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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies and power dynamics, specifically focusing on conservative views and government branches

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political power structures and factions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miko
    -0.68
    ishable
    -0.67
    amaz
    -0.66
     Redd
    -0.64
    subject
    -0.63
     Fields
    -0.63
     Hig
    -0.62
    eating
    -0.60
     Subjects
    -0.59
     Requ
    -0.59
    POSITIVE LOGITS
    erity
    0.84
     assembled
    0.80
    ariat
    0.79
     playbook
    0.78
    ablishment
    0.75
    rons
    0.75
     establishment
    0.72
     whip
    0.69
     dysfunction
    0.68
    tones
    0.68
    Act Density 0.135%

    No Known Activations