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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.17
    ully
    -0.15
    .BLL
    -0.15
    kad
    -0.14
    ebra
    -0.14
    mods
    -0.14
    енка
    -0.14
    ymes
    -0.14
    arkin
    -0.14
    EXTERN
    -0.14
    POSITIVE LOGITS
     reflection
    0.38
     mirror
    0.37
     mirrors
    0.36
    reflection
    0.36
     Mirror
    0.34
    mirror
    0.33
     reflections
    0.33
     Reflection
    0.33
     reflected
    0.32
     mirrored
    0.32
    Act Density 0.061%

    No Known Activations