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

    Neuronpedia

    INDEX
    Explanations

    issues related to access to resources and opportunities for marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canon
    -0.84
     Fool
    -0.74
     Tarant
    -0.70
     Comet
    -0.69
     Discord
    -0.68
    */(
    -0.66
    Fake
    -0.66
    Rum
    -0.65
    tons
    -0.65
    Recipe
    -0.65
    POSITIVE LOGITS
     resettlement
    1.07
     medically
    1.07
     caregivers
    1.03
     careg
    1.02
     disability
    0.98
     outpatient
    0.96
     homelessness
    0.96
     medication
    0.92
     treatment
    0.92
     healthcare
    0.92
    Act Density 0.304%

    No Known Activations