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

    Neuronpedia

    INDEX
    Explanations

    the presence of ordinal numbers and references to positions in sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -Identifier
    -0.17
     firstly
    -0.16
    ssel
    -0.15
    æľĢåIJİ
    -0.15
     finally
    -0.14
    /dialog
    -0.14
     cuá»iji
    -0.14
     overposting
    -0.13
     further
    -0.13
    åı¦å¤ĸ
    -0.13
    POSITIVE LOGITS
    -ever
    0.46
     few
    0.38
    -time
    0.35
    born
    0.35
    -rate
    0.33
    -hand
    0.33
    -generation
    0.32
    s
    0.31
    -person
    0.30
     ever
    0.30
    Act Density 0.132%

    No Known Activations