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

    Neuronpedia

    INDEX
    Explanations

    XML-like tags and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    niſſe
    -0.91
    ロウィン
    -0.91
     ſind
    -0.90
    GEBURTSDATUM
    -0.90
     queſta
    -0.90
    saraba
    -0.89
    ########.
    -0.88
    ſſung
    -0.87
    OGND
    -0.86
    хьтан
    -0.86
    POSITIVE LOGITS
     again
    0.33
    ↵
    0.32
     batch
    0.29
     subsequent
    0.29
    Client
    0.29
     update
    0.28
     visitar
    0.28
    ॉल
    0.28
     client
    0.27
    ↵↵
    0.26
    Act Density 0.006%

    No Known Activations