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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political titles and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oples
    -0.15
    خص
    -0.15
    .fhir
    -0.15
    央
    -0.15
    Mixin
    -0.14
    μο
    -0.14
    جÙĦ
    -0.14
    icks
    -0.14
    lanan
    -0.14
    oftware
    -0.14
    POSITIVE LOGITS
    airo
    0.16
    erras
    0.16
    ··
    0.15
    Å¡ek
    0.15
    VECTOR
    0.15
    ade
    0.14
    ãĤ¦ãĤ§
    0.14
     metab
    0.14
    vak
    0.14
    atz
    0.14
    Act Density 0.013%

    No Known Activations