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

    Neuronpedia

    INDEX
    Explanations

    advice and suggestions related to dating and relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.89
     quoique
    -0.86
     viciss
    -0.79
     inconce
    -0.77
     reluct
    -0.76
    Rgds
    -0.74
     bourgeo
    -0.73
    Ehh
    -0.72
     impractica
    -0.71
     Ikke
    -0.71
    POSITIVE LOGITS
     alike
    0.64
    <bos>
    0.62
     दोनों
    0.52
    vestres
    0.50
    .
    0.48
    ﷺ
    0.48
     respectively
    0.47
     throughout
    0.46
    OrWhiteSpace
    0.46
     sowie
    0.46
    Act Density 0.356%

    No Known Activations