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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or procedural concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kova
    -0.19
    pur
    -0.16
    esub
    -0.15
    itto
    -0.14
    製
    -0.14
    reur
    -0.14
    .capture
    -0.14
     pur
    -0.14
    åĢĴ
    -0.14
    wat
    -0.14
    POSITIVE LOGITS
    iar
    0.16
    adh
    0.15
     cih
    0.14
    oss
    0.14
    Ïĥα
    0.14
    uai
    0.14
    ingly
    0.14
     Grund
    0.13
    SPA
    0.13
    ucc
    0.13
    Act Density 0.004%

    No Known Activations