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

    Neuronpedia

    INDEX
    Explanations

    mathematical inequalities and symbols related to comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bia
    -0.18
     ç·¨
    -0.16
    akan
    -0.15
    tik
    -0.15
     Gear
    -0.14
    roti
    -0.14
    onta
    -0.14
    ntax
    -0.14
    asal
    -0.14
    anca
    -0.14
    POSITIVE LOGITS
    690
    0.17
    ÂŃi
    0.15
    na
    0.15
    577
    0.14
    327
    0.14
    ÚĨÙĩ
    0.14
     redemption
    0.13
    λί
    0.13
     pinch
    0.13
    pin
    0.13
    Act Density 0.059%

    No Known Activations