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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a portion or quantity of something being shared or retained

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "of" indicating possession or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     notwithstanding
    -0.68
    wise
    -0.62
    aji
    -0.61
     confir
    -0.60
     lapt
    -0.58
     case
    -0.58
    gee
    -0.58
     redesign
    -0.57
     rematch
    -0.56
    urches
    -0.56
    POSITIVE LOGITS
    their
    0.92
     their
    0.79
    them
    0.73
    ãĥĩãĤ£
    0.73
     his
    0.72
    æ©
    0.72
    ãģĨ
    0.72
    THING
    0.71
     those
    0.69
     its
    0.68
    Act Density 0.134%

    No Known Activations