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

    Neuronpedia

    INDEX
    Explanations

    the word "knock" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "knock."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.82
    rano
    -0.79
     Situation
    -0.73
     Sunrise
    -0.72
    RED
    -0.71
    emale
    -0.71
     Scotia
    -0.71
     Complex
    -0.70
     Municip
    -0.69
     Celeb
    -0.67
    POSITIVE LOGITS
     knock
    1.16
    down
    1.03
     knocked
    0.93
     knocking
    0.89
     knocks
    0.86
    kn
    0.81
     down
    0.81
    downs
    0.81
    weed
    0.80
    outs
    0.80
    Act Density 0.022%

    No Known Activations