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

    Neuronpedia

    INDEX
    Explanations

    terms related to political history and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     utop
    -0.79
     logis
    -0.75
     zó
    -0.68
     Departement
    -0.66
     republi
    -0.65
     geolog
    -0.63
     gallina
    -0.61
     gita
    -0.61
     solidar
    -0.60
     stör
    -0.60
    POSITIVE LOGITS
     history
    0.72
    history
    0.63
     History
    0.57
     HISTORY
    0.55
     histories
    0.55
     voud
    0.53
     tradition
    0.53
    četně
    0.52
     record
    0.52
    textTheme
    0.52
    Act Density 0.199%

    No Known Activations