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

    Neuronpedia

    INDEX
    Explanations

    references to scientific literature and publication data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elon
    -0.16
     mass
    -0.16
    iller
    -0.15
    ally
    -0.15
     Vie
    -0.15
    phia
    -0.15
    elves
    -0.14
    181
    -0.14
     oxid
    -0.14
    aly
    -0.14
    POSITIVE LOGITS
    amet
    0.17
     gsi
    0.15
    osci
    0.15
    ContentSize
    0.15
    letic
    0.15
    /welcome
    0.15
    ontent
    0.14
    [opt
    0.14
    AEA
    0.14
    akedirs
    0.14
    Act Density 0.012%

    No Known Activations