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

    Neuronpedia

    INDEX
    Explanations

    references to specific areas of research or focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arus
    -0.17
    xico
    -0.15
    HH
    -0.15
    uur
    -0.15
    511
    -0.15
     SÆ¡n
    -0.14
    Multiplicity
    -0.14
    185
    -0.14
    arde
    -0.14
    ilst
    -0.14
    POSITIVE LOGITS
     field
    0.31
     areas
    0.29
     fields
    0.28
     area
    0.28
     Bereich
    0.27
     lĩnh
    0.26
     área
    0.25
    areas
    0.25
     category
    0.25
    -field
    0.25
    Act Density 0.145%

    No Known Activations