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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to the creation of entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "created."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thom
    -0.75
     Adin
    -0.74
    itte
    -0.66
    afa
    -0.62
    phia
    -0.60
     Mandatory
    -0.59
    uru
    -0.58
    cgi
    -0.56
     Krishna
    -0.55
    duty
    -0.55
    POSITIVE LOGITS
    女
    0.82
    ãĥ¼ãĥĨãĤ£
    0.79
    ãĤ´
    0.74
    smanship
    0.73
     havoc
    0.72
     srf
    0.72
     mL
    0.69
    ãĥĨãĤ£
    0.68
    ãĤº
    0.68
    monton
    0.67
    Act Density 0.031%

    No Known Activations