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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and key phrases that indicate legal or formal obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _WP
    -0.14
    bond
    -0.14
    füg
    -0.14
    LD
    -0.14
     Sting
    -0.14
     exclus
    -0.14
    rite
    -0.14
    olumn
    -0.14
    ÄĽÅ¾
    -0.14
    sta
    -0.13
    POSITIVE LOGITS
    utow
    0.17
    در
    0.16
     SHR
    0.16
    iap
    0.14
    ollo
    0.14
     hall
    0.14
    adf
    0.13
    itations
    0.13
    ney
    0.13
    orial
    0.13
    Act Density 0.006%

    No Known Activations