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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuation or lists

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

    lists ending with etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
     transfieras
    -0.83
     queſta
    -0.73
     ſta
    -0.71
    :✨
    -0.69
     Autorizaciones
    -0.66
    Бахар
    -0.65
     فريبيس
    -0.65
     ſte
    -0.64
     المعيارى
    -0.63
    POSITIVE LOGITS
     etc
    0.34
    .
    0.31
     such
    0.31
    GIVEREF
    0.30
    leggen
    0.29
    endregion
    0.28
     seguente
    0.27
     related
    0.27
     waż
    0.26
     skrive
    0.25
    Act Density 0.030%

    No Known Activations