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

    Neuronpedia

    INDEX
    Explanations

    pronouns and expressions indicating a hierarchy or emphasis

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

    classifier usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.49
     صوتيه
    -0.47
    zzleHttp
    -0.45
    ulemon
    -0.45
    Geplaatst
    -0.44
     Nour
    -0.43
     ролях
    -0.43
    webElementXpaths
    -0.42
     Suits
    -0.42
    InjectAttribute
    -0.41
    POSITIVE LOGITS
     cái
    2.38
     chiếc
    1.20
    ái
    0.99
    อัน
    0.68
    ếc
    0.66
    ́i
    0.62
     thing
    0.62
    那個
    0.57
     aquilo
    0.57
     something
    0.56
    Act Density 0.001%

    No Known Activations