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

    Neuronpedia

    INDEX
    Explanations

    keywords related to projects and management

    oai_token-act-pair · gpt-3.5-turbo

    references to specific projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     die
    -0.80
     Die
    -0.69
     act
    -0.68
     certified
    -0.67
     Fein
    -0.66
     mechanic
    -0.65
     acting
    -0.65
     Driver
    -0.64
     lunch
    -0.63
     merchant
    -0.63
    POSITIVE LOGITS
    Project
    3.37
    project
    2.15
    projects
    1.74
    Vert
    1.28
    Construction
    1.26
    Documents
    1.21
    Building
    1.21
    Vision
    1.20
    Phase
    1.19
    Development
    1.18
    Act Density 0.037%

    No Known Activations