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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĴĪ
    -0.20
    brains
    -0.16
    ÃŃd
    -0.15
    691
    -0.15
     holes
    -0.14
    aju
    -0.14
    zones
    -0.14
    ÃŃl
    -0.14
    ÏģοÏį
    -0.14
    oyo
    -0.14
    POSITIVE LOGITS
     corner
    0.57
    corner
    0.50
    Corner
    0.45
     Corner
    0.44
    -corner
    0.43
     corners
    0.38
     bend
    0.37
     Bend
    0.31
    _corner
    0.27
     comer
    0.26
    Act Density 0.013%

    No Known Activations