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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or symbols indicating a decrease or loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hone
    -0.17
    seau
    -0.16
    onds
    -0.15
    quito
    -0.15
    keley
    -0.14
    melon
    -0.14
    izio
    -0.14
    amaño
    -0.14
    елÑı
    -0.14
    inter
    -0.14
    POSITIVE LOGITS
    ëłĪìĿ´
    0.15
    جد
    0.15
    avic
    0.14
    oldown
    0.13
    اÛĮØ´
    0.13
    olders
    0.13
    pery
    0.13
     Benny
    0.13
    èģĶç½ij
    0.13
    bing
    0.13
    Act Density 0.012%

    No Known Activations