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

    Neuronpedia

    INDEX
    Explanations

    concepts related to morality and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    distinguishing from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.48
    -0.46
    læg
    -0.43
    zingen
    -0.40
     inconsist
    -0.40
     обе
    -0.39
    vább
    -0.39
     Paglinawan
    -0.38
    Curse
    -0.38
    asantry
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    0.56
    RenderAtEndOf
    0.50
    IsContent
    0.48
    complexContent
    0.47
    iastes
    0.46
     gynhyrchwyd
    0.45
    🟤
    0.42
    indd
    0.42
     ")");
    0.41
     pédagogique
    0.40
    Act Density 0.117%

    No Known Activations