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

    Neuronpedia

    INDEX
    Explanations

    references to abortion and related advocacy positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elta
    -0.17
    izik
    -0.17
     Sleep
    -0.15
    aç
    -0.15
    ansen
    -0.15
     Vladim
    -0.14
     Spl
    -0.14
     sleep
    -0.14
    amer
    -0.14
    addir
    -0.14
    POSITIVE LOGITS
     abortion
    0.29
    -abortion
    0.24
     abortions
    0.23
     Roe
    0.19
     Doe
    0.18
     gest
    0.18
    gnu
    0.18
     trimest
    0.17
     Gest
    0.17
    Abort
    0.17
    Act Density 0.156%

    No Known Activations