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

    Neuronpedia

    INDEX
    Explanations

    references to reproductive conditions or issues, especially involving abortion

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.72
    "}")
    -0.71
    basicConfig
    -0.69
     وتسجيلات
    -0.68
    hört
    -0.67
    sizeCache
    -0.61
     transfieras
    -0.60
     lccn
    -0.60
    nextProps
    -0.60
    ("")]
    -0.59
    POSITIVE LOGITS
     abortion
    2.89
     abortions
    2.34
    abortion
    2.14
     Abortion
    2.08
     aborto
    1.34
    WriteTagHelper
    0.69
     Abor
    0.69
     abor
    0.63
     aborted
    0.63
     abort
    0.62
    Act Density 0.001%

    No Known Activations