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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and reflective imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.17
    perature
    -0.17
    .LayoutStyle
    -0.16
    munition
    -0.15
    urator
    -0.15
    Borders
    -0.15
     addCriterion
    -0.15
    ener
    -0.15
     Courtney
    -0.15
    .UnitTesting
    -0.15
    POSITIVE LOGITS
    pane
    0.18
    -image
    0.18
    roring
    0.18
    iams
    0.17
    ock
    0.17
    ance
    0.17
    iam
    0.17
    ry
    0.16
    rored
    0.16
     image
    0.16
    Act Density 0.014%

    No Known Activations