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

    Neuronpedia

    INDEX
    Explanations

    texts related to programming and coding concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ×ij
    -0.69
    ×ŀ
    -0.68
    ded
    -0.66
    de
    -0.66
    gg
    -0.63
    Gaza
    -0.62
    ×Ķ
    -0.61
    ×ķ
    -0.60
     Hills
    -0.60
    oning
    -0.60
    POSITIVE LOGITS
     concepts
    1.24
     Concepts
    1.05
    afety
    0.93
    ĸļ
    0.85
    ually
    0.85
    uggest
    0.83
     guiActiveUn
    0.78
    cape
    0.78
    concept
    0.78
     notions
    0.78
    Act Density 0.009%

    No Known Activations