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

    Neuronpedia

    INDEX
    Explanations

    security verification prompts to confirm if the user is human

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user verification or identity confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wonderland
    -0.68
    oft
    -0.68
     Canaver
    -0.67
     DRAG
    -0.63
    NetMessage
    -0.60
     hints
    -0.58
     auctions
    -0.58
    pport
    -0.57
     alike
    -0.57
    è¦ļéĨĴ
    -0.56
    POSITIVE LOGITS
    're
    0.74
    ve
    0.73
    email
    0.70
    iciency
    0.68
    RS
    0.68
    cise
    0.66
     verify
    0.64
    nos
    0.63
    orce
    0.62
    urrency
    0.62
    Act Density 0.025%

    No Known Activations