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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political matters and government policies

    oai_token-act-pair · gpt-3.5-turbo

    expressions and concepts related to politics and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cameo
    -0.65
    paio
    -0.63
     typo
    -0.62
     widow
    -0.62
     scout
    -0.62
     retracted
    -0.62
     teammate
    -0.62
    owler
    -0.61
     dunk
    -0.60
     caveat
    -0.60
    POSITIVE LOGITS
     worldwide
    0.91
    ankind
    0.91
    waves
    0.91
     globally
    0.88
     forever
    0.84
    making
    0.83
     affairs
    0.79
     destiny
    0.78
    soever
    0.78
     across
    0.74
    Act Density 0.428%

    No Known Activations