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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political or social concepts, particularly those associated with democracy and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MV
    -0.65
     IF
    -0.65
     RH
    -0.64
     STATS
    -0.64
     CM
    -0.62
     notwithstanding
    -0.61
     Hobby
    -0.59
     rolling
    -0.59
     showc
    -0.58
     TW
    -0.58
    POSITIVE LOGITS
    eness
    0.99
    ated
    0.98
    acist
    0.96
    ates
    0.95
    ruction
    0.93
    ration
    0.92
    acists
    0.91
    uments
    0.91
    ciating
    0.91
    andum
    0.91
    Act Density 0.118%

    No Known Activations