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

    Neuronpedia

    INDEX
    Explanations

    mandatory legal language or terms related to obligations in legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.41
     myſelf
    -1.30
     Monfieur
    -1.25
     themſelves
    -1.24
     itſelf
    -1.22
     chofe
    -1.15
     Anſ
    -1.14
     Efq
    -1.13
     Majefty
    -1.12
     Jefus
    -1.11
    POSITIVE LOGITS
     shall
    0.97
    ,
    0.73
    ↵↵
    0.68
    .
    0.66
     (
    0.65
     and
    0.63
     I
    0.62
     will
    0.62
     
    0.62
    ↵
    0.60
    Act Density 0.148%

    No Known Activations