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

    Neuronpedia

    INDEX
    Explanations

    demonstratives that emphasize identity and relationship

    oai_token-act-pair · gpt-3.5-turbo

    expressions of identity and community within a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reilly
    -0.77
    indal
    -0.72
    stroke
    -0.72
    èĥ
    -0.66
    ulence
    -0.65
    gency
    -0.64
    iculty
    -0.63
    è£ħ
    -0.63
    rounder
    -0.61
     boost
    -0.60
    POSITIVE LOGITS
     ourselves
    1.05
     stewards
    1.04
     brothers
    1.04
     educators
    1.03
     humans
    1.00
     citizens
    1.00
     Americans
    0.98
     learners
    0.96
     Christians
    0.96
    humans
    0.96
    Act Density 0.249%

    No Known Activations