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

    Neuronpedia

    INDEX
    Explanations

    references to fixed identifiers or constants in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rafraî
    -0.63
    keli
    -0.60
     JORDAN
    -0.60
     titolata
    -0.57
     Barrios
    -0.57
     Jordan
    -0.55
    vallen
    -0.54
    IBarButtonItem
    -0.52
     figliu
    -0.52
    gypti
    -0.51
    POSITIVE LOGITS
    R
    0.73
    bootstrapcdn
    0.69
    cticut
    0.67
    Хьажоргаш
    0.66
    AddHtmlAttribute
    0.66
     Wicidata
    0.64
     Beverley
    0.63
    IsMutable
    0.63
     departe
    0.62
     NRW
    0.60
    Act Density 0.120%

    No Known Activations