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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time and sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.15
     Anc
    -0.15
    310
    -0.15
     anc
    -0.14
    .insert
    -0.14
    nik
    -0.14
     Manning
    -0.14
     Ninh
    -0.14
     ÐĴи
    -0.14
    kowski
    -0.14
    POSITIVE LOGITS
    baugh
    0.16
    ande
    0.15
    eon
    0.15
    onnen
    0.15
    asion
    0.14
    ekil
    0.14
    ardi
    0.14
    wig
    0.14
    SystemService
    0.14
    asia
    0.14
    Act Density 0.472%

    No Known Activations