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

    Neuronpedia

    INDEX
    Explanations

    names or terms containing "Sus"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named "Susana" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.91
     overhead
    -0.77
     living
    -0.72
     learning
    -0.71
     sorting
    -0.68
     inertia
    -0.64
     projecting
    -0.64
     tuning
    -0.63
    ingo
    -0.63
    OPLE
    -0.63
    POSITIVE LOGITS
    annah
    1.21
    pect
    1.10
    pected
    1.10
    pir
    1.02
    pic
    1.00
    pects
    0.95
    pecting
    0.95
    Sus
    0.89
    ethe
    0.87
    ki
    0.87
    Act Density 0.011%

    No Known Activations