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

    Neuronpedia

    INDEX
    Explanations

    references to employment and internships, particularly focusing on hiring practices and compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.02
    2:0.15
    3:0.06
    4:0.04
    5:0.11
    6:0.06
    7:0.06
    8:0.05
    9:0.11
    10:0.06
    11:0.05
    Negative Logits
     sentencing
    -2.91
    aband
    -2.70
     prosecuting
    -2.57
     decriminal
    -2.54
     outlawed
    -2.53
     divorce
    -2.52
     pur
    -2.51
     confisc
    -2.50
     indict
    -2.49
     paraph
    -2.49
    POSITIVE LOGITS
     internship
    6.38
     interns
    5.45
    Intern
    5.13
     Intern
    5.00
     intern
    4.85
    intern
    4.82
     NYU
    3.40
     Volunte
    3.14
    )=(
    3.10
    chell
    3.05
    Act Density 0.002%

    No Known Activations