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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific attributes and details that describe objects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Whilst
    -1.47
     Whilst
    -1.41
     realised
    -1.23
    initialise
    -1.19
     tyres
    -1.18
     whilst
    -1.18
     specialises
    -1.17
     realising
    -1.17
     enquiries
    -1.16
     realise
    -1.16
    POSITIVE LOGITS
     confiable
    1.16
     parlor
    1.14
     favors
    1.10
     flavorful
    1.09
    ônicos
    1.06
     favorably
    1.04
    Neighbors
    1.03
     flavors
    1.03
     neighbors
    1.03
     Neighbors
    1.02
    Act Density 7.048%

    No Known Activations