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

    Neuronpedia

    INDEX
    Explanations

    punctuation used in sentences

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

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abstracta
    -0.43
     själva
    -0.40
    DebuggerNonUser
    -0.39
     dàng
    -0.35
    pires
    -0.32
    下载附件
    -0.31
    žky
    -0.30
    קישורים
    -0.30
     země
    -0.29
    ORIG
    -0.29
    POSITIVE LOGITS
     EconPapers
    0.68
     ब्रेकडाउन
    0.66
     <=",
    0.64
    linawan
    0.60
     فريبيس
    0.57
    彼の
    0.56
    pośred
    0.54
    niſſe
    0.54
    //
    0.53
     }{@
    0.53
    Act Density 0.092%

    No Known Activations