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

    Neuronpedia

    INDEX
    Explanations

    content related to deception and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Whilst
    -1.17
     Whilst
    -1.14
     tyres
    -1.12
     realised
    -1.11
    labour
    -1.11
     analysed
    -1.09
     specialises
    -1.08
     recognised
    -1.05
    behaviour
    -1.05
    Analyse
    -1.04
    POSITIVE LOGITS
     parlor
    1.04
     confiable
    1.01
     favors
    1.01
     favorably
    0.97
     theaters
    0.97
     flavorful
    0.96
    ônicos
    0.96
     flavors
    0.96
     flavor
    0.94
     theater
    0.94
    Act Density 2.568%

    No Known Activations