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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and reflection concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.18
    perature
    -0.17
     Courtney
    -0.16
    Borders
    -0.15
    etak
    -0.15
    .Rad
    -0.15
    alary
    -0.15
    alach
    -0.15
    ties
    -0.15
    ters
    -0.15
    POSITIVE LOGITS
    -image
    0.23
     image
    0.21
    image
    0.20
    roring
    0.19
    pane
    0.19
    iam
    0.18
    iams
    0.18
    stone
    0.17
    rored
    0.17
    ë§ģ
    0.17
    Act Density 0.014%

    No Known Activations