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

    Neuronpedia

    INDEX
    Explanations

    comparisons and discussions of quantity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ιλο
    -0.15
    овеÑĢ
    -0.15
    ismet
    -0.15
    á»ĵng
    -0.14
     говоÑĢиÑĤÑĮ
    -0.14
    uffer
    -0.14
    ldb
    -0.14
    lob
    -0.13
    ubi
    -0.13
    DMI
    -0.13
    POSITIVE LOGITS
     beyond
    0.50
     Beyond
    0.42
     besides
    0.40
    Beyond
    0.38
    eyond
    0.36
     além
    0.35
     oltre
    0.31
     Besides
    0.26
     other
    0.25
    éĻ¤äºĨ
    0.25
    Act Density 0.177%

    No Known Activations