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

    Neuronpedia

    INDEX
    Explanations

    terms related to compliance with rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adherence to rules or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Healing
    -0.71
     whirlwind
    -0.71
    ury
    -0.67
     Onion
    -0.64
    amon
    -0.63
    saw
    -0.60
     Tip
    -0.60
     Torch
    -0.59
     Roots
    -0.58
    Mem
    -0.58
    POSITIVE LOGITS
     comply
    3.52
     complied
    2.56
     complying
    2.49
     compliance
    1.93
     obey
    1.93
     compliant
    1.84
    compliance
    1.71
     abide
    1.69
     conform
    1.64
     adhere
    1.55
    Act Density 0.015%

    No Known Activations