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

    Neuronpedia

    INDEX
    Explanations

    phrases with repeated pronouns such as "you", "your", and "You" alongside personal reflections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipal
    -0.69
     airs
    -0.63
    ¿½
    -0.63
    ice
    -0.63
     Chap
    -0.63
     Gamb
    -0.58
    icy
    -0.57
     Samoa
    -0.57
    ãĥ³ãĤ¸
    -0.57
    assembly
    -0.56
    POSITIVE LOGITS
    're
    1.61
     guys
    1.35
    've
    1.35
    tub
    1.30
    'll
    1.28
     guessed
    1.16
    'd
    1.08
     yourselves
    1.01
     know
    1.00
    RS
    0.98
    Act Density 0.987%

    No Known Activations