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

    Neuronpedia

    INDEX
    Explanations

    specific numerical codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    галÑĸ
    -0.17
    надлеж
    -0.16
    wo
    -0.15
    wi
    -0.15
    wa
    -0.15
     span
    -0.15
    leck
    -0.15
    åĿĽ
    -0.15
    one
    -0.14
    oro
    -0.14
    POSITIVE LOGITS
    еÑħ
    0.19
    ез
    0.19
    иг
    0.19
    ÑĢоÑģ
    0.18
    ÑĤÑı
    0.17
    леÑĤ
    0.17
    levant
    0.16
    ĭ
    0.16
    ÑĤа
    0.16
    .scalablytyped
    0.15
    Act Density 0.013%

    No Known Activations