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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and data-related terms

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

    work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.73
     betweenstory
    -0.68
    Hozzáférés
    -0.63
    styleType
    -0.62
     الحره
    -0.61
    Tembelea
    -0.59
    AISSEE
    -0.59
     EconPapers
    -0.56
     AssemblyTitle
    -0.56
     createSlice
    -0.56
    POSITIVE LOGITS
     work
    0.85
     works
    0.78
    work
    0.75
    works
    0.69
     working
    0.69
     opere
    0.63
     Works
    0.63
     worker
    0.63
     WORK
    0.61
    工作
    0.60
    Act Density 0.045%

    No Known Activations