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

    Neuronpedia

    INDEX
    Explanations

    references to historical oppression and racial dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BlockSize
    -0.15
    uve
    -0.15
     Sexo
    -0.15
    pok
    -0.15
    708
    -0.15
    CAF
    -0.14
    bjerg
    -0.14
    맥
    -0.14
    asje
    -0.14
    (Edit
    -0.14
    POSITIVE LOGITS
     Revolutionary
    0.15
     plantation
    0.15
     legally
    0.14
    kers
    0.14
     plant
    0.14
     Plant
    0.13
    etty
    0.13
    inus
    0.13
    _keeper
    0.13
     pathology
    0.13
    Act Density 0.041%

    No Known Activations