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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -mf
    -0.18
    ãĥªãĥ¼
    -0.16
    stub
    -0.16
    bilt
    -0.15
    ãģŁãģĹ
    -0.15
    ertura
    -0.15
    iffe
    -0.15
     ÐŁÑĢа
    -0.14
     ваг
    -0.14
     <!--[
    -0.14
    POSITIVE LOGITS
     Dorm
    0.17
    abal
    0.15
    hus
    0.14
     Dudley
    0.14
    bane
    0.14
     Aqu
    0.14
    hu
    0.14
    ansi
    0.14
    cha
    0.13
    zn
    0.13
    Act Density 0.793%

    No Known Activations