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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stroke
    -0.80
    geon
    -0.78
    gar
    -0.78
    ixed
    -0.72
    fect
    -0.69
    dos
    -0.66
    riger
    -0.62
    Lew
    -0.62
     Nieto
    -0.61
    Rah
    -0.61
    POSITIVE LOGITS
     affili
    1.05
    ally
    1.03
     headquartered
    1.02
     sponsoring
    0.95
    ality
    0.91
     founded
    0.90
     disbanded
    0.90
     affiliation
    0.86
     affiliated
    0.85
     devoted
    0.83
    Act Density 0.059%

    No Known Activations