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

    Neuronpedia

    INDEX
    Explanations

    references to spatial locations or corners in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    corner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TIM
    -0.37
     Fiscal
    -0.36
     US
    -0.36
     USAF
    -0.35
     USA
    -0.35
     ​​
    -0.34
     NIH
    -0.34
     Illinois
    -0.34
     Thai
    -0.34
     Facebook
    -0.33
    POSITIVE LOGITS
     corner
    2.33
     Corner
    2.19
    Corner
    2.17
    corner
    2.16
     CORNER
    2.09
     corners
    2.02
     Corners
    1.80
    corners
    1.73
    Corners
    1.57
     esquina
    1.52
    Act Density 0.005%

    No Known Activations