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

    Neuronpedia

    INDEX
    Explanations

    references to horizontal orientation or positioning

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

    horizontal spatial context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pep
    -0.43
     pep
    -0.39
     pea
    -0.38
    LabelTagHelper
    -0.38
     Wür
    -0.38
     Muerte
    -0.37
     Pues
    -0.36
    例句
    -0.35
    assertIs
    -0.35
    </tbody>
    -0.34
    POSITIVE LOGITS
     horizontal
    1.94
     Horizontal
    1.93
    horizontal
    1.82
    Horizontal
    1.80
     horizontally
    1.63
     horizont
    1.52
    HORIZONTAL
    1.47
     orizz
    1.35
     horiz
    1.33
     Horiz
    1.27
    Act Density 0.008%

    No Known Activations