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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks within sentences and phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements of narrative and dialogue structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á¹
    -0.83
     rap
    -0.79
     Xperia
    -0.77
    Pool
    -0.77
     Loll
    -0.77
     maternal
    -0.77
    ÅĤ
    -0.77
     Hearthstone
    -0.75
    imes
    -0.75
     bronze
    -0.74
    POSITIVE LOGITS
     Hughes
    2.40
    Hug
    2.03
     Horowitz
    1.34
     Hug
    1.29
     Hugo
    1.26
     Welch
    1.24
     Robertson
    1.22
     Phillips
    1.21
     Schneider
    1.21
     Hubbard
    1.21
    Act Density 0.339%

    No Known Activations