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

    Neuronpedia

    INDEX
    Explanations

    references to degrees and educational qualifications

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

    academic degree programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTHOOK
    -0.54
    feuer
    -0.48
    armen
    -0.47
     Barbar
    -0.47
     Simons
    -0.46
    orange
    -0.46
    WriteTagHelper
    -0.45
     Tim
    -0.44
    TIM
    -0.44
     Kenner
    -0.44
    POSITIVE LOGITS
     degree
    0.65
     Degrees
    0.62
     Degree
    0.61
     degrees
    0.60
     diploma
    0.59
    Degree
    0.59
     DEGREE
    0.56
    学位
    0.56
    Degrees
    0.56
    degree
    0.54
    Act Density 0.004%

    No Known Activations