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

    Neuronpedia

    INDEX
    Explanations

    phrases related to astronomical objects, especially the Milky Way

    oai_token-act-pair · gpt-3.5-turbo

    references to galaxies and the Silk Road

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itars
    -0.72
    psons
    -0.72
    unci
    -0.68
    ded
    -0.68
    pent
    -0.67
    itent
    -0.66
     propri
    -0.66
     accur
    -0.65
    AMI
    -0.65
    ounter
    -0.65
    POSITIVE LOGITS
     Circle
    0.88
    WAY
    0.81
     Gate
    0.80
     Fields
    0.78
     Tide
    0.78
     Basin
    0.76
     Width
    0.75
     Corridor
    0.75
     Gates
    0.75
     Grove
    0.74
    Act Density 0.075%

    No Known Activations