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

    Neuronpedia

    INDEX
    Explanations

    dates and time references

    oai_token-act-pair · gpt-3.5-turbo

    references to fundraising or financial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cooldown
    -0.72
     distraction
    -0.64
     Complex
    -0.63
    Dialogue
    -0.63
    France
    -0.63
    imil
    -0.62
    ZI
    -0.61
    ../
    -0.60
    Italy
    -0.60
    #
    -0.60
    POSITIVE LOGITS
    ²¾
    1.10
     sure
    0.68
    uth
    0.66
    plin
    0.64
    lihood
    0.63
    leans
    0.62
    é¾įå¥ij士
    0.61
     whatsoever
    0.61
    alde
    0.61
    cipled
    0.60
    Act Density 0.000%

    No Known Activations