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

    Neuronpedia

    INDEX
    Explanations

    references to ethnic identity and cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akens
    -0.18
    exampleInput
    -0.16
    .ai
    -0.15
     incontri
    -0.15
    _AI
    -0.14
    ÙĦب
    -0.14
    ZX
    -0.14
    lrt
    -0.14
    Calibri
    -0.14
    utron
    -0.14
    POSITIVE LOGITS
     Rom
    0.58
     Roma
    0.51
    Rom
    0.43
     roma
    0.42
     ROM
    0.41
     rom
    0.40
    roma
    0.34
    rom
    0.34
    ROM
    0.34
    _ROM
    0.31
    Act Density 0.008%

    No Known Activations