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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future intentions or plans

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

    planning on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pēc
    -0.32
    ุท
    -0.30
     šķ
    -0.30
     deberes
    -0.29
     estaciones
    -0.29
     banderas
    -0.29
    "}")
    -0.29
     jei
    -0.29
     scienza
    -0.28
     dinámico
    -0.28
    POSITIVE LOGITS
    Planning
    0.98
     Planning
    0.98
     planning
    0.96
    planning
    0.93
     PLANNING
    0.83
    :✨
    0.75
    planner
    0.73
     surla
    0.69
    planned
    0.69
    Planned
    0.68
    Act Density 0.006%

    No Known Activations