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

    Neuronpedia

    INDEX
    Explanations

    physical actions or changes happening to an object or system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to actions or processes that imply movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clin
    -0.63
     redistributed
    -0.62
     Unc
    -0.60
     wil
    -0.60
     wont
    -0.58
     loos
    -0.58
     blurred
    -0.57
     applied
    -0.56
     Courtesy
    -0.56
     Looking
    -0.56
    POSITIVE LOGITS
    ify
    1.43
    ize
    1.34
    imize
    1.29
    ulate
    1.29
    iate
    1.19
    itate
    1.16
    strate
    1.16
    ise
    1.12
    uate
    1.11
    igrate
    1.09
    Act Density 0.367%

    No Known Activations