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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific terms or articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Russ
    -0.58
    enta
    -0.57
    OND
    -0.57
    robe
    -0.56
     (>
    -0.55
     shenan
    -0.54
    worldly
    -0.53
    SPA
    -0.53
    ,
    -0.52
    ,—
    -0.50
    POSITIVE LOGITS
     involves
    1.18
     consists
    1.14
     revolves
    1.12
     comprises
    1.10
     represents
    1.07
     constitutes
    1.07
     is
    1.07
     relies
    1.04
     contains
    1.03
     allows
    1.03
    Act Density 0.174%

    No Known Activations