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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to returning or restoring to a previous state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kloped
    -0.73
    chaun
    -0.69
    MeasureSpec
    -0.68
     Voraus
    -0.66
    alsy
    -0.65
    pexpr
    -0.64
     dewasa
    -0.64
    ترنت
    -0.63
    choly
    -0.63
    contentLoaded
    -0.62
    POSITIVE LOGITS
     regaining
    1.07
     restoring
    1.05
     regain
    1.00
     restore
    0.98
     regained
    0.96
     restores
    0.96
     tornare
    0.95
     restored
    0.94
     back
    0.92
     reverting
    0.91
    Act Density 0.263%

    No Known Activations