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

    Neuronpedia

    INDEX
    Explanations

    links or prompts to check something out

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage checking out resources or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ade
    -0.71
    amphetamine
    -0.69
    matter
    -0.69
    MpServer
    -0.67
     cumbers
    -0.67
    channelAvailability
    -0.65
    ajor
    -0.64
    wig
    -0.63
    quickShipAvailable
    -0.62
    Nevertheless
    -0.60
    POSITIVE LOGITS
     our
    1.07
     these
    1.00
     how
    0.92
     what
    0.91
     some
    0.90
     my
    0.86
     pics
    0.85
     this
    0.84
     screenshots
    0.81
     whats
    0.80
    Act Density 0.059%

    No Known Activations