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

    Neuronpedia

    INDEX
    Explanations

    references to emotional moments or states

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -1.36
     unspeak
    -1.33
     depic
    -1.30
     reluct
    -1.29
     apprehen
    -1.28
     disagre
    -1.28
     hentai
    -1.25
     impra
    -1.23
     intersper
    -1.23
     maneu
    -1.19
    POSITIVE LOGITS
     everywhere
    0.72
     uska
    0.60
     betweenstory
    0.58
     Walkover
    0.58
    hidden
    0.57
    onViewCreated
    0.56
     apellidos
    0.55
     hidden
    0.55
     actionMode
    0.55
    neté
    0.55
    Act Density 0.452%

    No Known Activations