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

    Neuronpedia

    INDEX
    Explanations

    references to the origin of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </b>
    -0.73
    </i>
    -0.69
     setState
    -0.58
    owulf
    -0.58
    ագրություններ
    -0.58
    <b>
    -0.56
    dymyr
    -0.56
     Cowper
    -0.56
    weeney
    -0.55
    Munich
    -0.55
    POSITIVE LOGITS
     Origin
    1.78
     origin
    1.76
     Origins
    1.73
     origins
    1.72
    Origin
    1.71
    origin
    1.65
    Origins
    1.57
    origins
    1.53
     ORIGIN
    1.52
     originates
    1.47
    Act Density 0.130%

    No Known Activations