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

    Neuronpedia

    INDEX
    Explanations

    references to scientific analysis and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    positor
    -0.16
    inq
    -0.16
    ouro
    -0.16
    lek
    -0.15
    iny
    -0.15
     Sn
    -0.15
    awning
    -0.15
    nik
    -0.14
    ollo
    -0.14
    dl
    -0.14
    POSITIVE LOGITS
     NAT
    0.17
     odv
    0.17
     Natural
    0.16
    oran
    0.15
     naturally
    0.15
    Natural
    0.15
     natural
    0.14
     SUBSTITUTE
    0.14
    gro
    0.14
    nga
    0.14
    Act Density 0.096%

    No Known Activations