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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating past habitual actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    llons
    -0.55
     المعيارى
    -0.52
    dures
    -0.49
    nesc
    -0.47
    AYLOR
    -0.46
    -0.44
    thè
    -0.44
    annique
    -0.44
     протягом
    -0.44
    ukunfts
    -0.43
    POSITIVE LOGITS
     ftu
    0.91
     perfon
    0.89
    «<
    0.89
     juft
    0.89
     feen
    0.87
     »>
    0.87
     fta
    0.86
     ftre
    0.86
     fep
    0.86
     tranf
    0.84
    Act Density 0.159%

    No Known Activations