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

    Neuronpedia

    INDEX
    Explanations

    references to time and sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulong
    -0.15
    isas
    -0.15
    ruta
    -0.15
     componentName
    -0.14
    aze
    -0.14
    imore
    -0.14
    ustom
    -0.14
    ÙĦÙĬÙħ
    -0.14
    ÏĦοι
    -0.14
    isor
    -0.14
    POSITIVE LOGITS
     early
    0.42
    early
    0.40
     initial
    0.32
     earliest
    0.30
    Early
    0.29
     soon
    0.29
    æĹ©
    0.28
     Early
    0.28
     initially
    0.27
    æľĢåĪĿ
    0.25
    Act Density 0.241%

    No Known Activations