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

    Neuronpedia

    INDEX
    Explanations

    words related to political conflicts and social causes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conflict or resistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waivers
    -0.70
     Atmospheric
    -0.67
    NULL
    -0.65
    ascript
    -0.64
     Seym
    -0.63
     Investigator
    -0.62
     Mist
    -0.61
     Subtle
    -0.60
     inspected
    -0.58
     unpop
    -0.56
    POSITIVE LOGITS
     against
    1.36
     waged
    1.19
     Against
    1.16
    against
    1.16
    Against
    0.92
    front
    0.83
     toward
    0.82
    back
    0.80
     fought
    0.80
     underway
    0.79
    Act Density 0.108%

    No Known Activations