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

    Neuronpedia

    INDEX
    Explanations

    numerical references and rankings within statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sto
    -0.15
    -quarters
    -0.15
    st
    -0.15
    boom
    -0.14
    odor
    -0.14
     Theme
    -0.14
    -thirds
    -0.14
    ÌĨ
    -0.14
    ruz
    -0.13
    viz
    -0.13
    POSITIVE LOGITS
    th
    0.91
    TH
    0.42
    ths
    0.42
     th
    0.41
    thon
    0.38
    thy
    0.36
    thic
    0.35
    thro
    0.34
    thin
    0.34
    teenth
    0.34
    Act Density 0.057%

    No Known Activations