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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ethics and moral decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    immers
    -0.15
     ener
    -0.15
    apiro
    -0.15
    akeup
    -0.14
     Franti
    -0.14
    lisi
    -0.14
    é«ĺéĢŁ
    -0.14
     screwed
    -0.14
    æ´²
    -0.14
    çĿ
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.17
    esian
    0.15
    Fallback
    0.15
    FromString
    0.14
     commitment
    0.14
     commitments
    0.14
     Davidson
    0.13
    arel
    0.13
    itemap
    0.13
    æĢĿ
    0.13
    Act Density 0.059%

    No Known Activations