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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "many" and its variations, indicating references to large quantities or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.17
    siz
    -0.16
    istrovstvÃŃ
    -0.15
    ÛĮÙĩ
    -0.15
     noen
    -0.14
    _codegen
    -0.14
    à¸ļาà¸ĩ
    -0.14
    eldorf
    -0.14
    ÙĩاÛĮÛĮ
    -0.14
    @js
    -0.14
    POSITIVE LOGITS
     of
    0.34
    -many
    0.31
    /all
    0.26
    /m
    0.25
     different
    0.25
    -sided
    0.24
    ToMany
    0.24
     more
    0.22
    ãĢħ
    0.22
     fewer
    0.21
    Act Density 0.487%

    No Known Activations