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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "knock" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onde
    -0.16
    anch
    -0.14
    ths
    -0.14
    ÑĢава
    -0.14
    igned
    -0.14
    .Promise
    -0.14
    ccione
    -0.14
    reuse
    -0.14
    raison
    -0.14
     Beste
    -0.13
    POSITIVE LOGITS
     knock
    0.39
     Knock
    0.36
     knocks
    0.34
     knocking
    0.33
     knocked
    0.33
    Kn
    0.31
    kn
    0.31
    down
    0.25
    -k
    0.24
     Kn
    0.23
    Act Density 0.011%

    No Known Activations