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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cringe
    -0.78
     chats
    -0.75
     flashbacks
    -0.71
     kios
    -0.70
     menus
    -0.70
     Skype
    -0.70
     authorization
    -0.69
     invitations
    -0.68
     mandatory
    -0.68
     chat
    -0.68
    POSITIVE LOGITS
    ^{
    1.65
    _{
    1.48
    \)
    1.44
     {\
    1.39
    +(
    1.39
    âĪĴ
    1.39
    $$
    1.37
    /(
    1.33
    )=
    1.31
     âĪĴ
    1.29
    Act Density 0.082%

    No Known Activations