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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political campaigns, speeches, and statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.79
    fal
    -0.68
    of
    -0.68
    ãĤ·ãĥ£
    -0.68
    nings
    -0.66
    Of
    -0.66
    phal
    -0.65
    adr
    -0.64
    rin
    -0.60
     flow
    -0.60
    POSITIVE LOGITS
     extensively
    1.20
     furiously
    1.03
     tirelessly
    1.02
     alongside
    1.02
     against
    0.99
     passionately
    0.94
     peacefully
    0.93
     vigorously
    0.92
     diligently
    0.89
     loudly
    0.88
    Act Density 0.155%

    No Known Activations