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

    Neuronpedia

    INDEX
    Explanations

    short phrases indicating progression or continuation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Argumento
    -0.60
    Vedi
    -0.57
    Inoltre
    -0.56
    katapos
    -0.55
    Contactez
    -0.55
    Avez
    -0.55
    Eksteraj
    -0.54
    Sinopse
    -0.54
    NamedQueries
    -0.52
     kemer
    -0.52
    POSITIVE LOGITS
     ALONG
    1.13
     along
    0.98
    along
    0.96
     Along
    0.93
     reluct
    0.92
     milf
    0.92
    Along
    0.90
     shenan
    0.90
     madonna
    0.87
     scrat
    0.85
    Act Density 0.088%

    No Known Activations