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

    Neuronpedia

    INDEX
    Explanations

    amounts of money specified in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    staking
    -0.80
    esville
    -0.71
    sym
    -0.67
    knife
    -0.62
    antha
    -0.60
     swearing
    -0.58
     ail
    -0.55
    FontSize
    -0.54
    stakes
    -0.54
     mell
    -0.53
    POSITIVE LOGITS
    rd
    2.16
    RD
    1.24
    DS
    1.06
    dfx
    1.03
    peat
    0.98
    DES
    0.89
    PO
    0.89
    ds
    0.88
     quarters
    0.80
    DP
    0.80
    Act Density 0.096%

    No Known Activations