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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical or scientific measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ~
    -0.17
     targeting
    -0.16
     upfront
    -0.16
     contrario
    -0.16
     prote
    -0.16
     dataset
    -0.16
     leveraging
    -0.15
     gender
    -0.15
     respective
    -0.14
     crafting
    -0.14
    POSITIVE LOGITS
    ä¹¾
    0.16
     Problems
    0.15
    _PROC
    0.15
    isz
    0.15
     Proble
    0.14
    adaÅŁ
    0.14
     problems
    0.14
    <quote
    0.14
     Procedures
    0.14
     problème
    0.14
    Act Density 0.079%

    No Known Activations