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

    Neuronpedia

    INDEX
    Explanations

    phrases related to declarations or statements of political significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rotina
    -0.39
    اعده
    -0.36
     informée
    -0.34
     routine
    -0.33
     fussy
    -0.33
    Quite
    -0.33
     Vereins
    -0.32
     rutina
    -0.32
     impact
    -0.32
     perceptions
    -0.32
    POSITIVE LOGITS
     patriotic
    0.98
     patriotism
    0.93
     patriots
    0.90
     patriot
    0.86
     patrio
    0.78
     nation
    0.77
     patrie
    0.77
     unity
    0.73
    nation
    0.71
     Nation
    0.71
    Act Density 0.352%

    No Known Activations