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

    Neuronpedia

    INDEX
    Explanations

    terms related to nuclear weaponry and warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.92
    Vidite
    -0.79
    ViewFeatures
    -0.72
    Referințe
    -0.71
     Sienna
    -0.69
     Curs
    -0.67
    Personensuche
    -0.67
    DockStyle
    -0.66
     plato
    -0.66
     Viceroy
    -0.65
    POSITIVE LOGITS
     nuclear
    2.19
    nuclear
    1.96
     Nuclear
    1.94
    Nuclear
    1.90
     NUCLEAR
    1.79
     nucléaire
    1.74
    uclear
    1.50
     nuclei
    1.43
     nukes
    1.37
    核
    1.34
    Act Density 0.104%

    No Known Activations