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

    Neuronpedia

    INDEX
    Explanations

    implementation-related terms and code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.18
     Ages
    -0.17
    eldon
    -0.16
    assi
    -0.15
    riel
    -0.15
     weighted
    -0.15
     Hilton
    -0.15
    ạnh
    -0.15
    ummies
    -0.15
    elle
    -0.15
    POSITIVE LOGITS
    ัà¸ģษà¸ĵ
    0.20
    umb
    0.20
    omb
    0.19
    acency
    0.19
    ike
    0.18
    otti
    0.17
    enet
    0.17
    ause
    0.17
    ough
    0.17
    astic
    0.17
    Act Density 0.032%

    No Known Activations