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

    Neuronpedia

    INDEX
    Explanations

    places and locations that involve security checks like train stations, airports, and paranormal investigation sites

    oai_token-act-pair · gpt-3.5-turbo

    locations or contexts associated with various public activities and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLIED
    -0.54
     WARN
    -0.53
     TODAY
    -0.48
    ItemTracker
    -0.46
     Grassley
    -0.46
    ^^^^
    -0.46
     Unch
    -0.45
     Gork
    -0.45
    Spoiler
    -0.45
     Woodward
    -0.44
    POSITIVE LOGITS
     respectively
    1.00
     etc
    0.86
     alike
    0.83
     thereof
    0.78
    depending
    0.56
    .).
    0.55
     whichever
    0.54
     attRot
    0.51
     versa
    0.51
    etc
    0.50
    Act Density 1.552%

    No Known Activations