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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize honesty and transparency in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.54
    SBATCH
    -0.47
     disambiguazione
    -0.47
    scryfall
    -0.43
    thâu
    -0.41
     uLocal
    -0.41
    NameInMap
    -0.37
    ########.
    -0.37
     coorden
    -0.36
     Numerade
    -0.36
    POSITIVE LOGITS
     honest
    2.44
     honesty
    2.38
    honest
    2.09
     honestly
    1.95
    Honest
    1.93
     Honest
    1.91
     truthful
    1.88
     Honesty
    1.86
     honnête
    1.77
     frank
    1.70
    Act Density 0.493%

    No Known Activations