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

    Neuronpedia

    INDEX
    Explanations

    comparative language indicating degree or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allon
    -0.16
    ziel
    -0.16
    ibox
    -0.14
    createUrl
    -0.14
    autoreleasepool
    -0.13
    rende
    -0.13
    lauf
    -0.13
    outh
    -0.13
     Clarence
    -0.13
     æĦĽ
    -0.13
    POSITIVE LOGITS
     than
    0.28
    -than
    0.23
    than
    0.22
    Than
    0.21
     Than
    0.20
     THAN
    0.20
    _than
    0.20
     rather
    0.18
     Rather
    0.18
    rather
    0.17
    Act Density 0.124%

    No Known Activations