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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../../../
    -0.30
    ../../
    -0.24
    ../
    -0.22
    ../../../../
    -0.19
    ãĥ¼ãĥĬ
    -0.19
    fold
    -0.18
    äºĮäºĮ
    -0.17
    bast
    -0.17
    th
    -0.17
    tega
    -0.16
    POSITIVE LOGITS
    nd
    0.59
    -thirds
    0.40
    nds
    0.32
    gether
    0.29
    ND
    0.28
     dozen
    0.28
     nd
    0.27
     thirds
    0.27
    /th
    0.27
    nde
    0.23
    Act Density 0.583%

    No Known Activations