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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical expressions and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    und
    -0.16
    /plugin
    -0.15
    rement
    -0.15
    aus
    -0.14
    mage
    -0.14
    ak
    -0.14
    íĮĶ
    -0.14
    Attribute
    -0.14
    cou
    -0.14
    _decrypt
    -0.14
    POSITIVE LOGITS
    antro
    0.18
    elmet
    0.15
    estring
    0.15
    suming
    0.15
     Quote
    0.15
    ÙģاÙĤ
    0.14
     Fulton
    0.14
    оди
    0.14
    ugin
    0.13
     dét
    0.13
    Act Density 0.015%

    No Known Activations