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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming and technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to processes and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tains
    -0.73
     Breed
    -0.66
     Lauder
    -0.62
     Laz
    -0.62
    iates
    -0.60
     CFL
    -0.59
    Were
    -0.58
    ivism
    -0.57
     Outside
    -0.57
    otonin
    -0.55
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.91
     è£ıè
    0.82
    alde
    0.81
    ãĥīãĥ©
    0.76
    Reviewer
    0.76
    EStream
    0.76
    ãĥ´
    0.74
    MpServer
    0.74
    ãĥ´ãĤ¡
    0.72
    ãģ®éŃĶ
    0.71
    Act Density 0.703%

    No Known Activations