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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "novel" that indicate new or innovative ideas, concepts, or findings

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

    novel concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.64
     informée
    -0.51
     المعيارى
    -0.50
     Roskov
    -0.49
     estekak
    -0.48
    ⟬
    -0.48
     castor
    -0.47
     Phosphate
    -0.47
     mascara
    -0.47
    counted
    -0.47
    POSITIVE LOGITS
     novel
    1.90
    Novel
    1.73
     Novel
    1.70
    novel
    1.61
     NOVEL
    1.55
     novelty
    1.12
     Novelty
    0.91
     noved
    0.91
     Novels
    0.87
     novels
    0.82
    Act Density 0.010%

    No Known Activations