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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of exposure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zon
    -0.18
    enge
    -0.17
    emons
    -0.16
    kir
    -0.16
    ±
    -0.15
     Ging
    -0.15
    rowable
    -0.15
    erness
    -0.14
    ĥĿ
    -0.14
    _STRUCTURE
    -0.14
    POSITIVE LOGITS
     exposure
    0.22
    ively
    0.20
    /import
    0.18
     Exposure
    0.18
     kepada
    0.17
     exposures
    0.16
    avad
    0.16
    entially
    0.15
    PRINTF
    0.15
     exposed
    0.15
    Act Density 0.016%

    No Known Activations