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

    Neuronpedia

    INDEX
    Explanations

    words related to psychological and medical symptoms and treatments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.81
    698
    -0.64
    bourg
    -0.58
     Sparkle
    -0.57
    nesday
    -0.57
     Ket
    -0.56
     kernels
    -0.56
     Kro
    -0.56
     Perspective
    -0.55
     Merge
    -0.55
    POSITIVE LOGITS
    achment
    0.85
    uments
    0.83
    ãĥ¼ãĤ¯
    0.83
    lycer
    0.73
    inately
    0.73
    ãĥĥãĥĪ
    0.73
    acers
    0.73
    ãĥ¼ãĥ«
    0.73
    cientious
    0.72
    acl
    0.71
    Act Density 0.156%

    No Known Activations