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

    Neuronpedia

    INDEX
    Explanations

    capitalized proper nouns and abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    monton
    -0.17
    ablish
    -0.17
    771
    -0.15
    orough
    -0.14
    raison
    -0.14
    parity
    -0.13
    \Annotation
    -0.13
    ipc
    -0.13
     MEMORY
    -0.13
    วย
    -0.13
    POSITIVE LOGITS
    eron
    0.15
    utt
    0.15
     finished
    0.13
    enis
    0.13
    eren
    0.13
     thor
    0.13
     Thor
    0.13
    æ¸Ī
    0.13
     Toys
    0.13
     Fut
    0.13
    Act Density 0.975%

    No Known Activations