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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate completeness or fullness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    replete with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsxFileName
    -0.46
     userSchema
    -0.43
     vectorielle
    -0.43
     plufieurs
    -0.40
    courir
    -0.40
     Steering
    -0.40
    steering
    -0.40
     Keuangan
    -0.40
     precedenti
    -0.39
    AnimationsModule
    -0.39
    POSITIVE LOGITS
     dilengkapi
    0.69
     כולל
    0.66
     inclusief
    0.62
     include
    0.59
     includes
    0.58
     včetně
    0.57
     replete
    0.57
    พร้อม
    0.57
    包括
    0.57
     inklusive
    0.56
    Act Density 0.005%

    No Known Activations