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

    Neuronpedia

    INDEX
    Explanations

    numerical data or references in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viso
    -0.17
    les
    -0.16
    eka
    -0.15
    aravel
    -0.14
    acher
    -0.14
    agini
    -0.14
    tes
    -0.14
    ije
    -0.14
     Yin
    -0.14
     vul
    -0.13
    POSITIVE LOGITS
     leaf
    0.15
    essian
    0.14
     Throw
    0.14
    ühl
    0.14
    .scalablytyped
    0.14
    _DT
    0.14
    丸
    0.14
    hoc
    0.13
    iram
    0.13
     Dahl
    0.13
    Act Density 0.001%

    No Known Activations