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

    Neuronpedia

    INDEX
    Explanations

    references to political ideals and democracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.95
     himſelf
    -0.85
     poffe
    -0.84
     itſelf
    -0.81
     Jefus
    -0.81
     myſelf
    -0.80
     edelstahl
    -0.80
     pleaſure
    -0.78
     Monfieur
    -0.77
     ſmall
    -0.76
    POSITIVE LOGITS
     political
    0.84
     global
    0.81
    political
    0.67
     Political
    0.63
    global
    0.60
     Global
    0.59
    poli
    0.58
     POLITICAL
    0.58
    Political
    0.57
    mergeFrom
    0.57
    Act Density 0.504%

    No Known Activations