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

    Neuronpedia

    INDEX
    Explanations

    references to airline flights and travel details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of flights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Harris
    -0.67
    PUT
    -0.66
    laus
    -0.66
    âĶĢâĶĢ
    -0.64
    ãĥ¤
    -0.64
    1920
    -0.62
    lder
    -0.62
    ENTION
    -0.62
     Territories
    -0.61
    izont
    -0.60
    POSITIVE LOGITS
     flights
    1.26
    pread
    1.06
    peed
    0.95
    planes
    0.90
    plane
    0.89
    mares
    0.88
    walker
    0.87
    afety
    0.87
    uggest
    0.86
     planes
    0.86
    Act Density 0.010%

    No Known Activations