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

    Neuronpedia

    INDEX
    Explanations

    references to championships and competitive weight classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.51
    Bent
    -0.40
    Dax
    -0.40
     resourceCulture
    -0.39
    trane
    -0.38
     rigs
    -0.37
    ⟬
    -0.36
    elakaan
    -0.36
     نظ
    -0.36
     Bent
    -0.36
    POSITIVE LOGITS
     pay
    0.48
     TLC
    0.46
     Money
    0.45
     estekak
    0.45
    Autoritní
    0.44
    UnusedPrivate
    0.44
     Elimination
    0.43
     steel
    0.43
     Pay
    0.42
    ragalactic
    0.42
    Act Density 0.271%

    No Known Activations