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

    Neuronpedia

    INDEX
    Explanations

    mentions of mirrors or reflective imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elan
    -0.16
    aign
    -0.16
    ured
    -0.15
    mps
    -0.15
    alach
    -0.15
    .LayoutStyle
    -0.15
    ties
    -0.15
    illet
    -0.15
    utton
    -0.15
    ener
    -0.15
    POSITIVE LOGITS
    pane
    0.19
    roring
    0.17
     reflection
    0.17
    grams
    0.17
    rored
    0.17
    inke
    0.16
    -image
    0.16
    iams
    0.15
    ophon
    0.15
    ance
    0.15
    Act Density 0.015%

    No Known Activations