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

    Neuronpedia

    INDEX
    Explanations

    Spanish language words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numeric data and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.85
    chwitz
    -0.74
    Reloaded
    -0.72
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.72
    yip
    -0.72
    Bench
    -0.71
    âĸĵ
    -0.68
    Arcade
    -0.68
     VIDE
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
    POSITIVE LOGITS
    ensis
    0.91
     tion
    0.83
    ude
    0.81
     Ãł
    0.81
     ib
    0.73
     ng
    0.71
     pour
    0.71
     faire
    0.70
    pd
    0.70
    ete
    0.69
    Act Density 0.189%

    No Known Activations