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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly related to measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0
    -0.32
    00
    -0.31
     zero
    -0.25
    ï¼IJ
    -0.23
    âĤĢ
    -0.21
    鼶
    -0.21
    ०
    -0.20
    _zero
    -0.20
     ZERO
    -0.20
     Zero
    -0.19
    POSITIVE LOGITS
    óst
    0.15
    inky
    0.14
     Trojan
    0.14
    ishi
    0.14
    ophon
    0.13
    ï¸ı
    0.13
    eland
    0.13
     tip
    0.13
     Deck
    0.13
    عر
    0.13
    Act Density 0.077%

    No Known Activations