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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a verb indicating a state or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "you are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.72
    ionics
    -0.71
     è£ıè
    -0.64
    offs
    -0.64
     )]
    -0.63
    Discuss
    -0.62
    rates
    -0.62
    Eastern
    -0.61
    osate
    -0.61
    Others
    -0.61
    POSITIVE LOGITS
     hereby
    0.92
     yourself
    0.92
     yourselves
    0.90
     gonna
    0.90
     aware
    0.83
     lucky
    0.82
     able
    0.81
     obligated
    0.80
     obliged
    0.79
     bound
    0.77
    Act Density 0.105%

    No Known Activations