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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the creation of various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "created" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thom
    -0.71
     Mandatory
    -0.70
    itte
    -0.69
     Adin
    -0.68
    duty
    -0.66
    enger
    -0.62
    pled
    -0.61
     Buffett
    -0.59
    most
    -0.57
    cgi
    -0.57
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.85
    女
    0.77
    ãĥĨãĤ£
    0.74
    ovie
    0.73
    emis
    0.73
    ãĤº
    0.72
    smanship
    0.70
    æ©
    0.70
    ilts
    0.70
    Drag
    0.69
    Act Density 0.040%

    No Known Activations