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

    Neuronpedia

    INDEX
    Explanations

    phrases related to foundations, organizations, and fundraising

    oai_token-act-pair · gpt-3.5-turbo

    references to various foundations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.72
    thin
    -0.72
     Machines
    -0.68
    corn
    -0.68
    Balt
    -0.66
    lan
    -0.66
    dos
    -0.65
    strip
    -0.63
    lass
    -0.62
    teenth
    -0.61
    POSITIVE LOGITS
     foundation
    0.94
     Foundation
    0.92
     trustees
    0.78
    fman
    0.73
     donor
    0.72
     Seym
    0.70
    onic
    0.70
     trustee
    0.68
    foundation
    0.67
    onica
    0.67
    Act Density 0.010%

    No Known Activations