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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical measurements like height, width, and depth

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -1.35
     reluct
    -1.33
     accla
    -1.32
     intersper
    -1.29
     shenan
    -1.25
     maneu
    -1.25
     philanth
    -1.24
     encomp
    -1.22
     increa
    -1.19
     inev
    -1.19
    POSITIVE LOGITS
     width
    0.86
     depth
    0.84
    width
    0.79
    Width
    0.77
    depth
    0.74
     height
    0.72
     density
    0.70
    height
    0.69
     thickness
    0.68
     дописавши
    0.66
    Act Density 0.162%

    No Known Activations