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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the concept of reduction or simplification of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.66
    WebServlet
    -0.59
    χος
    -0.56
    DockStyle
    -0.56
    rrggbb
    -0.56
    categorical
    -0.55
     secondly
    -0.55
     defStyleAttr
    -0.55
    uarine
    -0.55
    entrant
    -0.55
    POSITIVE LOGITS
     reduced
    0.79
    Reduced
    0.70
     REDUC
    0.68
     reduction
    0.67
    reduced
    0.65
     reduziert
    0.64
     redus
    0.64
     reductions
    0.63
     reducido
    0.63
     reduce
    0.63
    Act Density 0.447%

    No Known Activations