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

    Neuronpedia

    INDEX
    Explanations

    references to authority and critical assessments of certain ideological perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.94
     https
    -0.84
    https
    -0.79
     incentiv
    -0.78
     microbiome
    -0.75
    ​​​​
    -0.72
     impactful
    -0.69
    ​​
    -0.67
     curated
    -0.66
     LGBTQ
    -0.65
    POSITIVE LOGITS
     daß
    1.17
     mußte
    1.08
     mußten
    1.06
     muß
    1.01
     läßt
    1.01
     Daß
    1.00
     müßte
    0.98
    ^(@)
    0.96
    faßt
    0.95
     wußte
    0.93
    Act Density 5.775%

    No Known Activations