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

    Neuronpedia

    INDEX
    Explanations

    topics related to political ideologies and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.61
     cérémonie
    -0.57
    adə
    -0.57
    addOn
    -0.56
     pilotes
    -0.54
     cittadini
    -0.54
     acús
    -0.53
     négociations
    -0.53
     hâte
    -0.53
    íqu
    -0.53
    POSITIVE LOGITS
     anti
    1.25
     liberal
    1.18
     radical
    1.12
     conservative
    1.10
    liberal
    0.98
     liberalism
    0.98
    conservative
    0.98
     neo
    0.96
     extremist
    0.95
     libertarian
    0.95
    Act Density 0.660%

    No Known Activations