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

    Neuronpedia

    INDEX
    Explanations

    references to important titles and roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uits
    -0.18
    lets
    -0.17
    zas
    -0.17
     Preis
    -0.17
    agrams
    -0.15
    .assign
    -0.14
    rels
    -0.14
    idon
    -0.14
    UMB
    -0.14
    ictionaries
    -0.14
    POSITIVE LOGITS
     themselves
    0.21
    ibrator
    0.16
    大ä¼ļ
    0.15
    /vendors
    0.14
     Sting
    0.14
    ongoose
    0.14
    847
    0.14
    inch
    0.14
     Meadows
    0.14
    ieder
    0.13
    Act Density 0.369%

    No Known Activations