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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated characters or syllables in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arter
    -0.17
    ve
    -0.17
    atur
    -0.15
    ething
    -0.15
    icas
    -0.14
     consequ
    -0.14
    fal
    -0.14
     arter
    -0.14
     moreover
    -0.14
    ий
    -0.14
    POSITIVE LOGITS
    ÑĢониÑĩеÑģ
    0.19
    atron
    0.19
    elts
    0.19
    stor
    0.17
    ylland
    0.16
    érica
    0.16
    asn
    0.16
    еÑĢ
    0.15
    зд
    0.15
    ónico
    0.15
    Act Density 0.012%

    No Known Activations