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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures within text data that demonstrate complexity or variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amarin
    -0.16
    aras
    -0.15
    leton
    -0.15
    acific
    -0.15
    ean
    -0.15
     Sanity
    -0.14
     Morr
    -0.14
    icip
    -0.14
    eid
    -0.14
    stream
    -0.14
    POSITIVE LOGITS
    ī
    0.16
    ем
    0.16
    áÄį
    0.15
    ön
    0.15
    erot
    0.15
    estic
    0.14
    anco
    0.14
    ware
    0.14
    urnal
    0.14
    mÄĽ
    0.14
    Act Density 0.014%

    No Known Activations