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

    Neuronpedia

    INDEX
    Explanations

    military-related terms and references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.59
    etragen
    -0.50
    来说
    -0.49
    พล
    -0.49
    τως
    -0.48
     passers
    -0.47
    newswire
    -0.47
    hatikan
    -0.47
     aquí
    -0.47
    zijde
    -0.47
    POSITIVE LOGITS
     trip
    0.86
     trips
    0.86
     honeymoon
    0.75
     Trips
    0.74
     TRIP
    0.72
    Trips
    0.71
    trips
    0.71
    trip
    0.69
     travels
    0.69
    StoryboardSegue
    0.68
    Act Density 0.402%

    No Known Activations