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

    Neuronpedia

    INDEX
    Explanations

    entity references in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burg
    -0.15
     heaven
    -0.15
    riel
    -0.14
    ilst
    -0.14
    -0.14
    bett
    -0.14
    å¼
    -0.13
     rew
    -0.13
    agit
    -0.13
    219
    -0.13
    POSITIVE LOGITS
    .generated
    0.15
    yp
    0.15
    udad
    0.14
    udades
    0.14
     Xã
    0.14
     subur
    0.13
     weave
    0.13
     Stark
    0.13
    lyph
    0.13
    bid
    0.13
    Act Density 0.011%

    No Known Activations