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

    Neuronpedia

    INDEX
    Explanations

    references to financial interest and interest rates

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

    "interest"

    np_acts-logits-general · gemini-2.0-flash

    interest rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.59
    Autoritní
    -0.58
     Mó
    -0.53
     jaws
    -0.53
     shovels
    -0.53
     aly
    -0.52
     Caw
    -0.52
    loài
    -0.52
     rooftops
    -0.51
    ﴿
    -0.51
    POSITIVE LOGITS
     interest
    2.02
     Interest
    2.00
    interest
    1.91
    Interest
    1.89
     INTEREST
    1.59
    INTEREST
    1.53
     Interests
    1.47
     interests
    1.47
     interés
    1.38
    interests
    1.31
    Act Density 0.157%

    No Known Activations