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

    Neuronpedia

    INDEX
    Explanations

    variations of the letter "s" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    к
    -0.19
    ohn
    -0.18
    м
    -0.18
    umed
    -0.17
    ording
    -0.17
    umi
    -0.17
    tek
    -0.17
    SC
    -0.16
    ig
    -0.16
    ам
    -0.16
    POSITIVE LOGITS
     pec
    0.24
     tart
    0.22
    izable
    0.20
    ot
    0.20
    rat
    0.20
    izer
    0.20
     mart
    0.19
    art
    0.19
    ä¸Ī
    0.18
    izing
    0.18
    Act Density 0.270%

    No Known Activations