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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and transparency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leneck
    -0.46
    telar
    -0.46
    orElse
    -0.43
    sistente
    -0.41
    corer
    -0.40
    prechung
    -0.40
    wój
    -0.39
    baiki
    -0.39
    rably
    -0.38
    تيجة
    -0.37
    POSITIVE LOGITS
     disclosure
    1.03
     transparency
    0.98
     disclosing
    0.97
     secrecy
    0.97
     discloses
    0.95
     disclose
    0.92
     disclosed
    0.88
     Transparency
    0.87
     secretive
    0.86
     publicly
    0.86
    Act Density 0.561%

    No Known Activations