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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific symbols used in the text

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

    following commas like "however,"

    np_acts-logits-general · gemini-2.0-flash

    However, we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.74
    jspb
    -0.66
    uxxxx
    -0.64
     AssemblyCompany
    -0.64
    writeField
    -0.60
    errHandler
    -0.59
    قایناق‌لار
    -0.56
    RenderAtEndOf
    -0.55
     Paglinawan
    -0.54
    ьаж
    -0.53
    POSITIVE LOGITS
     it
    0.49
     mivel
    0.46
     there
    0.43
     we
    0.43
     the
    0.40
     selain
    0.38
     việc
    0.36
     jornadas
    0.36
     kiedy
    0.36
     meskipun
    0.36
    Act Density 0.440%

    No Known Activations