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

    Neuronpedia

    INDEX
    Explanations

    percentage values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /her
    -0.17
    OrUpdate
    -0.15
    ว
    -0.15
    ร
    -0.15
    ième
    -0.14
    oms
    -0.14
    est
    -0.14
    اÙĨت
    -0.14
    oom
    -0.13
    rike
    -0.13
    POSITIVE LOGITS
    /-
    0.23
    iles
    0.21
    raquo
    0.19
    nbsp
    0.19
    /$
    0.17
    /'
    0.17
    emsp
    0.17
     chance
    0.17
    ile
    0.17
    twenty
    0.17
    Act Density 0.065%

    No Known Activations