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

    Neuronpedia

    INDEX
    Explanations

    references to the letter or identifier "X" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     población
    -0.48
     Economía
    -0.47
     cortesía
    -0.47
     ciudadanía
    -0.46
    UnsafeEnabled
    -0.45
     transición
    -0.44
    RegisterType
    -0.43
     sociedad
    -0.43
    xiv
    -0.42
     ocasión
    -0.42
    POSITIVE LOGITS
     x
    1.52
     X
    1.45
     ×
    0.82
     getX
    0.75
    X
    0.73
     × 
    0.65
    getX
    0.64
     XNUMX
    0.62
    ×
    0.61
     xxx
    0.57
    Act Density 0.487%

    No Known Activations