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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "learned" in various contexts

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

    learned information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mutiny
    -0.53
     hypnosis
    -0.51
     witchcraft
    -0.51
     pleaſure
    -0.50
    涤
    -0.50
     houſe
    -0.49
    werkstatt
    -0.49
     desmotivaciones
    -0.49
     autopsy
    -0.48
     prostitution
    -0.48
    POSITIVE LOGITS
     learned
    1.95
    learned
    1.94
     Learned
    1.84
    Lear
    1.19
     learnt
    1.09
     aprendido
    0.99
     LEARN
    0.95
     gelernt
    0.80
    LEARN
    0.75
     gained
    0.73
    Act Density 0.032%

    No Known Activations