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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to diverse applications or multiple uses of something across different fields or areas.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    references to applications or uses across various fields and contexts

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

    preceding lists of possible options

    np_acts-logits-general · gemini-2.0-flash

    contexts and uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.57
     ویکی‌پدیای
    -0.56
     Paglinawan
    -0.56
    #+#
    -0.51
     همین
    -0.51
     Paulson
    -0.49
    الدراسه
    -0.49
     مرئيه
    -0.48
    upported
    -0.48
    Vidite
    -0.48
    POSITIVE LOGITS
    بوابة
    0.41
     including
    0.39
     such
    0.38
     ErrIntOverflow
    0.37
     things
    0.36
     annat
    0.35
    ParallelGroup
    0.35
     THINGS
    0.35
     Including
    0.35
    像是
    0.34
    Act Density 0.680%

    No Known Activations