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

    Neuronpedia

    INDEX
    Explanations

    references to cookies and cookie policies

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

    cookies and biscuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspect
    -0.35
     circumstance
    -0.34
    ---|
    -0.34
     Lincoln
    -0.33
    TextInputLayout
    -0.33
    Theo
    -0.33
     המק
    -0.33
     situation
    -0.33
     potential
    -0.33
     line
    -0.32
    POSITIVE LOGITS
     cookies
    2.36
     Cookies
    2.27
    Cookies
    2.20
    cookies
    2.20
     COOKIES
    1.89
     biscuits
    1.09
     COOKIE
    1.09
    COOKIE
    1.08
    🍪
    1.05
    クッキー
    1.02
    Act Density 0.003%

    No Known Activations