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

    Neuronpedia

    INDEX
    Explanations

    emphatic punctuation and expressions of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artner
    -0.15
    ylland
    -0.15
    avan
    -0.15
    onas
    -0.14
     Mej
    -0.14
    Ïģή
    -0.14
    дам
    -0.14
    деÑĤ
    -0.14
    urance
    -0.14
    unday
    -0.14
    POSITIVE LOGITS
    ola
    0.18
    690
    0.16
     Irving
    0.14
    OLA
    0.14
    097
    0.14
    817
    0.13
    253
    0.13
     ngang
    0.13
    addtogroup
    0.13
     ðŁĶ
    0.13
    Act Density 1.381%

    No Known Activations