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

    Neuronpedia

    INDEX
    Explanations

    words related to planning and organization

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to planning and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.72
    ér
    -0.67
    otten
    -0.66
    PLIED
    -0.66
    vine
    -0.65
    ved
    -0.64
    icient
    -0.64
    terness
    -0.64
    ensis
    -0.63
    rite
    -0.63
    POSITIVE LOGITS
     ACTIONS
    1.02
     itiner
    0.88
     deployment
    0.77
     contingency
    0.76
     trip
    0.75
     evacuation
    0.75
     rollout
    0.73
     future
    0.73
     events
    0.73
     seating
    0.71
    Act Density 0.345%

    No Known Activations