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

    Neuronpedia

    INDEX
    Explanations

    terms related to violations and infringement of laws or rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŀĿ
    -0.18
    arde
    -0.15
    irit
    -0.14
    AREST
    -0.14
    ëĬIJ
    -0.14
    anou
    -0.14
    ToSelector
    -0.14
    orro
    -0.14
    ourg
    -0.14
    onde
    -0.14
    POSITIVE LOGITS
     principles
    0.19
     norms
    0.18
     integrity
    0.17
     rules
    0.17
     by
    0.17
     laws
    0.17
    0.15
     trust
    0.15
     privacy
    0.15
     code
    0.15
    Act Density 0.071%

    No Known Activations