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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation towards people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     curfew
    -0.73
     Worse
    -0.67
     Doctrine
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    thing
    -0.63
     Throne
    -0.63
    Hide
    -0.63
     Uniform
    -0.61
     Catholicism
    -0.59
     Zionism
    -0.59
    POSITIVE LOGITS
     generously
    0.96
     contributions
    0.95
     Cosponsors
    0.91
     contributors
    0.90
    rats
    0.87
     generous
    0.86
     encour
    0.83
     generosity
    0.82
     participating
    0.80
     contributing
    0.80
    Act Density 0.080%

    No Known Activations