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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "told" indicating communication or information being conveyed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information was told

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endblock
    -0.54
     houſe
    -0.52
     turntable
    -0.48
    StoryboardSegue
    -0.47
     aquarium
    -0.45
     pattes
    -0.44
     BoxFit
    -0.44
     elevator
    -0.44
     archive
    -0.43
    Derp
    -0.43
    POSITIVE LOGITS
     learnt
    0.45
     Told
    0.45
     kaarangay
    0.43
    said
    0.43
    say
    0.42
    mybatisplus
    0.42
     mukaan
    0.41
     relâche
    0.41
    Told
    0.41
     désolés
    0.40
    Act Density 0.012%

    No Known Activations