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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global initiatives or plans

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical regions and their relations to larger global initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wered
    -0.77
     lowly
    -0.73
     slightest
    -0.64
     outnumbered
    -0.64
     gunshots
    -0.62
    ampires
    -0.62
     Akin
    -0.62
     breasts
    -0.62
     sucks
    -0.62
     crashing
    -0.61
    POSITIVE LOGITS
     preparations
    0.97
     continuum
    0.96
     effort
    0.95
     plan
    0.92
     strategy
    0.91
     efforts
    0.86
     roadmap
    0.86
     agenda
    0.85
    igsaw
    0.85
    Operation
    0.85
    Act Density 0.267%

    No Known Activations