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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Du" and its variations, along with terms related to nobility and hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.60
     ence
    -0.48
     Vince
    -0.47
    Denise
    -0.47
    ConfigureAwait
    -0.46
     muse
    -0.46
    DialogInterface
    -0.45
     Prisma
    -0.44
    osa
    -0.44
    Gerard
    -0.44
    POSITIVE LOGITS
     du
    0.62
     rust
    0.57
     inherited
    0.53
    SharedDtor
    0.52
     desierto
    0.52
     desert
    0.50
     deserts
    0.50
    tvguidetime
    0.49
     justly
    0.49
     axial
    0.47
    Act Density 0.228%

    No Known Activations