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

    Neuronpedia

    INDEX
    Explanations

    references to restrictions on weapons, violence, and laws surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anskje
    -0.72
     "..\..\..\
    -0.66
    󠁢
    -0.65
     myſelf
    -0.64
     الرياضيه
    -0.63
    atigable
    -0.62
    </tfoot>
    -0.61
    INSEE
    -0.60
    MemoryWarning
    -0.60
    ]")]
    -0.59
    POSITIVE LOGITS
     allowed
    2.47
     permitted
    2.33
     Allowed
    2.15
    allowed
    2.11
    Allowed
    1.94
     ALLOWED
    1.88
    permitted
    1.84
     prohibited
    1.84
     forbidden
    1.81
     permissible
    1.80
    Act Density 0.607%

    No Known Activations