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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and initiatives related to specific causes or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to human rights and advocacy organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accelerator
    -0.83
     bluff
    -0.82
     muster
    -0.82
     lessons
    -0.81
     simulator
    -0.77
     advis
    -0.77
     doom
    -0.77
     lesson
    -0.76
     sober
    -0.76
     melt
    -0.76
    POSITIVE LOGITS
     Subst
    1.18
     Diseases
    1.18
     Devices
    1.16
     Terrorism
    1.16
     Practices
    1.15
     Activities
    1.15
     Crimes
    1.09
     Discrimination
    1.07
     Abuse
    1.05
     Occupations
    1.03
    Act Density 0.119%

    No Known Activations