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

    Neuronpedia

    INDEX
    Explanations

    references to social roles and expectations, particularly regarding gender and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vieto
    -0.41
    Way
    -0.40
    ish
    -0.40
    事で
    -0.39
     égard
    -0.39
    性
    -0.38
    /
    -0.38
    Um
    -0.38
     modo
    -0.37
     particulares
    -0.35
    POSITIVE LOGITS
    ScopeManager
    0.94
     saites
    0.94
     brightest
    0.90
     '\\;'
    0.86
     loudest
    0.83
    ParallelGroup
    0.82
     betweenstory
    0.82
     MainAxisSize
    0.80
    WebVitals
    0.79
    grà
    0.78
    Act Density 0.327%

    No Known Activations