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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transactions or exchanges

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving exchanges or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.90
    geist
    -0.87
    iaries
    -0.75
    gow
    -0.75
    oor
    -0.74
    quickShipAvailable
    -0.72
    onder
    -0.71
    Ind
    -0.70
    ister
    -0.69
    Nav
    -0.69
    POSITIVE LOGITS
     agreeing
    0.96
    geries
    0.92
     bribes
    0.92
     concessions
    0.91
    gery
    0.90
     preserving
    0.87
     assurances
    0.85
     terminating
    0.84
     retrieving
    0.82
     submitting
    0.81
    Act Density 0.071%

    No Known Activations