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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and employment contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argar
    -0.18
    ourd
    -0.16
    mez
    -0.15
    Outlined
    -0.15
    .writeln
    -0.15
    uvre
    -0.14
    ç»Ĩ
    -0.14
    .jasper
    -0.14
    arg
    -0.13
    oha
    -0.13
    POSITIVE LOGITS
     shall
    0.40
     Shall
    0.31
    shall
    0.30
     shalt
    0.23
     SHALL
    0.23
     embraced
    0.22
     embracing
    0.20
     her
    0.19
     hereby
    0.19
     whenever
    0.19
    Act Density 0.167%

    No Known Activations