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

    Neuronpedia

    INDEX
    Explanations

    terms related to rankings or scores in competitive settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [s
    -0.17
    enas
    -0.16
    dma
    -0.15
    ниÑĤ
    -0.15
    (s
    -0.14
    ÙijÙĦ
    -0.14
    rias
    -0.14
    alla
    -0.14
     mand
    -0.14
    ipa
    -0.14
    POSITIVE LOGITS
    ATO
    0.16
    signature
    0.15
    iday
    0.14
     Rim
    0.14
     ydk
    0.14
    Ùĩ
    0.14
    ÏĤ
    0.14
    çĨŁ
    0.14
    fol
    0.14
     erotici
    0.14
    Act Density 0.290%

    No Known Activations