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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or references to other content

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" used in various contexts, often indicating options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocrats
    -0.79
    ocracy
    -0.71
    ocratic
    -0.70
    OTAL
    -0.69
    ires
    -0.63
    emen
    -0.63
    prints
    -0.63
    emet
    -0.62
    itbart
    -0.61
    ocrat
    -0.61
    POSITIVE LOGITS
    chard
    1.33
    Else
    1.27
    acle
    1.25
    chid
    1.19
    ifice
    1.15
    nam
    1.11
    acles
    1.09
    ific
    1.06
    GAN
    1.03
     alternatively
    1.03
    Act Density 0.180%

    No Known Activations