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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pptd
    0.43
     dosen
    0.40
     wholeheartedly
    0.39
     sqrt
    0.38
     it
    0.38
     halve
    0.38
     whopping
    0.38
    🥺
    0.37
     by
    0.37
     chemotherapy
    0.37
    POSITIVE LOGITS
    ภัณฑ์
    0.39
    formerly
    0.38
     Prêmio
    0.38
    previously
    0.37
    model
    0.37
    Abstract
    0.37
    environment
    0.36
    affinity
    0.36
    Creative
    0.36
    conditions
    0.35
    Act Density 0.000%

    No Known Activations