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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "work."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    work and related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.39
     following
    -0.37
    tapkan
    -0.36
     sociedade
    -0.36
     Frankel
    -0.35
     ModelRenderer
    -0.34
     Genau
    -0.34
     camadas
    -0.33
     Glaser
    -0.33
     respeito
    -0.33
    POSITIVE LOGITS
    Work
    1.27
     Work
    1.21
     work
    1.19
     WORK
    1.08
    work
    1.08
    WORK
    1.02
     werk
    0.94
     Arbeit
    0.87
     Trabajo
    0.87
     arbeid
    0.86
    Act Density 0.036%

    No Known Activations