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

    Neuronpedia

    INDEX
    Explanations

    terms related to training and educational supervision processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urity
    -0.14
    uros
    -0.14
    .dispatch
    -0.14
    ãģ¹ãģ¦
    -0.14
    ån
    -0.14
    sein
    -0.13
    kus
    -0.13
    Çİ
    -0.13
    urgeon
    -0.13
     imageSize
    -0.13
    POSITIVE LOGITS
     feedback
    0.24
     progress
    0.23
     Progress
    0.23
    -progress
    0.23
     performance
    0.22
     rub
    0.22
     summ
    0.21
     Performance
    0.21
     observation
    0.20
     Feedback
    0.20
    Act Density 0.045%

    No Known Activations