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

    Neuronpedia

    INDEX
    Explanations

    references to monetary values, specifically in USD

    oai_token-act-pair · gpt-3.5-turbo

    monetary values in the form of USD

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resemb
    -0.77
    je
    -0.70
    borough
    -0.69
    otine
    -0.68
    door
    -0.68
    idem
    -0.68
    away
    -0.67
    naires
    -0.67
    addons
    -0.67
    aways
    -0.67
    POSITIVE LOGITS
    ORTS
    1.03
    USD
    0.88
    ICAN
    0.86
    UAL
    0.84
    ION
    0.84
    MY
    0.83
    ANK
    0.82
    ollar
    0.81
    $
    0.81
    ANA
    0.80
    Act Density 0.029%

    No Known Activations