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

    Neuronpedia

    INDEX
    Explanations

    specific characters, names, or identifiers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ht
    -0.16
     hood
    -0.16
    obot
    -0.16
    çijŁ
    -0.16
    duto
    -0.15
     bord
    -0.15
    jk
    -0.14
    ÙĬÙĦØ©
    -0.14
    964
    -0.14
    /lg
    -0.14
    POSITIVE LOGITS
    otton
    0.17
    aza
    0.15
    ema
    0.15
    iro
    0.15
    amba
    0.15
    rych
    0.15
    069
    0.14
    εÏĦ
    0.14
    Ñĥла
    0.14
    ãĥ³ãĥIJãĥ¼
    0.14
    Act Density 0.011%

    No Known Activations