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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "start" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    startup
    -0.17
    asures
    -0.16
    alie
    -0.16
    Startup
    -0.15
    sey
    -0.15
    anzi
    -0.15
    omb
    -0.15
    ameda
    -0.14
    ories
    -0.14
    Time
    -0.14
    POSITIVE LOGITS
    /end
    0.29
    swith
    0.27
    -up
    0.25
    le
    0.23
    bucks
    0.23
    seite
    0.21
    tls
    0.21
    -off
    0.21
     off
    0.20
    -stop
    0.20
    Act Density 0.103%

    No Known Activations