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

    Neuronpedia

    INDEX
    Explanations

    words or prefixes related to scientific or technical content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     to
    -0.68
     (
    -0.67
    .
    -0.66
     and
    -0.64
     time
    -0.64
     in
    -0.64
     възможно
    -0.64
     настоящий
    -0.63
     by
    -0.63
    ,
    -0.63
    POSITIVE LOGITS
     sappi
    1.87
     migli
    1.71
     abbra
    1.69
     incess
    1.68
     tramont
    1.65
     ritard
    1.65
     squa
    1.64
     erec
    1.63
     immen
    1.63
     embra
    1.63
    Act Density 0.360%

    No Known Activations