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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey the concept of "light" in various contextual meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĪ¬
    -0.17
    ãĤº
    -0.15
    rende
    -0.15
     prox
    -0.15
    âĶIJ
    -0.15
    asin
    -0.14
    531
    -0.14
    åħĥ
    -0.14
    /Branch
    -0.14
    ibri
    -0.14
    POSITIVE LOGITS
    ph
    0.17
    Archive
    0.16
    tat
    0.15
    ture
    0.15
    Decor
    0.14
     spotting
    0.14
    w
    0.14
    wie
    0.14
    vä
    0.14
    este
    0.13
    Act Density 0.009%

    No Known Activations