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

    Neuronpedia

    INDEX
    Explanations

    financial transactions or amounts of money mentioned within a text

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and spending references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.90
    Kenn
    -0.87
     Keane
    -0.83
     Shank
    -0.83
    Ke
    -0.83
    Lay
    -0.79
    hern
    -0.79
    kay
    -0.77
    ickets
    -0.75
    her
    -0.74
    POSITIVE LOGITS
     100
    1.61
     98
    1.58
     99
    1.55
     101
    1.42
    100
    1.42
     102
    1.38
     96
    1.37
     97
    1.37
     103
    1.25
    99
    1.22
    Act Density 0.191%

    No Known Activations