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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical variables and terms, particularly those involving "delta."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vish
    -0.83
     ItemType
    -0.82
     Nast
    -0.82
     Moseley
    -0.82
     PSL
    -0.78
     Samar
    -0.77
    NSURL
    -0.77
    ymce
    -0.76
     Pate
    -0.76
     Bieber
    -0.76
    POSITIVE LOGITS
     δ
    1.70
    delta
    1.54
    δ
    1.49
     delta
    1.01
     GenerationType
    0.93
    AppMethodBeat
    0.77
    eltas
    0.76
    aarrggbb
    0.76
    jsonwebtoken
    0.73
     minOccurs
    0.73
    Act Density 0.105%

    No Known Activations