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

    Neuronpedia

    INDEX
    Explanations

    superlatives indicating extremity, such as "least"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "least" or the idea of minimalism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.75
     Reborn
    -0.72
    gnu
    -0.70
    xxxxxxxx
    -0.69
    SHIP
    -0.69
    raltar
    -0.67
    axter
    -0.66
    stru
    -0.66
     Journals
    -0.64
    clerosis
    -0.64
    POSITIVE LOGITS
    erest
    0.80
     toler
    0.79
     practicable
    0.79
     intrusive
    0.78
     bit
    0.78
     conceivable
    0.76
     amount
    0.75
     possible
    0.75
     detectable
    0.75
     imaginable
    0.72
    Act Density 0.020%

    No Known Activations