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

    Neuronpedia

    INDEX
    Explanations

    statements related to government policy and public services

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorably
    -0.74
     someday
    -0.73
     utilizing
    -0.72
    heit
    -0.67
     localized
    -0.67
    boro
    -0.66
     endeavor
    -0.65
     favors
    -0.65
     favoring
    -0.65
     Palo
    -0.63
    POSITIVE LOGITS
    Labour
    1.24
    Scroll
    1.09
    Scotland
    0.97
    Britain
    0.96
     Labour
    0.94
    Liverpool
    0.93
    Shape
    0.88
     Trafford
    0.86
    England
    0.85
     Ukip
    0.84
    Act Density 0.298%

    No Known Activations