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

    Neuronpedia

    INDEX
    Explanations

    Chinese punctuation marks, specifically commas

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

    chinese punctuation 、

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.49
     feroit
    -0.47
     ainfi
    -0.46
     ſind
    -0.45
     skrzy
    -0.45
    IMDB
    -0.44
    JMenu
    -0.43
     avoient
    -0.43
     semelh
    -0.43
     ſich
    -0.43
    POSITIVE LOGITS
    、
    0.73
     、
    0.59
    、《
    0.54
    ）、
    0.54
    ㆍ
    0.52
     maupun
    0.51
    )、
    0.51
     एवं
    0.50
    ၊
    0.49
    )+(
    0.49
    Act Density 0.008%

    No Known Activations