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

    Neuronpedia

    INDEX
    Explanations

    references to small or seemingly insignificant details and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.17
     Hun
    -0.17
    /store
    -0.15
    ثار
    -0.14
     nÃło
    -0.14
     trunk
    -0.14
    obar
    -0.14
    ught
    -0.13
    .SuspendLayout
    -0.13
     Circular
    -0.13
    POSITIVE LOGITS
    /small
    0.20
    çIJ
    0.16
    -small
    0.16
     small
    0.16
    çij
    0.16
     detail
    0.15
    itol
    0.15
     Details
    0.15
    encil
    0.15
    оÑĢаз
    0.15
    Act Density 0.131%

    No Known Activations