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

    Neuronpedia

    INDEX
    Explanations

    nuclear-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    knapp
    -0.84
    Vidite
    -0.84
     CommonModule
    -0.80
    GrantedAuthority
    -0.77
     Phari
    -0.76
     defaultstate
    -0.76
     Roskov
    -0.75
     WaitForSeconds
    -0.74
    SuppressMessage
    -0.72
     Viceroy
    -0.70
    POSITIVE LOGITS
     nuclear
    1.40
     Nuclear
    1.28
    nuclear
    1.24
    Nuclear
    1.22
     NUCLEAR
    1.14
    uclear
    1.08
     nucléaire
    1.04
     nukes
    0.94
    NUC
    0.94
     nuclei
    0.91
    Act Density 0.095%

    No Known Activations