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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe enjoyable or fun activities, experiences, or components

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

    describing something as fun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ControllerAdvice
    -0.52
     silêncio
    -0.47
    ModelSerializer
    -0.44
    ceğine
    -0.44
     profundamente
    -0.42
    Scénario
    -0.41
     necesitamos
    -0.40
     zijne
    -0.40
     gyhoeddwyd
    -0.40
     profundo
    -0.39
    POSITIVE LOGITS
     fun
    1.49
     FUN
    1.21
    Fun
    1.21
    fun
    1.18
     Fun
    1.16
    FUN
    1.13
     divertido
    1.05
     diversión
    1.03
     divertida
    0.99
     divertidos
    0.93
    Act Density 0.023%

    No Known Activations