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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government action and policy changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sometimes
    -0.17
    bla
    -0.16
    uhe
    -0.15
    Certain
    -0.14
    icher
    -0.14
     Vide
    -0.14
    æľīäºĽ
    -0.13
    磨
    -0.13
     //////////////////////////////////////////////////////////////////////
    -0.13
    retty
    -0.13
    POSITIVE LOGITS
     instead
    0.19
     preferably
    0.16
     ÙģÙĪر
    0.16
    instead
    0.16
     forth
    0.15
     seri
    0.15
    obia
    0.15
     atleast
    0.15
    atatype
    0.15
     Instead
    0.15
    Act Density 0.307%

    No Known Activations