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

    Neuronpedia

    INDEX
    Explanations

    numeric values and numerical patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    old
    -0.18
    nds
    -0.17
    ounds
    -0.17
    nd
    -0.17
    /is
    -0.16
    ephir
    -0.16
    ãģĺ
    -0.16
    byss
    -0.16
    isper
    -0.15
    chwitz
    -0.15
    POSITIVE LOGITS
    teenth
    0.24
    teen
    0.17
    ëģĶ
    0.17
    -HT
    0.16
    th
    0.16
    bread
    0.15
    fold
    0.15
    rou
    0.15
    Thirty
    0.15
    ÐĨÐĨ
    0.14
    Act Density 0.349%

    No Known Activations