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

    Neuronpedia

    INDEX
    Explanations

    references to the prevalence or dominance of specific categories or characteristics

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    dominant
    -0.94
     dominant
    -0.92
     Dominant
    -0.90
    photobucket
    -0.74
    RoutingModule
    -0.60
    Initializable
    -0.59
     verschil
    -0.57
    verwijspagina
    -0.56
     predominant
    -0.55
    IBarButtonItem
    -0.54
    POSITIVE LOGITS
     dominates
    1.77
     dominate
    1.73
     dominating
    1.05
     predominate
    0.93
    ugh
    0.79
    transQ
    0.75
     dominated
    0.73
     abound
    0.68
    انيف
    0.65
    waltung
    0.63
    Act Density 0.003%

    No Known Activations