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

    Neuronpedia

    INDEX
    Explanations

    structured JSON elements within a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     McLaugh
    -0.96
     ujedno
    -0.91
     kompres
    -0.82
     kriminal
    -0.79
     silikon
    -0.79
     mikrofon
    -0.79
     unlaw
    -0.78
     Vaugh
    -0.76
     konflik
    -0.75
     Punj
    -0.75
    POSITIVE LOGITS
     bonjour
    0.85
     jaja
    0.81
     nè
    0.77
     appétit
    0.76
     desideri
    0.74
     ?</
    0.74
     ã
    0.73
     frambo
    0.73
    ?«
    0.72
     diable
    0.71
    Act Density 0.076%

    No Known Activations