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

    Neuronpedia

    INDEX
    Explanations

    occurrences of performance indicators or related metrics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tright
    -0.17
    p
    -0.15
    ür
    -0.15
    croft
    -0.15
    lette
    -0.14
    acin
    -0.14
    Äĩ
    -0.14
    c
    -0.14
    angan
    -0.14
    john
    -0.14
    POSITIVE LOGITS
    (s
    0.24
    (es
    0.17
    ellan
    0.16
    illin
    0.16
    ï¸ı
    0.15
    wards
    0.15
    æ´¥
    0.15
    еÑĢо
    0.14
    ¼
    0.14
    (#)
    0.14
    Act Density 0.010%

    No Known Activations