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

    Neuronpedia

    INDEX
    Explanations

    expressions related to literary and personal growth through revision

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

    would rather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obviously
    -0.56
     oczywiście
    -0.48
     Obviously
    -0.47
    Obviously
    -0.45
     Again
    -0.41
     again
    -0.41
     obviamente
    -0.40
    Again
    -0.40
     ovviamente
    -0.40
    obviously
    -0.40
    POSITIVE LOGITS
     חיצוניים
    0.65
    KURZBESCHREIBUNG
    0.65
     незавершена
    0.63
    GEBURTS
    0.63
     виправивши
    0.61
    InputBorder
    0.61
    ChildIndex
    0.59
     kasarigan
    0.59
     nonUne
    0.59
     GenerationType
    0.59
    Act Density 0.065%

    No Known Activations