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

    Neuronpedia

    INDEX
    Explanations

    numerical lists in the form of advice or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tips and advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.68
    Ń·
    -0.67
    status
    -0.65
    mson
    -0.65
    aos
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    ebook
    -0.64
    onel
    -0.63
    ourning
    -0.63
    ulsion
    -0.63
    POSITIVE LOGITS
     you
    0.92
    hooting
    0.90
     worth
    0.89
     pertaining
    0.84
     beginners
    0.82
     YOU
    0.79
     Helpful
    0.79
     outlining
    0.75
     recommended
    0.75
     why
    0.72
    Act Density 0.253%

    No Known Activations