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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes indicative of dialogue or naming in film-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.34
    .
    -0.20
    ãĢĮãģĬ
    -0.18
    ,S
    -0.18
    ↵
    -0.17
     “[
    -0.17
    ,“
    -0.17
     âĢŀ
    -0.17
    ãĢĮãģĤ
    -0.17
    &nbsp
    -0.17
    POSITIVE LOGITS
    Haunted
    0.21
    Untitled
    0.19
    Tonight
    0.19
    100
    0.18
    ¡
    0.18
    Yesterday
    0.18
    Everybody
    0.17
    Slinky
    0.17
    Caught
    0.17
    99
    0.17
    Act Density 0.089%

    No Known Activations