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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors indicating frequency or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ero
    -0.18
    urse
    -0.15
    é¡ĶãĤĴ
    -0.15
    ograms
    -0.14
    uters
    -0.14
    pic
    -0.14
    gba
    -0.14
    ramer
    -0.13
    jan
    -0.13
    uch
    -0.13
    POSITIVE LOGITS
    .appspot
    0.15
     factors
    0.15
    ĭ
    0.15
    磨
    0.14
     aside
    0.14
    etheless
    0.14
     reason
    0.14
     words
    0.14
    -One
    0.13
     other
    0.13
    Act Density 0.081%

    No Known Activations