai"

    np_acts-logits-general · gemini-2.0-flash

    sar followed by ai, coma, castic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [](
    -0.60
    antaine
    -0.59
    atimes
    -0.53
     numberWith
    -0.53
     actionMode
    -0.51
     TextInputType
    -0.50
    getBytes
    -0.50
    حياتها
    -0.50
     life
    -0.49
    BeginContext
    -0.48
    POSITIVE LOGITS
    Sar
    0.88
     Sar
    0.82
     sar
    0.76
    mybatisplus
    0.67
    fillType
    0.66
    parsedMessage
    0.64
     sari
    0.60
     Sarac
    0.59
     Saras
    0.57
     للاسماء
    0.56
    Act Density 0.115%

    No Known Activations