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

    Neuronpedia

    INDEX
    Explanations

    references to legal concepts or violations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal matters and the concept of law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.72
    pread
    -0.69
    xit
    -0.68
     Gree
    -0.67
     Pocket
    -0.65
    vae
    -0.65
     Stretch
    -0.62
     sqor
    -0.62
     pockets
    -0.61
    ittle
    -0.61
    POSITIVE LOGITS
     enforcement
    1.21
     Enforcement
    1.01
    breakers
    0.99
    enforcement
    0.98
     abiding
    0.97
    fulness
    0.97
    suit
    0.95
    lessness
    0.93
    breaker
    0.90
    breaking
    0.89
    Act Density 0.034%

    No Known Activations