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

    Neuronpedia

    INDEX
    Explanations

    descriptive text about hotels or resorts coupled with personal opinions

    oai_token-act-pair · gemini-2.0-flash

    luxury accommodations

    np_token-act-pair-logits · gpt-4o-mini

    Hotels and resorts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.69
     Theſe
    -0.66
     Monfieur
    -0.65
     whoſe
    -0.65
     faſt
    -0.65
     Anſ
    -0.64
     preſent
    -0.63
     Jefus
    -0.61
     againſt
    -0.61
     fevere
    -0.61
    POSITIVE LOGITS
     doGet
    0.49
     high
    0.49
     haut
    0.47
     Sands
    0.47
    JW
    0.47
    geqslant
    0.47
     upscale
    0.46
     Roe
    0.46
    taja
    0.45
    ,=
    0.44
    Act Density 1.383%

    No Known Activations