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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locations or objects within a space.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGHTS
    -0.75
    ITNESS
    -0.73
    ãĥīãĥ©
    -0.68
    ggies
    -0.67
    mx
    -0.65
    Privacy
    -0.65
     Qiao
    -0.64
    à¥
    -0.64
     ABE
    -0.63
    IVERS
    -0.62
    POSITIVE LOGITS
    pieces
    1.35
     fielder
    1.18
    piece
    0.98
    field
    0.88
    point
    0.86
     aisle
    0.83
    tenance
    0.82
    burst
    0.81
    liners
    0.80
    bell
    0.79
    Act Density 0.031%

    No Known Activations