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

    Neuronpedia

    INDEX
    Explanations

    elements of quality and style in writing

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

    quality of writing and prose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    therlands
    -0.48
    Clik
    -0.46
    Viited
    -0.43
    setVerticalGroup
    -0.43
     unsuccessfully
    -0.42
     CanadaChoose
    -0.42
    ungsbedingungen
    -0.42
    arrings
    -0.41
     незавершена
    -0.41
    şit
    -0.41
    POSITIVE LOGITS
     prose
    0.59
     writing
    0.57
     literary
    0.56
     readability
    0.54
     poetic
    0.52
     littéraire
    0.51
     scrittura
    0.49
     written
    0.49
     écrite
    0.48
     poetry
    0.48
    Act Density 0.024%

    No Known Activations