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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acher
    -0.16
    undles
    -0.15
    dit
    -0.15
    langs
    -0.15
    vari
    -0.14
    ksam
    -0.14
    оки
    -0.13
    yst
    -0.13
    akin
    -0.13
     saw
    -0.13
    POSITIVE LOGITS
     shall
    0.24
     Shall
    0.20
     SHALL
    0.18
     subparagraph
    0.17
    shall
    0.17
    ello
    0.16
    ilot
    0.16
     Compact
    0.15
     dors
    0.15
    ingly
    0.15
    Act Density 0.173%

    No Known Activations