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

    Neuronpedia

    INDEX
    Explanations

    references to a specific publication, "The Washington Post."

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Washington Post."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.88
    ãĥ¼ãĤ¯
    -0.76
    oj
    -0.72
    itional
    -0.70
    utory
    -0.68
    cles
    -0.65
    ãĤ¤ãĥĪ
    -0.65
    together
    -0.65
    itations
    -0.64
    ename
    -0.63
    POSITIVE LOGITS
    PLIED
    0.83
     Weekly
    0.76
     Tribune
    0.74
     Digest
    0.74
     Diary
    0.72
     Observer
    0.70
     Correspond
    0.69
     Dispatch
    0.69
     Magazine
    0.68
     Inqu
    0.68
    Act Density 0.054%

    No Known Activations