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

    Neuronpedia

    INDEX
    Explanations

    references to explosive or forceful events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    guyen
    -0.76
    ipeg
    -0.66
    Govern
    -0.66
    ADRA
    -0.66
    Trust
    -0.63
     compr
    -0.63
     Aware
    -0.63
    ournal
    -0.63
    sit
    -0.62
     Solitaire
    -0.60
    POSITIVE LOGITS
     furnace
    1.20
    hower
    1.00
    waves
    0.93
    ocy
    0.90
    blast
    0.90
    ocalypse
    0.86
    ographed
    0.86
     furn
    0.86
     blast
    0.81
    rack
    0.81
    Act Density 0.026%

    No Known Activations