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

    Neuronpedia

    INDEX
    Explanations

    references to societal expectations and personal boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adol
    -0.17
    ernet
    -0.16
    że
    -0.16
    æ¨
    -0.15
    TPL
    -0.15
    ç¿Ķ
    -0.15
    emet
    -0.14
    amet
    -0.14
    emy
    -0.14
     ^{°}
    -0.14
    POSITIVE LOGITS
     shouldn
    0.46
     should
    0.33
    should
    0.32
     Should
    0.30
     ought
    0.30
    Should
    0.30
    .should
    0.27
     SHOULD
    0.26
    _should
    0.23
    åºĶ该
    0.23
    Act Density 0.189%

    No Known Activations