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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by positive affirmations or compliments

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.73
    asio
    -0.72
    ¿½
    -0.67
    GMT
    -0.65
    emon
    -0.65
    eca
    -0.63
    abil
    -0.62
    ¶ħ
    -0.62
     Verge
    -0.61
    enges
    -0.60
    POSITIVE LOGITS
    're
    1.39
     guys
    1.36
    've
    1.06
    tub
    1.02
    'll
    0.99
     yourselves
    0.94
    'd
    0.90
     filthy
    0.85
     gotta
    0.84
    kai
    0.84
    Act Density 0.206%

    No Known Activations