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

    Neuronpedia

    INDEX
    Explanations

    strong, forceful actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "knock" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Situation
    -0.76
     Archives
    -0.76
    porting
    -0.74
     Offic
    -0.73
    rano
    -0.71
     Individuals
    -0.70
    mberg
    -0.70
     Celeb
    -0.70
     Complex
    -0.69
     Municip
    -0.68
    POSITIVE LOGITS
     knock
    1.27
     knocked
    0.99
     knocks
    0.96
     knocking
    0.95
    down
    0.94
     knockout
    0.86
     Knock
    0.81
    Maker
    0.80
    weed
    0.78
     inhibitor
    0.78
    Act Density 0.011%

    No Known Activations