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

    Neuronpedia

    INDEX
    Explanations

    references to trips or travel-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </thead>
    -0.92
     Kelle
    -0.73
     שוליים
    -0.67
     Nadel
    -0.67
     Kell
    -0.66
    cella
    -0.65
    Weiss
    -0.65
     Bracken
    -0.65
    Judi
    -0.63
    larıyla
    -0.63
    POSITIVE LOGITS
     trip
    1.64
     Trips
    1.58
     trips
    1.55
    trip
    1.48
    trips
    1.47
     Trip
    1.46
     TRIP
    1.40
    Trip
    1.40
    Trips
    1.37
    TRIP
    1.30
    Act Density 0.072%

    No Known Activations