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

    Neuronpedia

    INDEX
    Explanations

    references to trips and travel-related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </thead>
    -0.96
     Kell
    -0.68
    erías
    -0.65
    ffl
    -0.64
    gasus
    -0.63
     Bant
    -0.63
     Mante
    -0.62
     Nadel
    -0.60
     ۱۳۸
    -0.60
     MPR
    -0.60
    POSITIVE LOGITS
     Trips
    1.59
     trip
    1.57
     trips
    1.57
    trip
    1.57
     Trip
    1.51
    trips
    1.50
    Trip
    1.49
    Trips
    1.44
    TRIP
    1.41
     TRIP
    1.40
    Act Density 0.008%

    No Known Activations