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

    Neuronpedia

    INDEX
    Explanations

    references to academic honors and societies

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

    academic honors and societies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.51
     industriale
    -0.47
     messaggi
    -0.47
     compositeur
    -0.46
    ⟬
    -0.46
    msgTypes
    -0.45
     industriales
    -0.45
     duquel
    -0.44
     trône
    -0.44
     producteur
    -0.42
    POSITIVE LOGITS
     enrollment
    0.52
     Gifted
    0.52
     Honors
    0.52
     Scholars
    0.48
    oredCriteria
    0.47
    Enroll
    0.46
     enroll
    0.46
     students
    0.45
     Honor
    0.45
     honor
    0.45
    Act Density 0.006%

    No Known Activations