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

    Neuronpedia

    INDEX
    Explanations

    references to creating and sharing joyful memories and experiences

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

    laughter and fun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    日閲覧
    -0.44
    ErrUnexpectedEOF
    -0.43
    semitism
    -0.40
    MigrationBuilder
    -0.39
    mago
    -0.39
    véni
    -0.39
     discouraging
    -0.38
     Washing
    -0.38
    bosis
    -0.38
    pology
    -0.37
    POSITIVE LOGITS
     memories
    0.64
    SharedCtor
    0.58
     adventures
    0.54
    numerusform
    0.54
    memories
    0.52
     auroit
    0.52
     laughs
    0.52
     moments
    0.51
     avoient
    0.50
     laughter
    0.49
    Act Density 0.019%

    No Known Activations