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

    Neuronpedia

    INDEX
    Explanations

    the word "plans" and its associated phrases indicating future intentions or proposals

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

    plans for future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istore
    -0.53
     enfans
    -0.49
    GEBURTSDATUM
    -0.46
     caneca
    -0.46
     akumulator
    -0.46
     بيها
    -0.44
     charité
    -0.44
     pinulongan
    -0.44
     agujas
    -0.44
     camiset
    -0.43
    POSITIVE LOGITS
     plans
    1.93
    Plans
    1.88
     Plans
    1.87
    plans
    1.74
     PLANS
    1.64
     Pläne
    1.39
     планы
    0.99
     planos
    0.97
    Planned
    0.82
    planned
    0.77
    Act Density 0.005%

    No Known Activations