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

    Neuronpedia

    INDEX
    Explanations

    concepts related to classification systems and taxonomies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orris
    -0.15
    formats
    -0.15
    peq
    -0.14
     Blank
    -0.14
    ara
    -0.14
    roc
    -0.13
    Formats
    -0.13
     RectTransform
    -0.13
     Formats
    -0.13
    uentes
    -0.13
    POSITIVE LOGITS
     assignment
    0.31
     assigning
    0.29
    åĪĨç±»
    0.29
     categor
    0.29
     assign
    0.29
     ë¶Ħë¥ĺ
    0.28
     division
    0.28
     Assign
    0.28
     classification
    0.27
    Assign
    0.27
    Act Density 0.351%

    No Known Activations