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

    Neuronpedia

    INDEX
    Explanations

    words related to software or technology processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koreans
    -0.66
    TRUMP
    -0.62
     Europeans
    -0.60
    icter
    -0.59
     aliens
    -0.59
    submit
    -0.59
     Indones
    -0.59
     commenter
    -0.58
     negotiators
    -0.58
    CHAT
    -0.58
    POSITIVE LOGITS
     shores
    0.90
     inaugural
    0.81
     midst
    0.80
     deepest
    0.80
     backyard
    0.80
     behalf
    0.80
     doorstep
    0.79
     premises
    0.79
     own
    0.78
     basement
    0.77
    Act Density 0.155%

    No Known Activations