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

    Neuronpedia

    INDEX
    Explanations

    comments and notes pertaining to coding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    “
    -0.19
    ’
    -0.18
    your
    -0.17
    Your
    -0.17
     yourselves
    -0.17
    âĢ¦.
    -0.17
    âĢ¦âĢ¦
    -0.16
    YOUR
    -0.16
     Your
    -0.16
    ‘
    -0.16
    POSITIVE LOGITS
     ↵
    0.27
     */↵
    0.24
     FIXME
    0.22
     `_
    0.20
     {@
    0.20
    */↵
    0.20
     `
    0.19
     *)↵
    0.18
     ...)↵
    0.18
     TODO
    0.18
    Act Density 0.603%

    No Known Activations