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

    Neuronpedia

    INDEX
    Explanations

    sections or parts within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    references to different divisions or parts of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulet
    -0.82
    eus
    -0.72
    iom
    -0.70
    ereo
    -0.69
     ambassador
    -0.68
    asket
    -0.67
    ird
    -0.66
     constellation
    -0.66
     lawyer
    -0.63
    efe
    -0.62
    POSITIVE LOGITS
     sections
    3.34
     Sections
    2.32
     segments
    2.19
     portions
    1.95
     passages
    1.92
     subsections
    1.92
     chapters
    1.86
    sections
    1.83
     chunks
    1.80
     parts
    1.76
    Act Density 0.015%

    No Known Activations