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

    Neuronpedia

    INDEX
    Explanations

    expressions related to finance and economic systems

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

    Follows certain prepositions

    np_acts-logits-general · gemini-2.0-flash

    aggregation functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.20
     myſelf
    -1.00
     themſelves
    -0.96
     himſelf
    -0.96
     raiſ
    -0.91
     poffible
    -0.90
     houſe
    -0.89
     perſon
    -0.88
     auffi
    -0.87
     faſt
    -0.87
    POSITIVE LOGITS
     fucking
    0.64
    ございません
    0.56
    っております
    0.56
     hereby
    0.55
    でございます
    0.55
    ooga
    0.55
    俺は
    0.55
    ございました
    0.55
    おります
    0.54
     korban
    0.54
    Act Density 0.645%

    No Known Activations