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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or titles related to individuals or groups, particularly those with the prefix "Dat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    542
    -0.15
    ÑĤий
    -0.15
    hart
    -0.15
    uart
    -0.15
    hol
    -0.14
    iano
    -0.14
     variant
    -0.14
    48
    -0.14
    ham
    -0.14
    ander
    -0.13
    POSITIVE LOGITS
    keley
    0.17
    .scal
    0.15
    kus
    0.15
    ÑĢиÑĦ
    0.15
    atat
    0.14
    oster
    0.14
    oint
    0.14
    uke
    0.14
    kili
    0.14
    ako
    0.14
    Act Density 0.009%

    No Known Activations