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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of being "un" or lacking something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.17
     Ale
    -0.15
    h
    -0.15
     secondary
    -0.14
    YPE
    -0.14
    d
    -0.14
    razy
    -0.14
    /***/
    -0.13
    quier
    -0.13
     stuffing
    -0.13
    POSITIVE LOGITS
    isphere
    0.17
     mole
    0.17
     inventor
    0.17
    INC
    0.16
    iew
    0.16
    央
    0.16
    blem
    0.15
    icens
    0.15
    Ïģκ
    0.15
     creed
    0.14
    Act Density 0.027%

    No Known Activations