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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Computer
    -0.07
    quit
    -0.07
     auc
    -0.07
     Compiler
    -0.07
     compiling
    -0.07
     veut
    -0.07
     }}"></
    -0.07
     Jacob
    -0.07
     halluc
    -0.07
     Simpsons
    -0.07
    POSITIVE LOGITS
     passionately
    0.08
    SEARCH
    0.07
    gage
    0.07
    ≴
    0.06
     표현
    0.06
    ∜
    0.06
    posta
    0.06
    ità
    0.06
    康养
    0.06
    perf
    0.06
    Act Density 0.004%

    No Known Activations