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

    Neuronpedia

    INDEX
    Explanations

    personal actions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.79
    soDeliveryDate
    -0.71
    quickShipAvailable
    -0.67
    OULD
    -0.65
    IBLE
    -0.63
    interstitial
    -0.62
    JV
    -0.62
    ãĤ¬
    -0.61
    PRES
    -0.61
     Anyway
    -0.60
    POSITIVE LOGITS
     failed
    1.01
     botched
    0.88
     successfully
    0.87
     publicized
    0.83
     debunked
    0.81
     completed
    0.81
     disembark
    0.79
     unsuccessfully
    0.79
     acquitted
    0.78
     unsuccessful
    0.78
    Act Density 0.141%

    No Known Activations