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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "perform" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.04
     lagoons
    -0.80
    ])+
    -0.79
    tslib
    -0.79
     kaynağından
    -0.77
     Ceb
    -0.77
    DbType
    -0.77
     BorderRadius
    -0.77
     Zat
    -0.75
     cedo
    -0.75
    POSITIVE LOGITS
     perform
    1.56
     PERFORM
    1.56
     performed
    1.56
     Perform
    1.53
    Perform
    1.51
    perform
    1.48
     Performing
    1.37
     performs
    1.36
     performances
    1.35
     performing
    1.33
    Act Density 0.098%

    No Known Activations