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

    Neuronpedia

    INDEX
    Explanations

    titles and names of films and shows, particularly those that are playful or risqué in nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .X
    -0.18
    .V
    -0.15
    &E
    -0.14
    .Z
    -0.14
    &B
    -0.14
    ãĤĴãģĭ
    -0.14
    .Îł
    -0.14
     fb
    -0.14
    ê»
    -0.14
    &C
    -0.14
    POSITIVE LOGITS
    nech
    0.16
    vyk
    0.15
    .Actions
    0.14
     frau
    0.14
    PRICE
    0.14
    fout
    0.14
    ilians
    0.13
    .Migrations
    0.13
    oons
    0.13
    orry
    0.13
    Act Density 0.016%

    No Known Activations