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

    Neuronpedia

    INDEX
    Explanations

    references to education and scholarship achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pension
    -0.16
    anus
    -0.14
    azu
    -0.14
     DISCLAIMS
    -0.14
     retired
    -0.14
    ume
    -0.14
     Retirement
    -0.14
    ichick
    -0.14
    stery
    -0.14
    usan
    -0.14
    POSITIVE LOGITS
     studying
    0.20
     intern
    0.18
     majors
    0.17
     major
    0.17
     stud
    0.17
     finish
    0.17
     competing
    0.17
     plans
    0.17
     studies
    0.17
     recent
    0.17
    Act Density 0.102%

    No Known Activations