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

    Neuronpedia

    INDEX
    Explanations

    references to cookies and cookie-related policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.93
    ArrowToggle
    -0.91
    +#+#
    -0.77
    bootstrapcdn
    -0.76
     '\\;'
    -0.76
    رشف
    -0.74
     activations
    -0.69
    InvalidProtocol
    -0.67
     Sodom
    -0.67
    oa̍t
    -0.67
    POSITIVE LOGITS
     cookie
    1.07
    cookie
    0.97
     Cookie
    0.94
    Cookies
    0.90
     cookies
    0.87
     Cookies
    0.87
    Cookie
    0.84
     COOKIE
    0.72
    COOKIE
    0.69
    cookies
    0.68
    Act Density 0.036%

    No Known Activations