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

    Neuronpedia

    INDEX
    Explanations

    references to legal violations and breaches of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     illegal
    -0.66
     Colle
    -0.64
     banned
    -0.61
    joba
    -0.61
    Colle
    -0.60
     fortune
    -0.59
     Lein
    -0.58
     Illegal
    -0.57
    > 
    -0.57
     Compulsory
    -0.56
    POSITIVE LOGITS
     violation
    2.12
    violation
    1.86
     Violation
    1.83
     violations
    1.82
     violate
    1.67
     violating
    1.65
     violated
    1.64
     Violations
    1.62
     violates
    1.50
    Violation
    1.41
    Act Density 0.105%

    No Known Activations