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

    Neuronpedia

    INDEX
    Explanations

    legal and criminal terms and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rencies
    -0.81
    urches
    -0.80
    hops
    -0.78
    rooms
    -0.78
     Machines
    -0.76
    andals
    -0.76
    builders
    -0.76
    lees
    -0.76
     Rooms
    -0.75
    places
    -0.74
    POSITIVE LOGITS
     standpoint
    0.83
     version
    0.72
     berth
    0.72
     dose
    0.70
     clause
    0.70
     approximation
    0.70
     haircut
    0.69
     degree
    0.69
     perspective
    0.68
     foothold
    0.68
    Act Density 0.759%

    No Known Activations