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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to the second person pronoun "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensable
    -0.65
    ween
    -0.62
    ipal
    -0.61
    icy
    -0.60
    ector
    -0.60
    states
    -0.60
     Strikes
    -0.58
    ;;;;;;;;;;;;
    -0.57
    Champ
    -0.57
    ilts
    -0.56
    POSITIVE LOGITS
    're
    1.33
    tub
    1.16
    've
    1.14
    'll
    1.07
     guys
    1.06
    'd
    0.90
     guessed
    0.88
     hear
    0.88
    kai
    0.86
     yourselves
    0.86
    Act Density 0.149%

    No Known Activations