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

    Neuronpedia

    INDEX
    Explanations

    words relating to employment or industry

    oai_token-act-pair · gemini-2.0-flash

    agricultural labor and workers

    np_token-act-pair-logits · gpt-4o-mini

    workers/labor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.52
    ruptedException
    -0.52
    こんばんは
    -0.48
     soi
    -0.48
     smtplib
    -0.48
    noks
    -0.47
     חיצוניים
    -0.46
    sträger
    -0.46
    RPD
    -0.46
    тьяна
    -0.45
    POSITIVE LOGITS
     farm
    0.69
     tartalomajánló
    0.63
     construction
    0.62
     labours
    0.60
     workers
    0.59
    wrk
    0.59
    contentLoaded
    0.58
     Construction
    0.58
    TagMode
    0.58
     agricultural
    0.57
    Act Density 2.220%

    No Known Activations