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

    Neuronpedia

    INDEX
    Explanations

    structured formats and data organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confiable
    -1.01
     favors
    -0.99
    Neighbors
    -0.96
     parlor
    -0.95
     favorably
    -0.93
     flavorful
    -0.93
    ônicos
    -0.92
     flavors
    -0.92
     neighbors
    -0.92
    ônico
    -0.91
    POSITIVE LOGITS
    Whilst
    1.70
     Whilst
    1.64
    initialise
    1.40
     realised
    1.40
     specialises
    1.39
     realising
    1.37
     tyres
    1.37
     whilst
    1.37
     realise
    1.36
     enquiries
    1.35
    Act Density 5.904%

    No Known Activations