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

    Neuronpedia

    INDEX
    Explanations

    relevant information by searching and finding specific terms or data in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of discovery or retrieval of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     salute
    -0.78
    ISION
    -0.75
    stroke
    -0.69
     halftime
    -0.67
    Exit
    -0.65
    Chief
    -0.64
    inth
    -0.63
    ornings
    -0.62
     disrupting
    -0.59
     disrupt
    -0.59
    POSITIVE LOGITS
     Wikipedia
    1.49
     wik
    1.41
     youtube
    1.41
     websites
    1.38
     google
    1.33
     blogs
    1.32
     tutorials
    1.30
     forums
    1.28
     datas
    1.28
     Youtube
    1.28
    Act Density 0.494%

    No Known Activations