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

    Neuronpedia

    INDEX
    Explanations

    concepts related to computing, specifically in the context of neural networks and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    referrer
    -0.17
    ugar
    -0.17
    angel
    -0.14
    หย
    -0.14
    ackages
    -0.14
    aku
    -0.14
    _dispatcher
    -0.13
    ıs
    -0.13
    hek
    -0.13
     kre
    -0.13
    POSITIVE LOGITS
     feature
    0.23
     Mah
    0.23
     mah
    0.21
     features
    0.20
     explaining
    0.20
    -feature
    0.20
     latent
    0.19
     PCs
    0.19
    /features
    0.19
    feature
    0.18
    Act Density 0.030%

    No Known Activations