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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives that include the word "high"

    oai_token-act-pair · gemini-2.0-flash

    the word "high"

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

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.66
     חיצוניים
    -0.57
     &___
    -0.56
    rungsseite
    -0.55
     שוליים
    -0.55
    LEIA
    -0.54
    ografija
    -0.53
     postIndex
    -0.53
    Hochspringen
    -0.52
    المناصب
    -0.51
    POSITIVE LOGITS
     End
    0.52
     end
    0.52
    end
    0.50
    End
    0.49
    ViewImports
    0.47
    barung
    0.47
     league
    0.47
     profile
    0.46
    brido
    0.46
     END
    0.45
    Act Density 0.253%

    No Known Activations