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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific projects or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to specific projects, particularly those labeled as "Project 9."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     barb
    -0.72
     rout
    -0.70
    igne
    -0.70
    chenko
    -0.69
     discipl
    -0.68
     seats
    -0.67
    ðŁĺ
    -0.66
     bishops
    -0.65
    emouth
    -0.65
     heed
    -0.65
    POSITIVE LOGITS
     Project
    3.81
    Project
    3.04
    project
    2.40
     Projects
    2.20
     project
    1.96
     projects
    1.65
    projects
    1.63
     Program
    1.43
     Initiative
    1.41
     PRO
    1.30
    Act Density 0.014%

    No Known Activations