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

    Neuronpedia

    INDEX
    Explanations

    key academic phrases and structural elements typical in research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chts
    -0.17
    rej
    -0.16
    raits
    -0.15
    .nano
    -0.13
    lets
    -0.13
    ɵ
    -0.13
    avad
    -0.13
    edin
    -0.13
    -now
    -0.13
    avage
    -0.13
    POSITIVE LOGITS
     Drawing
    0.28
     drawing
    0.25
    Drawing
    0.25
     Specifically
    0.23
     Building
    0.23
     building
    0.23
     based
    0.22
     Based
    0.22
    drawing
    0.21
    building
    0.21
    Act Density 0.106%

    No Known Activations