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

    Neuronpedia

    INDEX
    Explanations

    references to projects and project-related terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ammans
    -0.80
     uſed
    -0.77
     whoſe
    -0.72
    antlr
    -0.70
     écl
    -0.70
     Efq
    -0.69
     tuturor
    -0.66
     Chew
    -0.65
     Cuth
    -0.65
     himſelf
    -0.65
    POSITIVE LOGITS
     projects
    1.77
     project
    1.72
     Project
    1.71
     PROJECT
    1.69
     Projects
    1.68
    PROJECT
    1.59
    Project
    1.57
    project
    1.49
    Projects
    1.49
     PROJECTS
    1.45
    Act Density 0.102%

    No Known Activations