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

    Neuronpedia

    INDEX
    Explanations

    terms related to options, variations, and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words describing variety, options, or different choices available to consumers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     nadzieję
    -0.36
     solche
    -0.34
     thiện
    -0.33
    UnusedPrivate
    -0.33
    nezeu
    -0.33
    inheritDoc
    -0.30
     solchen
    -0.29
     zilver
    -0.29
     kesel
    -0.29
    vierten
    -0.27
    POSITIVE LOGITS
     sizes
    0.98
     styles
    0.98
     genres
    0.94
     formats
    0.87
     types
    0.86
     nationalities
    0.83
     thicknesses
    0.82
     flavours
    0.81
     modes
    0.81
     colours
    0.81
    Act Density 1.029%

    No Known Activations