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

    Neuronpedia

    INDEX
    Explanations

    phrases related to breaking rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "breaking the law."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eton
    -0.69
    geries
    -0.65
     hereafter
    -0.63
     Inquis
    -0.62
    oran
    -0.60
     Reserved
    -0.58
    eers
    -0.58
    reau
    -0.57
    rily
    -0.57
    utz
    -0.56
    POSITIVE LOGITS
     membranes
    0.79
     membrane
    0.74
     protocol
    0.73
     stride
    0.70
     cycle
    0.70
     seal
    0.70
     habit
    0.68
    advertisement
    0.67
     boundaries
    0.67
     brittle
    0.67
    Act Density 0.108%

    No Known Activations