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

    Neuronpedia

    INDEX
    Explanations

    names of individuals mentioned in news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indo
    -0.63
    abase
    -0.63
    catentry
    -0.61
     contrace
    -0.60
    itiveness
    -0.59
    >[
    -0.58
    apor
    -0.56
     prelim
    -0.56
    atto
    -0.56
     sexes
    -0.55
    POSITIVE LOGITS
    velt
    0.69
    eworthy
    0.69
    ¿
    0.68
    ħĭ
    0.67
    aiden
    0.67
    hani
    0.65
    bery
    0.64
    Collins
    0.63
     Celt
    0.63
     Myster
    0.63
    Act Density 0.088%

    No Known Activations