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

    Neuronpedia

    INDEX
    Explanations

    references to feedback mechanisms and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trovi
    -0.70
    IpAddress
    -0.68
     Byers
    -0.64
    depuis
    -0.63
     Tull
    -0.62
    expandindo
    -0.59
     Kras
    -0.59
     hy
    -0.58
     dit
    -0.57
    prox
    -0.56
    POSITIVE LOGITS
     feedback
    1.10
     ujednoznacz
    1.06
    HasForeignKey
    1.01
     callbacks
    1.00
     Callback
    0.99
    feedback
    0.98
     useCallback
    0.97
     Feedback
    0.93
     callback
    0.92
     feedbacks
    0.90
    Act Density 0.074%

    No Known Activations