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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "knocking" or "knockdowns."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onde
    -0.17
    ogr
    -0.15
    ɵ
    -0.15
    ccione
    -0.15
    ÑĢава
    -0.15
    .Promise
    -0.14
     Rosenstein
    -0.14
    rophe
    -0.14
    uite
    -0.14
    ulo
    -0.14
    POSITIVE LOGITS
     knock
    0.31
     Knock
    0.29
     knocks
    0.27
     knocked
    0.27
     knocking
    0.26
    Kn
    0.26
    kn
    0.25
    down
    0.25
    -k
    0.22
     sense
    0.20
    Act Density 0.010%

    No Known Activations