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

    Neuronpedia

    INDEX
    Explanations

    words related to deceitful behavior or false appearances

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pret" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.89
    OTE
    -0.65
     Annotations
    -0.65
     [|
    -0.65
    stocks
    -0.64
    士
    -0.64
    OTOS
    -0.64
     Observatory
    -0.62
    itability
    -0.62
    SHIP
    -0.62
    POSITIVE LOGITS
    entious
    1.13
    reatment
    1.10
    rial
    1.00
    reating
    0.98
    zel
    0.95
    estate
    0.94
    heon
    0.93
    reated
    0.92
    inent
    0.89
     pret
    0.85
    Act Density 0.039%

    No Known Activations