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

    Neuronpedia

    INDEX
    Explanations

    references to gender differences in health-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comparative adjectives or adverbs

    np_acts-logits-general · gemini-2.0-flash

    more often or higher levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zości
    -0.52
     bVar
    -0.43
    consulté
    -0.43
    ResumeLayout
    -0.40
    zość
    -0.40
    Tja
    -0.40
    InjectAttribute
    -0.39
     nada
    -0.39
    misu
    -0.38
    spyOn
    -0.38
    POSITIVE LOGITS
     easier
    2.16
     better
    2.15
     stronger
    2.15
     clearer
    2.08
     more
    2.07
     quicker
    2.05
     faster
    2.02
     sharper
    2.02
     harder
    2.02
     happier
    2.01
    Act Density 2.002%

    No Known Activations