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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal principles and negligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.18
     houſe
    -1.17
     myſelf
    -1.16
     Majefty
    -1.16
     Monfieur
    -1.16
     المعيارى
    -1.15
     chofe
    -1.12
     raiſ
    -1.11
     ModelExpression
    -1.11
     Eſ
    -1.11
    POSITIVE LOGITS
     L
    0.61
    Lorem
    0.60
     adipis
    0.57
     inter
    0.54
     N
    0.50
     et
    0.49
     sit
    0.48
    ,
    0.47
     t
    0.47
     l
    0.45
    Act Density 0.042%

    No Known Activations