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

    Neuronpedia

    INDEX
    Explanations

    phrases related to vehicles and transportation

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and their movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metics
    -0.75
     vocabulary
    -0.72
    rue
    -0.72
    urable
    -0.71
     Lauder
    -0.70
    olon
    -0.70
    fol
    -0.69
     attribute
    -0.66
    ollah
    -0.65
     empowerment
    -0.65
    POSITIVE LOGITS
     parked
    1.12
     crashed
    1.08
     wreckage
    0.95
     takeoff
    0.90
     towed
    0.89
     tow
    0.86
     convoy
    0.86
    Crash
    0.86
     reconnaissance
    0.85
     collided
    0.85
    Act Density 0.319%

    No Known Activations