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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the importance of certain actions or concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlaw
    -0.87
     ?...
    -0.87
     !...
    -0.81
     accla
    -0.80
     invin
    -0.76
     hentai
    -0.76
     „,
    -0.76
     pubg
    -0.75
     milf
    -0.75
     depic
    -0.75
    POSITIVE LOGITS
    Билгалдахарш
    0.52
    expandindo
    0.50
    kleber
    0.49
    StructEnd
    0.48
    browserify
    0.47
     aspect
    0.46
    glMatrixMode
    0.46
    之一
    0.46
    PyExc
    0.45
     ever
    0.44
    Act Density 0.270%

    No Known Activations