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

    Neuronpedia

    INDEX
    Explanations

    references to specific airlines and their operational policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.15
    æ±½
    -0.15
    ãĥ¼ãĥī
    -0.15
    ackets
    -0.14
    ugar
    -0.14
    é¦
    -0.14
    aki
    -0.14
    iras
    -0.14
    Dll
    -0.14
    ainless
    -0.14
    POSITIVE LOGITS
     flight
    0.28
     Boeing
    0.27
     grounded
    0.26
     grounding
    0.25
     Flight
    0.24
     cabin
    0.24
     flights
    0.23
     crew
    0.23
     Airlines
    0.23
     bmi
    0.23
    Act Density 0.060%

    No Known Activations