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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to shadows and darkness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jak
    -0.15
    zig
    -0.15
    isposable
    -0.14
    ìłĢ
    -0.14
    itor
    -0.14
    agon
    -0.14
    annon
    -0.13
    ëłĪ
    -0.13
     aggi
    -0.13
    ekk
    -0.13
    POSITIVE LOGITS
    ened
    0.20
    ed
    0.18
    ablish
    0.17
    ening
    0.17
    ned
    0.16
    shade
    0.15
    /light
    0.15
    -dark
    0.15
    ippi
    0.15
     shadow
    0.15
    Act Density 0.047%

    No Known Activations