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

    Neuronpedia

    INDEX
    Explanations

    references to diversity and scholarship programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trainer
    -0.15
     trainers
    -0.15
     trainer
    -0.15
    FlowLayout
    -0.15
     Sınıf
    -0.14
    trainer
    -0.14
    Inspectable
    -0.14
    ände
    -0.13
    mant
    -0.13
    Inspect
    -0.13
    POSITIVE LOGITS
     scholarships
    0.39
     scholarship
    0.39
     awards
    0.35
     Scholarship
    0.34
    sch
    0.32
     merit
    0.31
     Scholar
    0.31
     award
    0.29
    Sch
    0.29
     Awards
    0.28
    Act Density 0.068%

    No Known Activations