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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "simple" or related forms that convey simplicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.50
    Karriere
    -0.49
     tenure
    -0.46
    HostException
    -0.44
     befind
    -0.44
     Rptr
    -0.43
    InStock
    -0.43
     prestaciones
    -0.43
     notamment
    -0.43
     Tenure
    -0.43
    POSITIVE LOGITS
     simple
    1.16
     Simple
    1.09
    Simple
    1.08
    simple
    1.07
     SIMPLE
    1.02
     semplici
    0.98
    SIMPLE
    0.98
     simples
    0.97
     einfachen
    0.91
     simpl
    0.90
    Act Density 0.038%

    No Known Activations