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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparative assessments and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ
    -0.17
    alle
    -0.17
     Jes
    -0.16
    icz
    -0.15
    365
    -0.15
    wan
    -0.14
     collateral
    -0.14
    es
    -0.14
     Parr
    -0.14
    oje
    -0.14
    POSITIVE LOGITS
    vit
    0.19
    виÑĤ
    0.15
     ÙħÙĨÙĩا
    0.15
    μαι
    0.14
    má
    0.14
    émon
    0.14
    unca
    0.14
    éĬ
    0.14
    vant
    0.14
    getSingleton
    0.14
    Act Density 0.228%

    No Known Activations