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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPH
    -0.15
     Dol
    -0.14
    iph
    -0.14
    aker
    -0.14
    esy
    -0.14
     noct
    -0.14
    ivet
    -0.13
    ynet
    -0.13
     Gothic
    -0.13
    ãĥĭãĥ¡
    -0.13
    POSITIVE LOGITS
     '\''
    0.16
    REFER
    0.16
    è³Ģ
    0.15
    اÙĨÙĩ
    0.15
    身ä¸Ĭ
    0.15
    using
    0.14
    iÄħ
    0.14
    ilik
    0.14
    UInteger
    0.14
    γκα
    0.14
    Act Density 0.004%

    No Known Activations