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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the string "ak"

    oai_token-act-pair · gpt-3.5-turbo

    words or names that contain the substring "ak"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pint
    -0.70
    drops
    -0.70
     Founders
    -0.63
     teasing
    -0.62
     balloons
    -0.61
     tears
    -0.61
     prost
    -0.59
     constituent
    -0.59
     coded
    -0.58
     redistributed
    -0.58
    POSITIVE LOGITS
    ota
    1.24
    arak
    1.21
    umar
    1.18
    ansas
    1.17
    ak
    1.16
    unin
    1.10
    unta
    1.10
    ame
    1.06
    udo
    1.05
    ushi
    1.04
    Act Density 0.016%

    No Known Activations