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

    Neuronpedia

    INDEX
    Explanations

    references to lighting and sound effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lightweight
    -0.21
    olian
    -0.18
     lightly
    -0.17
    ction
    -0.16
    icht
    -0.16
    лÑıн
    -0.16
     light
    -0.16
     lighter
    -0.15
    hell
    -0.15
    Ŀ
    -0.15
    POSITIVE LOGITS
    ening
    0.32
    nings
    0.31
    bul
    0.31
    enment
    0.30
    ened
    0.25
    ning
    0.25
    aber
    0.23
     bulbs
    0.23
    NING
    0.23
     fixtures
    0.22
    Act Density 0.045%

    No Known Activations